MyArxiv

2026-04-01

Sound 9

☆ FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining

Xiquan Li, Xuenan Xu, Ziyang Ma, Wenxi Chen, Haolin He, Qiuqiang Kong, Xie Chen

Contrastively pretrained audio-language models (e.g., CLAP) excel at clip-level understanding but struggle with frame-level tasks. Existing extensions fail to exploit the varying granularity of real-world audio-text data, where massive clip-level textual descriptions coexist with limited frame-level annotations. This paper proposes Fine-grained Language-Audio Pretraining (FineLAP), a novel training paradigm that advances both clip- and frame-level alignment in CLAP with heterogeneous data. FineLAP introduces a dual-stream sigmoid loss with a cluster-based sampling strategy to jointly learn from clip- and frame-level supervision. To capture both global semantics and local details, FineLAP uses a decoupled audio projector on top of a self-supervised encoder. To alleviate the scarcity of temporally annotated data, we present FineLAP-100k, a large-scale synthetic SED dataset constructed through a scalable curation pipeline. Extensive experiments demonstrate that FineLAP achieves SOTA performance across multiple audio understanding tasks, including retrieval, classification, sound event detection, and text-to-audio grounding. Ablation studies further show that coarse- and fine-grained alignment are mutually beneficial, providing insights for building better audio-language models (ALMs).

☆ TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models

Awais Khan, Muhammad Umar Farooq, Kutub Uddin, Khalid Malik

Partial audio deepfakes, where synthesized segments are spliced into genuine recordings, are particularly deceptive because most of the audio remains authentic. Existing detectors are supervised: they require frame-level annotations, overfit to specific synthesis pipelines, and must be retrained as new generative models emerge. We argue that this supervision is unnecessary. We hypothesize that speech foundation models implicitly encode a forensic signal: genuine speech forms smooth, slowly varying embedding trajectories, while splice boundaries introduce abrupt disruptions in frame-level transitions. Building on this, we propose TRACE (Training-free Representation-based Audio Countermeasure via Embedding dynamics), a training-free framework that detects partial audio deepfakes by analyzing the first-order dynamics of frozen speech foundation model representations without any training, labeled data, or architectural modification. We evaluate TRACE on four benchmarks that span two languages using six speech foundation models. In PartialSpoof, TRACE achieves 8.08% EER, competitive with fine-tuned supervised baselines. In LlamaPartialSpoof, the most challenging benchmark featuring LLM-driven commercial synthesis, TRACE surpasses a supervised baseline outright (24.12% vs. 24.49% EER) without any target-domain data. These results show that temporal dynamics in speech foundation models provide an effective, generalize signal for training-free audio forensics.

☆ Sona: Real-Time Multi-Target Sound Attenuation for Noise Sensitivity

Jeremy Zhengqi Huang, Emani Hicks, Sidharth, Gillian R. Hayes, Dhruv Jain

For people with noise sensitivity, everyday soundscapes can be overwhelming. Existing tools such as active noise cancellation reduce discomfort by suppressing the entire acoustic environment, often at the cost of awareness of surrounding people and events. We present Sona, an interactive mobile system for real-time soundscape mediation that selectively attenuates bothersome sounds while preserving desired audio. Sona is built on a target-conditioned neural pipeline that supports simultaneous attenuation of multiple overlapping sound sources, overcoming the single-target limitation of prior systems. It runs in real time on-device and supports user-extensible sound classes through in-situ audio examples, without retraining. Sona is informed by a formative study with 68 noise-sensitive individuals. Through technical benchmarking and an in-situ study with 10 participants, we show that Sona achieves low-latency, multi-target attenuation suitable for live listening, and enables meaningful reductions in bothersome sounds while maintaining awareness of surroundings. These results point toward a new class of personal AI systems that support comfort and social participation by mediating real-world acoustic environments.

comment: 12 pages, 6 figures

♻ ☆ Enhancing Infant Crying Detection with Gradient Boosting for Improved Emotional and Mental Health Diagnostics

Kyunghun Lee, Lauren M. Henry, Eleanor Hansen, Elizabeth Tandilashvili, Lauren S. Wakschlag, Elizabeth Norton, Daniel S. Pine, Melissa A. Brotman, Francisco Pereira

Infant crying can serve as a crucial indicator of various physiological and emotional states. This paper introduces a comprehensive approach detecting infant cries within audio data. We integrate Wav2Vec with traditional audio features and employ Gradient Boosting Machines for cry classification. We validate our approach on a real world dataset, demonstrating significant performance improvements over existing methods.

♻ ☆ Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics

Yangyang Qu, Massimiliano Todisco, Chiara Galdi, Nicholas Evans

Voice biometric systems can exhibit sex-related performance gaps even when overall verification accuracy is strong. We attribute these gaps to two practical mechanisms: (i) demographic shortcut learning, where speaker classification training exploits spurious correlations between sex and speaker identity, and (ii) feature entanglement, where sex-linked acoustic variation overlaps with identity cues and cannot be removed without degrading speaker discrimination. We propose Fair-Gate, a fairness-aware and interpretable risk-gating framework that addresses both mechanisms in a single pipeline. Fair-Gate applies risk extrapolation to reduce variation in speaker-classification risk across proxy sex groups, and introduces a local complementary gate that routes intermediate features into an identity branch and a sex branch. The gate provides interpretability by producing an explicit routing mask that can be inspected to understand which features are allocated to identity versus sex-related pathways. Experiments on VoxCeleb1 show that Fair-Gate improves the utility--fairness trade-off, yielding more sex-fair ASV performance under challenging evaluation conditions.

♻ ☆ DuoTok: Source-Aware Dual-Track Tokenization for Multi-Track Music Language Modeling

Rui Lin, Zhiyue Wu, Jiahe Le, Kangdi Wang, Weixiong Chen, Junyu Dai, Tao Jiang

Audio tokenization bridges continuous waveforms and multi-track music language models. In dual-track modeling, tokens should preserve three properties at once: high-fidelity reconstruction, strong predictability under a language model, and cross-track correspondence. We introduce DuoTok, a source-aware dual-track tokenizer that addresses this trade-off through staged disentanglement. DuoTok first pretrains a semantic encoder, then regularizes it with multi-task supervision, freezes the encoder, and applies hard dual-codebook routing while keeping auxiliary objectives on quantized codes. A diffusion decoder reconstructs high-frequency details, allowing tokens to focus on structured information for sequence modeling. On standard benchmarks, DuoTok achieves a favorable predictability-fidelity trade-off, reaching the lowest cnBPT while maintaining competitive reconstruction at 0.75 kbps. Under a held-constant dual-track language modeling protocol, enBPT also improves, indicating gains beyond codebook size effects. Controlled diagnostics show larger predictability costs under cross-track corruption and larger gains from longer context, suggesting that models trained on DuoTok tokens use cross-track structure and non-local history.

comment: 17 pages, 5 figures, 8 tables. Project page: https://eps-acoustic-revolution-lab.github.io/DUO_TOK/

♻ ☆ CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluation

Huan Shen, Yingao Wang, Shangkun Huang, Wei Zou, Yunzhang Chen

Turn-taking modeling is fundamental to spoken dialogue systems, yet its evaluation remains fragmented and often limited to binary boundary detection under narrow interaction settings. Such protocols hinder systematic comparison and obscure model weaknesses across conversational conditions. We present CoDeTT, a context-aware decision benchmark for turn-taking evaluation. CoDeTT formulates turn-taking as a structured decision problem and constructs a multi-scenario dataset with fine-grained decision categories and controlled context variations. Under a unified evaluation protocol, we assess representative existing models and observe substantial performance disparities across decision types and interaction scenarios. CoDeTT provides a standardized benchmark for systematic and context-aware evaluation of turn-taking systems. The benchmark dataset and evaluation toolkit are available at https://yingaowang-casia.github.io/CoDeTT.github.io/.

comment: Submitted to Interspeech 2026

♻ ☆ MATHDance: Mamba-Transformer Architecture with Uniform Tokenization for High-Quality 3D Dance Generation

Kaixing Yang, Xulong Tang, Ziqiao Peng, Yuxuan Hu, Xiangyue Zhang, Puwei Wang, Hongyan Liu, Jun He, Zhaoxin Fan

Music-to-dance generation represents a challenging yet pivotal task at the intersection of choreography, virtual reality, and creative content generation. Despite its significance, existing methods face substantial limitation in achieving choreographic consistency. To address the challenge, we propose MatchDance, a novel framework for music-to-dance generation that constructs a latent representation to enhance choreographic consistency. MatchDance employs a two-stage design: (1) a Kinematic-Dynamic-based Quantization Stage (KDQS), which encodes dance motions into a latent representation by Finite Scalar Quantization (FSQ) with kinematic-dynamic constraints and reconstructs them with high fidelity, and (2) a Hybrid Music-to-Dance Generation Stage(HMDGS), which uses a Mamba-Transformer hybrid architecture to map music into the latent representation, followed by the KDQS decoder to generate 3D dance motions. Additionally, a music-dance retrieval framework and comprehensive metrics are introduced for evaluation. Extensive experiments on the FineDance dataset demonstrate state-of-the-art performance.

♻ ☆ Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability

Xiaoxu Zhu, Junhua Li, Aaron J. Li, Guangchao Yao, Xiaojie Yu

Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks through supposedly anonymized representations. We present two contributions to address these challenges. First, we develop InterpTRQE-SptME (Timbre Residual Quantitative Evaluation Benchmark of Speech pre-training Models Encoding via Interpretability), a benchmark that directly measures residual speaker information in content embeddings using SHAP-based interpretability analysis. Unlike existing indirect metrics, our approach quantifies the exact proportion of speaker information remaining after disentanglement. Second, we propose InterpTF-SptME, which uses these interpretability insights to filter speaker information from embeddings. Testing on VCTK with seven models including HuBERT, WavLM, and ContentVec, we find that SHAP Noise filtering reduces speaker residuals from 18.05% to nearly zero while maintaining recognition accuracy (CTC loss increase under 1%). The method is model-agnostic and requires no retraining.

comment: 5 pages, 4 figures

Audio and Speech Processing 11

☆ Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separation ICASSP 2026

Yun-Ning, Hung, Richard Vogl, Filip Korzeniowski, Igor Pereira

While diffusion models are best known for their performance in generative tasks, they have also been successfully applied to many other tasks, including audio source separation. However, current generative approaches to music source separation often underperform on standard objective metrics. In this paper, we address this issue by introducing a novel generative vocal separation model based on the Elucidated Diffusion Model (EDM) framework. Our model processes complex short-time Fourier transform spectrograms and employs an improved U-Net architecture based on music-informed design choices. Our approach matches discriminative baselines on objective metrics and achieves perceptual quality comparable to state-of-the-art systems, as assessed by proxy subjective metrics. We hope these results encourage broader exploration of generative methods for music source separation

comment: Accepted at ICASSP 2026

☆ VisG AV-HuBERT: Viseme-Guided AV-HuBERT

Aristeidis Papadopoulos, Rishabh Jain, Naomi Harte

Audio-Visual Speech Recognition (AVSR) systems nowadays integrate Large Language Model (LLM) decoders with transformer-based encoders, achieving state-of-the-art results. However, the relative contributions of improved language modelling versus enhanced audiovisual encoding remain unclear. We propose Viseme-Guided AV-HuBERT (VisG AV-HuBERT), a multi-task fine-tuning framework that incorporates auxiliary viseme classification to strengthen the model's reliance on visual articulatory features. By extending AV-HuBERT with a lightweight viseme prediction sub-network, this method explicitly guides the encoder to preserve visual speech information. Evaluated on LRS3, VisG AV-HuBERT achieves comparable or improved performance over the baseline AV-HuBERT, with notable gains under heavy noise conditions. WER reduces from 13.59% to 6.60% (51.4% relative improvement) at -10 dB Signal-to-Noise Ratio (SNR) for Speech noise. Deeper analysis reveals substantial reductions in substitution errors across noise types, demonstrating improved speech unit discrimination. Evaluation on LRS2 confirms generalization capability. Our results demonstrate that explicit viseme modelling enhances encoder representations, and provides a foundation for enhancing noise-robust AVSR through encoder-level improvements.

comment: Includes Supplementary Material. Accepted for Publication at International Conference on Pattern Recognition 2026 - ICPR 2026. Code is available at https://github.com/aristosp/visg_avhubert

☆ Description and Discussion on DCASE 2026 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes

Masahiro Yasuda, Binh Thien Nguyen, Noboru Harada, Romain Serizel, Mayank Mishra, Marc Delcroix, Carlos Hernandez-Olivan, Shoko Araki, Daiki Takeuchi, Tomohiro Nakatani, Nobutaka Ono

This paper presents an overview of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2026 Challenge Task 4, Spatial Semantic Segmentation of Sound Scenes (S5). The S5 task focuses on the joint detection and separation of sound events in complex spatial audio mixtures, contributing to the foundation of immersive communication. First introduced in DCASE 2025, the S5 task continues in DCASE 2026 Task 4 with key changes to better reflect real-world conditions, including allowing mixtures to contain multiple sources of the same class and to contain no target sources. In this paper, we describe task setting, along with the corresponding updates to the evaluation metrics and dataset. The experimental results of the submitted systems are also reported and analyzed. The official access point for data and code is https://github.com/nttcslab/dcase2026_task4_baseline.

☆ OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models

Han Zhu, Lingxuan Ye, Wei Kang, Zengwei Yao, Liyong Guo, Fangjun Kuang, Zhifeng Han, Weiji Zhuang, Long Lin, Daniel Povey

We present OmniVoice, a massive multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discrete non-autoregressive (NAR) architecture. Unlike conventional discrete NAR models that suffer from performance bottlenecks in complex two-stage (text-to-semantic-to-acoustic) pipelines, OmniVoice directly maps text to multi-codebook acoustic tokens. This simplified approach is facilitated by two key technical innovations: (1) a full-codebook random masking strategy for efficient training, and (2) initialization from a pre-trained LLM to ensure superior intelligibility. By leveraging a 581k-hour multilingual dataset curated entirely from open-source data, OmniVoice achieves the broadest language coverage to date and delivers state-of-the-art performance across Chinese, English, and diverse multilingual benchmarks. Our code and pre-trained models are publicly available at https://github.com/k2-fsa/OmniVoice.

♻ ☆ Enhancing Infant Crying Detection with Gradient Boosting for Improved Emotional and Mental Health Diagnostics

Kyunghun Lee, Lauren M. Henry, Eleanor Hansen, Elizabeth Tandilashvili, Lauren S. Wakschlag, Elizabeth Norton, Daniel S. Pine, Melissa A. Brotman, Francisco Pereira

♻ ☆ Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics

Yangyang Qu, Massimiliano Todisco, Chiara Galdi, Nicholas Evans

♻ ☆ Measuring Prosody Diversity in Zero-Shot TTS: A New Metric, Benchmark, and Exploration ICASSP 2026

Yifan Yang, Bing Han, Hui Wang, Long Zhou, Wei Wang, Mingyu Cui, Xu Tan, Xie Chen

Prosody diversity is essential for achieving naturalness and expressiveness in zero-shot text-to-speech (TTS). However, frequently used acoustic metrics capture only partial views of prosodic variation and correlate poorly with human perception, leaving the problem of reliably quantifying prosody diversity underexplored. To bridge this gap, we introduce ProsodyEval, a prosody diversity assessment dataset that provides Prosody Mean Opinion Score (PMOS) alongside conventional acoustic metrics. ProsodyEval comprises 1000 speech samples derived from 7 mainstream TTS systems, with 2000 human ratings. Building on this, we propose the Discretized Speech Weighted Edit Distance (DS-WED), a new objective diversity metric that quantifies prosodic variation via weighted edit distance over semantic tokens. Experiments on ProsodyEval show that DS-WED achieves substantially higher correlation with human judgments than existing acoustic metrics, while remaining highly robust in speech tokenization from HuBERT and WavLM. Leveraging DS-WED, we benchmark state-of-the-art open-source TTS systems on LibriSpeech test-clean and Seed-TTS test-en, and further explorations uncover several factors that influence prosody diversity, including generative modeling paradigms, duration control, and reinforcement learning. Moreover, we find that current large audio language models (LALMs) remain limited in capturing prosodic variations. Audio samples are available at https://prosodyeval.github.io.

comment: Accepted in ICASSP 2026

♻ ☆ MATHDance: Mamba-Transformer Architecture with Uniform Tokenization for High-Quality 3D Dance Generation

Kaixing Yang, Xulong Tang, Ziqiao Peng, Yuxuan Hu, Xiangyue Zhang, Puwei Wang, Hongyan Liu, Jun He, Zhaoxin Fan

♻ ☆ How Open is Open TTS? A Practical Evaluation of Open Source TTS Tools

Teodora Răgman, Adrian Bogdan Stânea, Horia Cucu, Adriana Stan

Open-source text-to-speech (TTS) frameworks have emerged as highly adaptable platforms for developing speech synthesis systems across a wide range of languages. However, their applicability is not uniform -- particularly when the target language is under-resourced or when computational resources are constrained. In this study, we systematically assess the feasibility of building novel TTS models using four widely adopted open-source architectures: FastPitch, VITS, Grad-TTS, and Matcha-TTS. Our evaluation spans multiple dimensions, including qualitative aspects such as ease of installation, dataset preparation, and hardware requirements, as well as quantitative assessments of synthesis quality for Romanian. We employ both objective metrics and subjective listening tests to evaluate intelligibility, speaker similarity, and naturalness of the generated speech. The results reveal significant challenges in tool chain setup, data preprocessing, and computational efficiency, which can hinder adoption in low-resource contexts. By grounding the analysis in reproducible protocols and accessible evaluation criteria, this work aims to inform best practices and promote more inclusive, language-diverse TTS development. All information needed to reproduce this study (i.e. code and data) are available in our git repository: https://gitlab.com/opentts_ragman/OpenTTS

comment: Published in IEEE Access https://ieeexplore.ieee.org/document/11269795

♻ ☆ Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability

Xiaoxu Zhu, Junhua Li, Aaron J. Li, Guangchao Yao, Xiaojie Yu

comment: 5 pages, 4 figures

♻ ☆ Robust Residual Finite Scalar Quantization for Neural Compression

Xiaoxu Zhu, Xiaojie Yu, Guangchao Yao, Yiming Ren, Baoxiang Li

Finite Scalar Quantization (FSQ) offers simplified training but suffers from residual magnitude decay in multi-stage settings, where subsequent stages receive exponentially weaker signals. We propose Robust Residual Finite Scalar Quantization (RFSQ), addressing this fundamental limitation through two novel conditioning strategies: learnable scaling factors and invertible layer normalization. Our experiments across audio and image modalities demonstrate RFSQ's effectiveness and generalizability. In audio reconstruction at 24 bits/frame, RFSQ-LayerNorm achieves 3.646 DNSMOS, a 3.6% improvement over state-of-the-art RVQ (3.518). On ImageNet, RFSQ achieves 0.102 L1 loss and 0.100 perceptual loss, with LayerNorm providing 9.7% L1 improvement and 17.4% perceptual improvement over unconditioned variants. The LayerNorm strategy consistently outperforms alternatives by maintaining normalized input statistics across stages, effectively preventing exponential magnitude decay that limits naive residual approaches. RFSQ combines FSQ's simplicity with multi-stage quantization's representational power, establishing a new standard for neural compression across diverse modalities.

comment: 5 pages, 2 figures

Computer Vision and Pattern Recognition 150

☆ HippoCamp: Benchmarking Contextual Agents on Personal Computers

Zhe Yang, Shulin Tian, Kairui Hu, Shuai Liu, Hoang-Nhat Nguyen, Yichi Zhang, Zujin Guo, Mengying Yu, Zinan Zhang, Jingkang Yang, Chen Change Loy, Ziwei Liu

We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management. Unlike existing agent benchmarks that focus on tasks like web interaction, tool use, or software automation in generic settings, HippoCamp evaluates agents in user-centric environments to model individual user profiles and search massive personal files for context-aware reasoning. Our benchmark instantiates device-scale file systems over real-world profiles spanning diverse modalities, comprising 42.4 GB of data across over 2K real-world files. Building upon the raw files, we construct 581 QA pairs to assess agents' capabilities in search, evidence perception, and multi-step reasoning. To facilitate fine-grained analysis, we provide 46.1K densely annotated structured trajectories for step-wise failure diagnosis. We evaluate a wide range of state-of-the-art multimodal large language models (MLLMs) and agentic methods on HippoCamp. Our comprehensive experiments reveal a significant performance gap: even the most advanced commercial models achieve only 48.3% accuracy in user profiling, struggling particularly with long-horizon retrieval and cross-modal reasoning within dense personal file systems. Furthermore, our step-wise failure diagnosis identifies multimodal perception and evidence grounding as the primary bottlenecks. Ultimately, HippoCamp exposes the critical limitations of current agents in realistic, user-centric environments and provides a robust foundation for developing next-generation personal AI assistants.

comment: Project Page: https://hippocamp-ai.github.io/

☆ LAtent Phase Inference from Short time sequences using SHallow REcurrent Decoders (LAPIS-SHRED)

Yuxuan Bao, Xingyue Zhang, J. Nathan Kutz

Reconstructing full spatio-temporal dynamics from sparse observations in both space and time remains a central challenge in complex systems, as measurements can be spatially incomplete and can be also limited to narrow temporal windows. Yet approximating the complete spatio-temporal trajectory is essential for mechanistic insight and understanding, model calibration, and operational decision-making. We introduce LAPIS-SHRED (LAtent Phase Inference from Short time sequence using SHallow REcurrent Decoders), a modular architecture that reconstructs and/or forecasts complete spatiotemporal dynamics from sparse sensor observations confined to short temporal windows. LAPIS-SHRED operates through a three-stage pipeline: (i) a SHRED model is pre-trained entirely on simulation data to map sensor time-histories into a structured latent space, (ii) a temporal sequence model, trained on simulation-derived latent trajectories, learns to propagate latent states forward or backward in time to span unobserved temporal regions from short observational time windows, and (iii) at deployment, only a short observation window of hyper-sparse sensor measurements from the true system is provided, from which the frozen SHRED model and the temporal model jointly reconstruct or forecast the complete spatiotemporal trajectory. The framework supports bidirectional inference, inherits data assimilation and multiscale reconstruction capabilities from its modular structure, and accommodates extreme observational constraints including single-frame terminal inputs. We evaluate LAPIS-SHRED on six experiments spanning complex spatio-temporal physics: turbulent flows, multiscale propulsion physics, volatile combustion transients, and satellite-derived environmental fields, highlighting a lightweight, modular architecture suited for operational settings where observation is constrained by physical or logistical limitations.

☆ TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking

Jiyuan Hu, Zechuan Zhang, Zongxin Yang, Yi Yang

We present TRACE, a mesh-guided 3DGS editing framework that achieves automated, high-fidelity scene transformation. By anchoring video diffusion with explicit 3D geometry, TRACE uniquely enables fine-grained, part-level manipulatio--such as local pose shifting or component replacemen--while preserving the structural integrity of the central subject, a capability largely absent in existing editing methods. Our approach comprises three key stages: (1) Multi-view 3D-Anchor Synthesis, which leverages a sparse-view editor trained on our MV-TRACE datase--the first multi-view consistent dataset dedicated to scene-coherent object addition and modificatio--to generate spatially consistent 3D-anchors; (2) Tangible Geometry Anchoring (TGA), which ensures precise spatial synchronization between inserted meshes and the 3DGS scene via two-phase registration; and (3) Contextual Video Masking (CVM), which integrates 3D projections into an autoregressive video pipeline to achieve temporally stable, physically-grounded rendering. Extensive experiments demonstrate that TRACE consistently outperforms existing methods especially in editing versatility and structural integrity.

comment: 22 pages, 9 figures

☆ Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction

Jorge Condor, Nicolas Moenne-Loccoz, Merlin Nimier-David, Piotr Didyk, Zan Gojcic, Qi Wu

Primitive-based methods such as 3D Gaussian Splatting have recently become the state-of-the-art for novel-view synthesis and related reconstruction tasks. Compared to neural fields, these representations are more flexible, adaptive, and scale better to large scenes. However, the limited expressivity of individual primitives makes modeling high-frequency detail challenging. We introduce Neural Harmonic Textures, a neural representation approach that anchors latent feature vectors on a virtual scaffold surrounding each primitive. These features are interpolated within the primitive at ray intersection points. Inspired by Fourier analysis, we apply periodic activations to the interpolated features, turning alpha blending into a weighted sum of harmonic components. The resulting signal is then decoded in a single deferred pass using a small neural network, significantly reducing computational cost. Neural Harmonic Textures yield state-of-the-art results in real-time novel view synthesis while bridging the gap between primitive- and neural-field-based reconstruction. Our method integrates seamlessly into existing primitive-based pipelines such as 3DGUT, Triangle Splatting, and 2DGS. We further demonstrate its generality with applications to 2D image fitting and semantic reconstruction.

☆ True (VIS) Lies: Analyzing How Generative AI Recognizes Intentionality, Rhetoric, and Misleadingness in Visualization Lies

Graziano Blasilli, Marco Angelini

This study investigates the ability of multimodal Large Language Models (LLMs) to identify and interpret misleading visualizations, and recognize these observations along with their underlying causes and potential intentionality. Our analysis leverages concepts from visualization rhetoric and a newly developed taxonomy of authorial intents as explanatory lenses. We formulated three research questions and addressed them experimentally using a dataset of 2,336 COVID-19-related tweets, half of which contain misleading visualizations, and supplemented it with real-world examples of perceptual, cognitive, and conceptual errors drawn from VisLies, the IEEE VIS community event dedicated to showcasing deceptive and misleading visualizations. To ensure broad coverage of the current LLM landscape, we evaluated 16 state-of-the-art models. Among them, 15 are open-weight models, spanning a wide range of model sizes, architectural families, and reasoning capabilities. The selection comprises small models, namely Nemotron-Nano-V2-VL (12B parameters), Mistral-Small-3.2 (24B), DeepSeek-VL2 (27B), Gemma3 (27B), and GTA1 (32B); medium-sized models, namely Qianfan-VL (70B), Molmo (72B), GLM-4.5V (108B), LLaVA-NeXT (110B), and Pixtral-Large (124B); and large models, namely Qwen3-VL (235B), InternVL3.5 (241B), Step3 (321B), Llama-4-Maverick (400B), and Kimi-K2.5 (1000B). In addition, we employed OpenAI GPT-5.4, a frontier proprietary model. To establish a human perspective on these tasks, we also conducted a user study with visualization experts to assess how people perceive rhetorical techniques and the authorial intentions behind the same misleading visualizations. This allows comparison between model and expert behavior, revealing similarities and differences that provide insights into where LLMs align with human judgment and where they diverge.

☆ A ROS 2 Wrapper for Florence-2: Multi-Mode Local Vision-Language Inference for Robotic Systems

J. E. Domínguez-Vidal

Foundation vision-language models are becoming increasingly relevant to robotics because they can provide richer semantic perception than narrow task-specific pipelines. However, their practical adoption in robot software stacks still depends on reproducible middleware integrations rather than on model quality alone. Florence-2 is especially attractive in this regard because it unifies captioning, optical character recognition, open-vocabulary detection, grounding and related vision-language tasks within a comparatively manageable model size. This article presents a ROS 2 wrapper for Florence-2 that exposes the model through three complementary interaction modes: continuous topic-driven processing, synchronous service calls and asynchronous actions. The wrapper is designed for local execution and supports both native installation and Docker container deployment. It also combines generic JSON outputs with standard ROS 2 message bindings for detection-oriented tasks. A functional validation is reported together with a throughput study on several GPUs, showing that local deployment is feasible with consumer grade hardware. The repository is publicly available here: https://github.com/JEDominguezVidal/florence2_ros2_wrapper

comment: 5 pages, 1 figure

☆ Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defects

Hanzhe Liang, Luocheng Zhang, Junyang Xia, HanLiang Zhou, Bingyang Guo, Yingxi Xie, Can Gao, Ruiyun Yu, Jinbao Wang, Pan Li

Although self-supervised 3D anomaly detection assumes that acquiring high-precision point clouds is computationally expensive, in real manufacturing scenarios it is often feasible to collect a limited number of anomalous samples. Therefore, we study open-set supervised 3D anomaly detection, where the model is trained with only normal samples and a small number of known anomalous samples, aiming to identify unknown anomalies at test time. We present Open-Industry, a high-quality industrial dataset containing 15 categories, each with five real anomaly types collected from production lines. We first adapt general open-set anomaly detection methods to accommodate 3D point cloud inputs better. Building upon this, we propose Open3D-AD, a point-cloud-oriented approach that leverages normal samples, simulated anomalies, and partially observed real anomalies to model the probability density distributions of normal and anomalous data. Then, we introduce a simple Correspondence Distributions Subsampling to reduce the overlap between normal and non-normal distributions, enabling stronger dual distributions modeling. Based on these contributions, we establish a comprehensive benchmark and evaluate the proposed method extensively on Open-Industry as well as established datasets including Real3D-AD and Anomaly-ShapeNet. Benchmark results and ablation studies demonstrate the effectiveness of Open3D-AD and further reveal the potential of open-set supervised 3D anomaly detection.

comment: Resources: https://github.com/hzzzzzhappy/open-industry

☆ AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation

Prantik Deb, Srimanth Dhondy, N. Ramakrishna, Anu Kapoor, Raju S. Bapi, Tapabrata Chakraborti

Chest X-ray (CXR) segmentation is an important step in computer-aided diagnosis, yet deploying large foundation models in clinical settings remains challenging due to computational constraints. We propose AdaLoRA-QAT, a two-stage fine-tuning framework that combines adaptive low-rank encoder adaptation with full quantization-aware training. Adaptive rank allocation improves parameter efficiency, while selective mixed-precision INT8 quantization preserves structural fidelity crucial for clinical reliability. Evaluated across large-scale CXR datasets, AdaLoRA-QAT achieves 95.6% Dice, matching full-precision SAM decoder fine-tuning while reducing trainable parameters by 16.6\times and yielding 2.24\times model compression. A Wilcoxon signed-rank test confirms that quantization does not significantly degrade segmentation accuracy. These results demonstrate that AdaLoRA-QAT effectively balances accuracy, efficiency, and structural trust-worthiness, enabling compact and deployable foundation models for medical image segmentation. Code and pretrained models are available at: https://prantik-pdeb.github.io/adaloraqat.github.io/

comment: Accepted to ISBI 2026(Oral Presentation)

☆ Looking into a Pixel by Nonlinear Unmixing -- A Generative Approach

Maofeng Tang, Hairong Qi

Due to the large footprint of pixels in remote sensing imagery, hyperspectral unmixing (HU) has become an important and necessary procedure in hyperspectral image analysis. Traditional HU methods rely on a prior spectral mixing model, especially for nonlinear mixtures, which has largely limited the performance and generalization capacity of the unmixing approach. In this paper, we address the challenging problem of hyperspectral nonlinear unmixing (HNU) without explicit knowledge of the mixing model. Inspired by the principle of generative models, where images of the same distribution can be generated as that of the training images without knowing the exact probability distribution function of the image, we develop an invertible mixing-unmixing process via a bi-directional GAN framework, constrained by both the cycle consistency and the linkage between linear and nonlinear mixtures. The combination of cycle consistency and linear linkage provides powerful constraints without requiring an explicit mixing model. We refer to the proposed approach as the linearly-constrained CycleGAN unmixing net, or LCGU net. Experimental results indicate that the proposed LCGU net exhibits stable and competitive performance across different datasets compared with other state-of-the-art model-based HNU methods.

☆ Toward Personalized Darts Training: A Data-Driven Framework Based on Skeleton-Based Biomechanical Analysis and Motion Modeling

Zhantao Chen, Dongyi He, Jin Fang, Xi Chen, Yisuo Liu, Xiaozhen Zhong, Xuejun Hu

As sports training becomes more data-driven, traditional dart coaching based mainly on experience and visual observation is increasingly inadequate for high-precision, goal-oriented movements. Although prior studies have highlighted the importance of release parameters, joint motion, and coordination in dart throwing, most quantitative methods still focus on local variables, single-release metrics, or static template matching. These approaches offer limited support for personalized training and often overlook useful movement variability. This paper presents a data-driven dart training assistance system. The system creates a closed-loop framework spanning motion capture, feature modeling, and personalized feedback. Dart-throwing data were collected in markerless conditions using a Kinect 2.0 depth sensor and an optical camera. Eighteen kinematic features were extracted from four biomechanical dimensions: three-link coordination, release velocity, multi-joint angular configuration, and postural stability. Two modules were developed: a personalized optimal throwing trajectory model that combines historical high-quality samples with the minimum jerk criterion, and a motion deviation diagnosis and recommendation model based on z-scores and hierarchical logic. A total of 2,396 throwing samples from professional and non-professional athletes were collected. Results show that the system generates smooth personalized reference trajectories consistent with natural human movement. Case studies indicate that it can detect poor trunk stability, abnormal elbow displacement, and imbalanced velocity control, then provide targeted recommendations. The framework shifts dart evaluation from deviation from a uniform standard to deviation from an individual's optimal control range, improving personalization and interpretability for darts training and other high-precision target sports.

☆ ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation

Hao Zhang, Lue Fan, Weikang Bian, Zehuan Wu, Lewei Lu, Zhaoxiang Zhang, Hongsheng Li

We present ReinDriveGen, a framework that enables full controllability over dynamic driving scenes, allowing users to freely edit actor trajectories to simulate safety-critical corner cases such as front-vehicle collisions, drifting cars, vehicles spinning out of control, pedestrians jaywalking, and cyclists cutting across lanes. Our approach constructs a dynamic 3D point cloud scene from multi-frame LiDAR data, introduces a vehicle completion module to reconstruct full 360° geometry from partial observations, and renders the edited scene into 2D condition images that guide a video diffusion model to synthesize realistic driving videos. Since such edited scenarios inevitably fall outside the training distribution, we further propose an RL-based post-training strategy with a pairwise preference model and a pairwise reward mechanism, enabling robust quality improvement under out-of-distribution conditions without ground-truth supervision. Extensive experiments demonstrate that ReinDriveGen outperforms existing approaches on edited driving scenarios and achieves state-of-the-art results on novel ego viewpoint synthesis.

comment: Project page: https://drive-sim.github.io/ReinDriveGen/

☆ Lightweight Prompt-Guided CLIP Adaptation for Monocular Depth Estimation

Reyhaneh Ahani Manghotay, Jie Liang

Leveraging the rich semantic features of vision-language models (VLMs) like CLIP for monocular depth estimation tasks is a promising direction, yet often requires extensive fine-tuning or lacks geometric precision. We present a parameter-efficient framework, named MoA-DepthCLIP, that adapts pretrained CLIP representations for monocular depth estimation with minimal supervision. Our method integrates a lightweight Mixture-of-Adapters (MoA) module into the pretrained Vision Transformer (ViT-B/32) backbone combined with selective fine-tuning of the final layers. This design enables spatially-aware adaptation, guided by a global semantic context vector and a hybrid prediction architecture that synergizes depth bin classification with direct regression. To enhance structural accuracy, we employ a composite loss function that enforces geometric constraints. On the NYU Depth V2 benchmark, MoA-DepthCLIP achieves competitive results, significantly outperforming the DepthCLIP baseline by improving the $δ_1$ accuracy from 0.390 to 0.745 and reducing the RMSE from 1.176 to 0.520. These results are achieved while requiring substantially few trainable parameters, demonstrating that lightweight, prompt-guided MoA is a highly effective strategy for transferring VLM knowledge to fine-grained monocular depth estimation tasks.

comment: 14 pages, 2 figures

☆ ProTPS: Prototype-Guided Text Prompt Selection for Continual Learning

Jie Mei, Li-Leng Peng, Keith Fuller, Jenq-Neng Hwang

For continual learning, text-prompt-based methods leverage text encoders and learnable prompts to encode semantic features for sequentially arrived classes over time. A common challenge encountered by existing works is how to learn unique text prompts, which implicitly carry semantic information of new classes, so that the semantic features of newly arrived classes do not overlap with those of trained classes, thereby mitigating the catastrophic forgetting problem. To address this challenge, we propose a novel approach Prototype-guided Text Prompt Selection (ProTPS)'' to intentionally increase the training flexibility thus encouraging the learning of unique text prompts. Specifically, our ProTPS learns class-specific vision prototypes and text prompts. Vision prototypes guide the selection and learning of text prompts for each class. We first evaluate our ProTPS in both class incremental (CI) setting and cross-datasets continual (CDC) learning setting. Because our ProTPS achieves performance close to the upper bounds, we further collect a real-world dataset with 112 marine species collected over a span of six years, named Marine112, to bring new challenges to the community. Marine112 is authentically suited for the class and domain incremental (CDI) learning setting and is under natural long-tail distribution. The results under three settings show that our ProTPS performs favorably against the recent state-of-the-art methods. The implementation code and Marine112 dataset will be released upon the acceptance of our paper.

☆ TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models

Awais Khan, Muhammad Umar Farooq, Kutub Uddin, Khalid Malik

☆ ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data

Yaoqin Ye, Yiteng Xu, Qin Sun, Xinge Zhu, Yujing Sun, Yuexin Ma

Human behaviors in real-world environments are inherently interactive, with an individual's motion shaped by surrounding agents and the scene. Such capabilities are essential for applications in virtual avatars, interactive animation, and human-robot collaboration. We target real-time human interaction-to-reaction generation, which generates the ego's future motion from dynamic multi-source cues, including others' actions, scene geometry, and optional high-level semantic inputs. This task is fundamentally challenging due to (i) limited and fragmented interaction data distributed across heterogeneous single-person, human-human, and human-scene domains, and (ii) the need to produce low-latency yet high-fidelity motion responses during continuous online interaction. To address these challenges, we propose ReMoGen (Reaction Motion Generation), a modular learning framework for real-time interaction-to-reaction generation. ReMoGen leverages a universal motion prior learned from large-scale single-person motion datasets and adapts it to target interaction domains through independently trained Meta-Interaction modules, enabling robust generalization under data-scarce and heterogeneous supervision. To support responsive online interaction, ReMoGen performs segment-level generation together with a lightweight Frame-wise Segment Refinement module that incorporates newly observed cues at the frame level, improving both responsiveness and temporal coherence without expensive full-sequence inference. Extensive experiments across human-human, human-scene, and mixed-modality interaction settings show that ReMoGen produces high-quality, coherent, and responsive reactions, while generalizing effectively across diverse interaction scenarios.

comment: accepted by CVPR 2026, project page: https://4dvlab.github.io/project_page/remogen/

☆ ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction

Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Di Wen, Danda Pani Paudel, Luc Van Gool, Kailun Yang

3D semantic occupancy prediction is central to autonomous driving, yet current methods are vulnerable to long-tailed class bias and out-of-distribution (OOD) inputs, often overconfidently assigning anomalies to rare classes. We present ProOOD, a lightweight, plug-and-play method that couples prototype-guided refinement with training-free OOD scoring. ProOOD comprises (i) prototype-guided semantic imputation that fills occluded regions with class-consistent features, (ii) prototype-guided tail mining that strengthens rare-class representations to curb OOD absorption, and (iii) EchoOOD, which fuses local logit coherence with local and global prototype matching to produce reliable voxel-level OOD scores. Extensive experiments on five datasets demonstrate that ProOOD achieves state-of-the-art performance on both in-distribution 3D occupancy prediction and OOD detection. On SemanticKITTI, it surpasses baselines by +3.57% mIoU overall and +24.80% tail-class mIoU; on VAA-KITTI, it improves AuPRCr by +19.34 points, with consistent gains across benchmarks. These improvements yield more calibrated occupancy estimates and more reliable OOD detection in safety-critical urban driving. The source code is publicly available at https://github.com/7uHeng/ProOOD.

comment: Accepted to CVPR 2026. The source code is publicly available at https://github.com/7uHeng/ProOOD

☆ PHASOR: Anatomy- and Phase-Consistent Volumetric Diffusion for CT Virtual Contrast Enhancement

Zilong Li, Dongyang Li, Chenglong Ma, Zhan Feng, Dakai Jin, Junping Zhang, Hao Luo, Fan Wang, Hongming Shan

Contrast-enhanced computed tomography (CECT) is pivotal for highlighting tissue perfusion and vascularity, yet its clinical ubiquity is impeded by the invasive nature of contrast agents and radiation risks. While virtual contrast enhancement (VCE) offers an alternative to synthesizing CECT from non-contrast CT (NCCT), existing methods struggle with anatomical heterogeneity and spatial misalignment, leading to inconsistent enhancement patterns and incorrect details. This paper introduces PHASOR, a volumetric diffusion framework for high-fidelity CT VCE. By treating CT volumes as coherent sequences, we leverage a video diffusion model to enhance structural coherence and volumetric accuracy. To ensure anatomy-phase consistent synthesis, we introduce two complementary modules. First, anatomy-routed mixture-of-experts (AR-MoE) anchors distinct enhancement patterns to anatomical semantics, with organ-specific memory to capture salient details. Second, intensity-phase aware representation alignment (IP-REPA) highlights intricate contrast signals while mitigating the impact of imperfect spatial alignment. Extensive experiments across three datasets demonstrate that PHASOR significantly outperforms state-of-the-art methods in both synthesis quality and enhancement accuracy.

☆ A global dataset of continuous urban dashcam driving

Md Shadab Alam, Olena Bazilinska, Pavlo Bazilinskyy

We introduce CROWD (City Road Observations With Dashcams), a manually curated dataset of ordinary, minute scale, temporally contiguous, unedited, front facing urban dashcam segments screened and segmented from publicly available YouTube videos. CROWD is designed to support cross-domain robustness and interaction analysis by prioritising routine driving and explicitly excluding crashes, crash aftermath, and other edited or incident-focused content. The release contains 51,753 segment records spanning 20,275.56 hours (42,032 videos), covering 7,103 named inhabited places in 238 countries and territories across all six inhabited continents (Africa, Asia, Europe, North America, South America and Oceania), with segment level manual labels for time of day (day or night) and vehicle type. To lower the barrier for benchmarking, we provide per-segment CSV files of machine-generated detections for all 80 MS-COCO classes produced with YOLOv11x, together with segment-local multi-object tracks (BoT-SORT); e.g. person, bicycle, motorcycle, car, bus, truck, traffic light, stop sign, etc. CROWD is distributed as video identifiers with segment boundaries and derived annotations, enabling reproducible research without redistributing the underlying videos.

☆ ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration

Fengyuan Yang, Luying Huang, Jiazhi Guan, Quanwei Yang, Dongwei Pan, Jianglin Fu, Haocheng Feng, Wei He, Kaisiyuan Wang, Hang Zhou, Angela Yao

Recent advances in Video Foundation Models (VFMs) have revolutionized human-centric video synthesis, yet fine-grained and independent editing of subjects and scenes remains a critical challenge. Recent attempts to incorporate richer environment control through rigid 3D geometric compositions often encounter a stark trade-off between precise control and generative flexibility. Furthermore, the heavy 3D pre-processing still limits practical scalability. In this paper, we propose ONE-SHOT, a parameter-efficient framework for compositional human-environment video generation. Our key insight is to factorize the generative process into disentangled signals. Specifically, we introduce a canonical-space injection mechanism that decouples human dynamics from environmental cues via cross-attention. We also propose Dynamic-Grounded-RoPE, a novel positional embedding strategy that establishes spatial correspondences between disparate spatial domains without any heuristic 3D alignments. To support long-horizon synthesis, we introduce a Hybrid Context Integration mechanism to maintain subject and scene consistency across minute-level generations. Experiments demonstrate that our method significantly outperforms state-of-the-art methods, offering superior structural control and creative diversity for video synthesis. Our project has been available on: https://martayang.github.io/ONE-SHOT/.

comment: 23 pages, 7 figures

☆ Foundation Model-guided Iteratively Prompting and Pseudo-Labeling for Partially Labeled Medical Image Segmentation

Qiaochu Zhao, Wei Wei, David Horowitz, Richard Bakst, Yading Yuan

Automated medical image segmentation has achieved remarkable progress with fully labeled data. However, site-specific clinical priorities and the high cost of manual annotation often yield scans with only a subset of organs labeled, leading to the partially labeled problem that degrades performance. To address this issue, we propose IPnP, an Iteratively Prompting and Pseudo-labeling framework, for partially labeled medical image segmentation. IPnP iteratively generates and refines pseudo-labels for unlabeled organs through collaboration between a trainable segmentation network (specialist) and a frozen foundation model (generalist), progressively recovering full-organ supervision. On the public dataset AMOS with the simulated partial-label setting, IPnP consistently improves segmentation performance over prior methods and approaches the performance of the fully labeled reference. We further evaluate on a private, partially labeled dataset of 210 head-and-neck cancer patients and demonstrate our effectiveness in real-world clinical settings.

comment: 5 pages, 5 figures. Accepted for presentation at IEEE International Symposium on Biomedical Imaging (ISBI) 2026

☆ Sub-metre Lunar DEM Generation and Validation from Chandrayaan-2 OHRC Multi-View Imagery Using Open-Source Photogrammetry

Aaranay Aadi, Jai Singla, Nitant Dube, Oleg Alexandrov

High-resolution digital elevation models (DEMs) of the lunar surface are essential for surface mobility planning, landing site characterization, and planetary science. The Orbiter High Resolution Camera (OHRC) on board Chandrayaan-2 has the best ground sampling capabilities of any lunar orbital imaging currently in use by acquiring panchromatic imagery at a resolution of roughly 20-30 cm per pixel. This work presents, for the first time, the generation of sub-metre DEMs from OHRC multi-view imagery using an exclusively open-source pipeline. Candidate stereo pairs are identified from non-paired OHRC archives through geometric analysis of image metadata, employing baseline-to-height (B/H) ratio computation and convergence angle estimation. Dense stereo correspondence and ray triangulation are then applied to generate point clouds, which are gridded into DEMs at effective spatial resolutions between approximately 24 and 54 cm across five geographically distributed lunar sites. Absolute elevation consistency is established through Iterative Closest Point (ICP) alignment against Lunar Reconnaissance Orbiter Narrow Angle Camera (NAC) Digital Terrain Models, followed by constant-bias offset correction. Validation against NAC reference terrain yields a vertical RMSE of 5.85 m (at native OHRC resolution), and a horizontal accuracy of less than 30 cm assessed by planimetric feature matching.

comment: 17 pages, 8 figures

☆ Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization

Yueh-Cheng Liu, Jozef Hladký, Matthias Nießner, Angela Dai

Recent advances in 3D Gaussian Splatting (3DGS) present two main directions: feed-forward models offer fast inference in sparse-view settings, while per-scene optimization yields high-quality renderings but is computationally expensive. To combine the benefits of both, we introduce Diff3R, a novel framework that explicitly bridges feed-forward prediction and test-time optimization. By incorporating a differentiable 3DGS optimization layer directly into the training loop, our network learns to predict an optimal initialization for test-time optimization rather than a conventional zero-shot result. To overcome the computational cost of backpropagating through the optimization steps, we propose computing gradients via the Implicit Function Theorem and a scalable, matrix-free PCG solver tailored for 3DGS optimization. Additionally, we incorporate a data-driven uncertainty model into the optimization process by adaptively controlling how much the parameters are allowed to change during optimization. This approach effectively mitigates overfitting in under-constrained regions and increases robustness against input outliers. Since our proposed optimization layer is model-agnostic, we show that it can be seamlessly integrated into existing feed-forward 3DGS architectures for both pose-given and pose-free methods, providing improvements for test-time optimization.

comment: Project page: https://liu115.github.io/diff3r, Video: https://www.youtube.com/watch?v=IxzNSAdUY70

☆ Forecasting Motion in the Wild

Neerja Thakkar, Shiry Ginosar, Jacob Walker, Jitendra Malik, Joao Carreira, Carl Doersch

Visual intelligence requires anticipating the future behavior of agents, yet vision systems lack a general representation for motion and behavior. We propose dense point trajectories as visual tokens for behavior, a structured mid-level representation that disentangles motion from appearance and generalizes across diverse non-rigid agents, such as animals in-the-wild. Building on this abstraction, we design a diffusion transformer that models unordered sets of trajectories and explicitly reasons about occlusion, enabling coherent forecasts of complex motion patterns. To evaluate at scale, we curate 300 hours of unconstrained animal video with robust shot detection and camera-motion compensation. Experiments show that forecasting trajectory tokens achieves category-agnostic, data-efficient prediction, outperforms state-of-the-art baselines, and generalizes to rare species and morphologies, providing a foundation for predictive visual intelligence in the wild.

comment: project page: https://motion-forecasting.github.io/

☆ AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration

Ruhao Liu, Weiqi Huang, Qi Li, Xinchao Wang

Membership Inference Attacks (MIAs) serve as a fundamental auditing tool for evaluating training data leakage in machine learning models. However, existing methodologies predominantly rely on static, handcrafted heuristics that lack adaptability, often leading to suboptimal performance when transferred across different large models. In this work, we propose AutoMIA, an agentic framework that reformulates membership inference as an automated process of self-exploration and strategy evolution. Given high-level scenario specifications, AutoMIA self-explores the attack space by generating executable logits-level strategies and progressively refining them through closed-loop evaluation feedback. By decoupling abstract strategy reasoning from low-level execution, our framework enables a systematic, model-agnostic traversal of the attack search space. Extensive experiments demonstrate that AutoMIA consistently matches or outperforms state-of-the-art baselines while eliminating the need for manual feature engineering.

☆ PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks

Jingning Xu, Haochen Luo, Chen Liu

Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computationally expensive and often fail to generalize to unseen attack types. To address these limitations, we introduce Paraphrase-Decomposition-Aggregation (PDA), a training-free defense framework that leverages text augmentation to enhance VLM robustness under diverse adversarial image attacks. PDA performs prompt paraphrasing, question decomposition, and consistency aggregation entirely at test time, thus requiring no modification on the underlying models. To balance robustness and efficiency, we instantiate PDA as invariants that reduce the inference cost while retaining most of its robustness gains. Experiments on multiple VLM architectures and benchmarks for visual question answering, classification, and captioning show that PDA achieves consistent robustness gains against various adversarial perturbations while maintaining competitive clean accuracy, establishing a generic, strong and practical defense framework for VLMs during inference.

☆ Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding

Yiheng Wang, Lichen Zhu, Yueqian Lin, Yudong Liu, Jingyang Zhang, Hai "Helen" Li, Yiran Chen

Multimodal Large Language Models (MLLMs) have shown strong performance on video question answering, but their application to long-form videos is constrained by limited context length and computational cost, making keyframe sampling essential. Existing approaches typically rely on semantic relevance or reinforcement learning, which either fail to capture evidential clues or suffer from inefficient combinatorial optimization. In this work, we propose an evidence-driven keyframe sampling framework grounded in information bottleneck theory. We formulate keyframe selection as maximizing the conditional mutual information between selected frames and the query, providing a principled objective that reflects each frame's contribution to answering the question. To make this objective tractable, we exploit its structure to derive a decomposed optimization that reduces subset selection to independent frame-level scoring. We further introduce a query-conditioned evidence scoring network trained with a contrastive objective to estimate evidential importance efficiently. Experiments on long-form video understanding benchmarks show that our method consistently outperforms prior sampling strategies under strict token budgets, while significantly improving training efficiency.

☆ EgoSim: Egocentric World Simulator for Embodied Interaction Generation

Jinkun Hao, Mingda Jia, Ruiyan Wang, Xihui Liu, Ran Yi, Lizhuang Ma, Jiangmiao Pang, Xudong Xu

We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation. Existing egocentric simulators either lack explicit 3D grounding, causing structural drift under viewpoint changes, or treat the scene as static, failing to update world states across multi-stage interactions. EgoSim addresses both limitations by modeling 3D scenes as updatable world states. We generate embodiment interactions via a Geometry-action-aware Observation Simulation model, with spatial consistency from an Interaction-aware State Updating module. To overcome the critical data bottleneck posed by the difficulty in acquiring densely aligned scene-interaction training pairs, we design a scalable pipeline that extracts static point clouds, camera trajectories, and embodiment actions from in-the-wild large-scale monocular egocentric videos. We further introduce EgoCap, a capture system that enables low-cost real-world data collection with uncalibrated smartphones. Extensive experiments demonstrate that EgoSim significantly outperforms existing methods in terms of visual quality, spatial consistency, and generalization to complex scenes and in-the-wild dexterous interactions, while supporting cross-embodiment transfer to robotic manipulation. Codes and datasets will be open soon. The project page is at egosimulator.github.io.

comment: Project Page: egosimulator.github.io

☆ Customizing Large Vision Model-Guided Low-Rank Approximation for Ground-Roll Denoise

Jiacheng Liao, Feng Qian, Ziyin Fan, Yongjian Guo

Ground-roll is a dominant source of coherent noise in land and vertical seismic profiling (VSP) data, severely masking reflection events and degrading subsequent imaging and interpretation. Conventional attenuation methods, including transform-domain filtering, sparse representation, and deep learning, often suffer from limited adaptability, signal leakage, or dependence on labeled training data, especially under strong signal-noise overlap. To address these challenges, we propose a training-free framework that reformulates ground-roll attenuation as a semantic-guided signal separation problem. Specifically, a promptable large vision model is employed to extract high-level semantic priors by converting seismic gathers into visual representations and localizing ground-roll-dominant regions via text or image prompts. The resulting semantic response is transformed into a continuous soft mask, which is embedded into a mask-conditioned low-rank inverse formulation to enable spatially adaptive suppression and reflection-preserving reconstruction. An efficient alternating direction method of multipliers (ADMM)-based solver is further developed to solve the proposed inverse problem, enabling stable and physically consistent signal recovery without requiring task-specific training or manual annotation. Extensive experiments on both synthetic and field VSP datasets demonstrate that the proposed method achieves superior ground-roll attenuation while preserving reflection continuity and waveform fidelity, consistently outperforming representative transform-domain filtering and implicit neural representation methods.

☆ Maximizing T2-Only Prostate Cancer Localization from Expected Diffusion Weighted Imaging

Weixi Yi, Yipei Wang, Wen Yan, Hanyuan Zhang, Natasha Thorley, Alexander Ng, Shonit Punwani, Fernando Bianco, Mark Emberton, Veeru Kasivisvanathan, Dean C. Barratt, Shaheer U. Saeed, Yipeng Hu

Multiparametric MRI is increasingly recommended as a first-line noninvasive approach to detect and localize prostate cancer, requiring at minimum diffusion-weighted (DWI) and T2-weighted (T2w) MR sequences. Early machine learning attempts using only T2w images have shown promising diagnostic performance in segmenting radiologist-annotated lesions. Such uni-modal T2-only approaches deliver substantial clinical benefits by reducing costs and expertise required to acquire other sequences. This work investigates an arguably more challenging application using only T2w at inference, but to localize individual cancers based on independent histopathology labels. We formulate DWI images as a latent modality (readily available during training) to classify cancer presence at local Barzell zones, given only T2w images as input. In the resulting expectation-maximization algorithm, a latent modality generator (implemented using a flow matching-based generative model) approximates the latent DWI image posterior distribution in the E-steps, while in M-steps a cancer localizer is simultaneously optimized with the generative model to maximize the expected likelihood of cancer presence. The proposed approach provides a novel theoretical framework for learning from a privileged DWI modality, yielding superior cancer localization performance compared to approaches that lack training DWI images or existing frameworks for privileged learning and incomplete modalities. The proposed T2-only methods perform competitively or better than baseline methods using multiple input sequences (e.g., improving the patient-level F1 score by 14.4\% and zone-level QWK by 5.3\% over the T2w+DWI baseline). We present quantitative evaluations using internal and external datasets from 4,133 prostate cancer patients with histopathology-verified labels.

☆ ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration

Bei Yan, Yuecong Min, Jie Zhang, Shiguang Shan, Xilin Chen

Large Vision-Language Models (LVLMs) frequently suffer from severe hallucination issues. Existing mitigation strategies predominantly rely on isolated, single-step states to enhance visual focus or suppress strong linguistic priors. However, these static approaches neglect dynamic context changes across the generation process and struggles to correct inherited information loss. To address this limitation, we propose Adaptive Context inTegration (ACT), a training-free inference intervention method that mitigates hallucination through the adaptive integration of contextual information. Specifically, we first propose visual context exploration, which leverages spatio-temporal profiling to adaptively amplify attention heads responsible for visual exploration. To further facilitate vision-language alignment, we propose semantic context aggregation that marginalizes potential semantic queries to effectively aggregate visual evidence, thereby resolving the information loss caused by the discrete nature of token prediction. Extensive experiments across diverse LVLMs demonstrate that ACT significantly reduces hallucinations and achieves competitive results on both discriminative and generative benchmarks, acting as a robust and highly adaptable solution without compromising fundamental generation capabilities.

☆ DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Driving

Yiyao Zhu, Ying Xue, Haiming Zhang, Guangfeng Jiang, Wending Zhou, Xu Yan, Jiantao Gao, Yingjie Cai, Bingbing Liu, Zhen Li, Shaojie Shen

Vision-based autonomous driving has gained much attention due to its low costs and excellent performance. Compared with dense BEV (Bird's Eye View) or sparse query models, Gaussian-centric method is a comprehensive yet sparse representation by describing scene with 3D semantic Gaussians. In this paper, we introduce DLWM, a novel paradigm with Dual Latent World Models specifically designed to enable holistic gaussian-centric pre-training in autonomous driving using two stages. In the first stage, DLWM predicts 3D Gaussians from queries by self-supervised reconstructing multi-view semantic and depth images. Equipped with fine-grained contextual features, in the second stage, two latent world models are trained separately for temporal feature learning, including Gaussian-flow-guided latent prediction for downstream occupancy perception and forecasting tasks, and ego-planning-guided latent prediction for motion planning. Extensive experiments in SurroundOcc and nuScenes benchmarks demonstrate that DLWM shows significant performance gains across Gaussian-centric 3D occupancy perception, 4D occupancy forecasting and motion planning tasks.

comment: Accepted by CVPR 2026

☆ Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization

Hao Fang, Wenbo Yu, Bin Chen, Xuan Wang, Shu-Tao Xia, Qing Liao, Ke Xu

Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model by transmitting locally computed gradients to a central server without exposing their private data. Nonetheless, recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage, e.g., an attacker can invert shared gradients to reconstruct sensitive data by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. However, existing attacks simply perform gradient inversion in the latent space of the GAN model, which limits their expression ability and generalizability. To tackle these challenges, we propose \textbf{G}radient \textbf{I}nversion over \textbf{F}eature \textbf{D}omains (GIFD), which disassembles the GAN model and searches the hierarchical features of the intermediate layers. Instead of optimizing only over the initial latent code, we progressively change the optimized layer, from the initial latent space to intermediate layers closer to the output images. In addition, we design a regularizer to avoid unreal image generation by adding a small ${l_1}$ ball constraint to the searching range. We also extend GIFD to the out-of-distribution (OOD) setting, which weakens the assumption that the training sets of GANs and FL tasks obey the same data distribution. Furthermore, we consider the challenging OOD scenario of label inconsistency and propose a label mapping technique as an effective solution. Extensive experiments demonstrate that our method can achieve pixel-level reconstruction and outperform competitive baselines across a variety of FL scenarios.

☆ YieldSAT: A Multimodal Benchmark Dataset for High-Resolution Crop Yield Prediction

Miro Miranda, Deepak Pathak, Patrick Helber, Benjamin Bischke, Hiba Najjar, Francisco Mena, Cristhian Sanchez, Akshay Pai, Diego Arenas, Matias Valdenegro-Toro, Marcela Charfuelan, Marlon Nuske, Andreas Dengel

Crop yield prediction requires substantial data to train scalable models. However, creating yield prediction datasets is constrained by high acquisition costs, heterogeneous data quality, and data privacy regulations. Consequently, existing datasets are scarce, low in quality, or limited to regional levels or single crop types, hindering the development of scalable data-driven solutions. In this work, we release YieldSAT, a large, high-quality, and multimodal dataset for high-resolution crop yield prediction. YieldSAT spans various climate zones across multiple countries, including Argentina, Brazil, Uruguay, and Germany, and includes major crop types, including corn, rapeseed, soybeans, and wheat, across 2,173 expert-curated fields. In total, over 12.2 million yield samples are available, each with a spatial resolution of 10 m. Each field is paired with multispectral satellite imagery, resulting in 113,555 labeled satellite images, complemented by auxiliary environmental data. We demonstrate the potential of large-scale and high-resolution crop yield prediction as a pixel regression task by comparing various deep learning models and data fusion architectures. Furthermore, we highlight open challenges arising from severe distribution shifts in the ground truth data under real-world conditions. To mitigate this, we explore a domain-informed Deep Ensemble approach that exhibits significant performance gains. The dataset is available at https://yieldsat.github.io/.

☆ EmoScene: A Dual-space Dataset for Controllable Affective Image Generation

Li He, Longtai Zhang, Wenqiang Zhang, Yan Wang, Lizhe Qi

Text-to-image diffusion models have achieved high visual fidelity, yet precise control over scene semantics and fine-grained affective tone remains challenging. Human visual affect arises from the rapid integration of contextual meaning, including valence, arousal, and dominance, with perceptual cues such as color harmony, luminance contrast, texture variation, curvature, and spatial layout. However, current text-to-image models rarely represent affective and perceptual factors within a unified representation, which limits their ability to synthesize scenes with coherent and nuanced emotional intent. To address this gap, we construct EmoScene, a large-scale dual-space emotion dataset that jointly encodes affective dimensions and perceptual attributes, with contextual semantics provided as supporting annotations. EmoScene contains 1.2M images across more than three hundred real-world scene categories, each annotated with discrete emotion labels, continuous VAD values, perceptual descriptors and textual captions. Multi-space analyses reveal how discrete emotions occupy the VAD space and how affect systematically correlates with scene-level perceptual factors. To benchmark EmoScene, we provide a lightweight reference baseline that injects dual-space controls into a frozen diffusion backbone via shallow cross-attention modulation, serving as a reproducible probe of affect controllability enabled by dual-space supervision.

☆ Autoregressive Appearance Prediction for 3D Gaussian Avatars

Michael Steiner, Zhang Chen, Alexander Richard, Vasu Agrawal, Markus Steinberger, Michael Zollhöfer

A photorealistic and immersive human avatar experience demands capturing fine, person-specific details such as cloth and hair dynamics, subtle facial expressions, and characteristic motion patterns. Achieving this requires large, high-quality datasets, which often introduce ambiguities and spurious correlations when very similar poses correspond to different appearances. Models that fit these details during training can overfit and produce unstable, abrupt appearance changes for novel poses. We propose a 3D Gaussian Splatting avatar model with a spatial MLP backbone that is conditioned on both pose and an appearance latent. The latent is learned during training by an encoder, yielding a compact representation that improves reconstruction quality and helps disambiguate pose-driven renderings. At driving time, our predictor autoregressively infers the latent, producing temporally smooth appearance evolution and improved stability. Overall, our method delivers a robust and practical path to high-fidelity, stable avatar driving.

comment: Project Page: https://steimich96.github.io/AAP-3DGA/

☆ Learning Quantised Structure-Preserving Motion Representations for Dance Fingerprinting

Arina Kharlamova, Bowei He, Chen Ma, Xue Liu

We present DANCEMATCH, an end-to-end framework for motion-based dance retrieval, the task of identifying semantically similar choreographies directly from raw video, defined as DANCE FINGERPRINTING. While existing motion analysis and retrieval methods can compare pose sequences, they rely on continuous embeddings that are difficult to index, interpret, or scale. In contrast, DANCEMATCH constructs compact, discrete motion signatures that capture the spatio-temporal structure of dance while enabling efficient large-scale retrieval. Our system integrates Skeleton Motion Quantisation (SMQ) with Spatio-Temporal Transformers (STT) to encode human poses, extracted via Apple CoMotion, into a structured motion vocabulary. We further design DANCE RETRIEVAL ENGINE (DRE), which performs sub-linear retrieval using a histogram-based index followed by re-ranking for refined matching. To facilitate reproducible research, we release DANCETYPESBENCHMARK, a pose-aligned dataset annotated with quantised motion tokens. Experiments demonstrate robust retrieval across diverse dance styles and strong generalisation to unseen choreographies, establishing a foundation for scalable motion fingerprinting and quantitative choreographic analysis.

☆ Representation Selection via Cross-Model Agreement using Canonical Correlation Analysis

Dylan B. Lewis, Jens Gregor, Hector Santos-Villalobos

Modern vision pipelines increasingly rely on pretrained image encoders whose representations are reused across tasks and models, yet these representations are often overcomplete and model-specific. We propose a simple, training-free method to improve the efficiency of image representations via a post-hoc canonical correlation analysis (CCA) operator. By leveraging the shared structure between representations produced by two pre-trained image encoders, our method finds linear projections that serve as a principled form of representation selection and dimensionality reduction, retaining shared semantic content while discarding redundant dimensions. Unlike standard dimensionality reduction techniques such as PCA, which operate on a single embedding space, our approach leverages cross-model agreement to guide representation distillation and refinement. The technique allows representations to be reduced by more than 75% in dimensionality with improved downstream performance, or enhanced at fixed dimensionality via post-hoc representation transfer from larger or fine-tuned models. Empirical results on ImageNet-1k, CIFAR-100, MNIST, and additional benchmarks show consistent improvements over both baseline and PCA-projected representations, with accuracy gains of up to 12.6%.

comment: 9 pages, 5 figures, 6 tables

☆ Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction Alignment

Zhuchenyang Liu, Yao Zhang, Yu Xiao

2D assembly diagrams are often abstract and hard to follow, creating a need for intelligent assistants that can monitor progress, detect errors, and provide step-by-step guidance. In mixed reality settings, such systems must recognize completed and ongoing steps from the camera feed and align them with the diagram instructions. Vision Language Models (VLMs) show promise for this task, but face a depiction gap because assembly diagrams and video frames share few visual features. To systematically assess this gap, we construct IKEA-Bench, a benchmark of 1,623 questions across 6 task types on 29 IKEA furniture products, and evaluate 19 VLMs (2B-38B) under three alignment strategies. Our key findings: (1) assembly instruction understanding is recoverable via text, but text simultaneously degrades diagram-to-video alignment; (2) architecture family predicts alignment accuracy more strongly than parameter count; (3) video understanding remains a hard bottleneck unaffected by strategy. A three-level mechanistic analysis further reveals that diagrams and video occupy disjoint ViT subspaces, and that adding text shifts models from visual to text-driven reasoning. These results identify visual encoding as the primary target for improving cross-depiction robustness. Project page: https://ryenhails.github.io/IKEA-Bench/

☆ ProCap: Projection-Aware Captioning for Spatial Augmented Reality

Zimo Cao, Yuchen Deng, Haibin Ling, Bingyao Huang

Spatial augmented reality (SAR) directly projects digital content onto physical scenes using projectors, creating immersive experience without head-mounted displays. However, for SAR to support intelligent interaction, such as reasoning about the scene or answering user queries, it must semantically distinguish between the physical scene and the projected content. Standard Vision Language Models (VLMs) struggle with this virtual-physical ambiguity, often confusing the two contexts. To address this issue, we introduce ProCap, a novel framework that explicitly decouples projected content from physical scenes. ProCap employs a two-stage pipeline: first it visually isolates virtual and physical layers via automated segmentation; then it uses region-aware retrieval to avoid ambiguous semantic context due to projection distortion. To support this, we present RGBP (RGB + Projections), the first large-scale SAR semantic benchmark dataset, featuring 65 diverse physical scenes and over 180,000 projections with dense, decoupled annotations. Finally, we establish a dual-captioning evaluation protocol using task-specific tokens to assess physical scene and projection descriptions independently. Our experiments show that ProCap provides a robust semantic foundation for future SAR research. The source code, pre-trained models and the RGBP dataset are available on the project page: https://ZimoCao.github.io/ProCap/.

comment: 16 pages, 7 figures

☆ JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation

Issa Sugiura, Koki Maeda, Shuhei Kurita, Yusuke Oda, Daisuke Kawahara, Naoaki Okazaki

Reliable evaluation is essential for the development of vision-language models (VLMs). However, Japanese VQA benchmarks have undergone far less iterative refinement than their English counterparts. As a result, many existing benchmarks contain issues such as ambiguous questions, incorrect answers, and instances that can be solved without visual grounding, undermining evaluation reliability and leading to misleading conclusions in model comparisons. To address these limitations, we introduce JAMMEval, a refined collection of Japanese benchmarks for reliable VLM evaluation. It is constructed by systematically refining seven existing Japanese benchmark datasets through two rounds of human annotation, improving both data quality and evaluation reliability. In our experiments, we evaluate open-weight and proprietary VLMs on JAMMEval and analyze the capabilities of recent models on Japanese VQA. We further demonstrate the effectiveness of our refinement by showing that the resulting benchmarks yield evaluation scores that better reflect model capability, exhibit lower run-to-run variance, and improve the ability to distinguish between models of different capability levels. We release our dataset and code to advance reliable evaluation of VLMs.

comment: 16 pages, 11 figures

☆ IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off

Linyan Dai, Xinwei Zhang, Haoyang Li, Qingqing Ye, Haibo Hu

Personalized text-to-image diffusion models (e.g., DreamBooth, LoRA) enable users to synthesize high-fidelity avatars from a few reference photos for social expression. However, once these generations are shared on social media platforms (e.g., Instagram, Facebook), they can be linked to the real user via face recognition systems, enabling identity tracking and profiling. Existing defenses mainly follow an anti-personalization strategy that protects publicly released reference photos by disrupting model fine-tuning. While effective against unauthorized personalization, they do not address another practical setting in which personalization is authorized, but the resulting public outputs still leak identity information. To address this problem, we introduce a new defense setting, termed model-side output immunization, whose goal is to produce a personalized model that supports authorized personalization while reducing the identity linkability of public generations, with tunable control over the privacy-utility trade-off to accommodate diverse privacy needs. To this end, we propose Identity-Decoupled personalized Diffusion Models (IDDM), a model-side defense that integrates identity decoupling into the personalization pipeline. Concretely, IDDM follows an alternating procedure that interleaves short personalization updates with identity-decoupled data optimization, using a two-stage schedule to balance identity linkability suppression and generation utility. Extensive experiments across multiple datasets, diverse prompts, and state-of-the-art face recognition systems show that IDDM consistently reduces identity linkability while preserving high-quality personalized generation.

☆ Super-Resolving Coarse-Resolution Weather Forecasts With Flow Matching

Aymeric Delefosse, Anastase Charantonis, Dominique Béréziat

Machine learning-based weather forecasting models now surpass state-of-the-art numerical weather prediction systems, but training and operating these models at high spatial resolution remains computationally expensive. We present a modular framework that decouples forecasting from spatial resolution by applying learned generative super-resolution as a post-processing step to coarse-resolution forecast trajectories. We formulate super-resolution as a stochastic inverse problem, using a residual formulation to preserve large-scale structure while reconstructing unresolved variability. The model is trained with flow matching exclusively on reanalysis data and is applied to global medium-range forecasts. We evaluate (i) design consistency by re-coarsening super-resolved forecasts and comparing them to the original coarse trajectories, and (ii) high-resolution forecast quality using standard ensemble verification metrics and spectral diagnostics. Results show that super-resolution preserves large-scale structure and variance after re-coarsening, introduces physically consistent small-scale variability, and achieves competitive probabilistic forecast skill at 0.25° resolution relative to an operational ensemble baseline, while requiring only a modest additional training cost compared with end-to-end high-resolution forecasting.

comment: Accepted to Climate Informatics 2026

☆ Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models

Md. Abu Bakor Siddique, Shahrin Hossain, Sadman Ahmed Siam, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan

Geometric Problem Solving (GPS) remains at the heart of enhancing mathematical reasoning in large language models because it requires the combination of diagrammatic understanding, symbolic manipulation and logical inference. In existing literature, researchers have chiefly focused on synchronising the diagram descriptions with text literals and solving the problem. In this vein, they have either taken a neural, symbolic or neuro-symbolic approach. But this solves only the first two of the requirements, namely diagrammatic understanding and symbolic manipulation, while leaving logical inference underdeveloped. The logical inference is often limited to one chain-of-thought (CoT). To address this weakness in hitherto existing models, this paper proposes MARS-GPS, that generates multiple parallel reasoning rollouts augmented with Python code execution for numerical verification, ranks them using token-level entropy as a confidence signal, and aggregates answers through a multi-stage voting and self-verification pipeline. Empirical results show that MARS-GPS with 8 parallel rollouts achieves 88.8% on Geometry3K, a nearly +11% improvement over the prior state-of-the-art, with accuracy scaling consistently as the number of rollouts increases from 1 to 16 (+6.0% on ablation subset). We provide our code and data in an anonymous repository: https://anonymous.4open.science/r/MARS-GPS-DE55.

comment: Under review, 4 figures, 7 tables

☆ Adversarial Attenuation Patch Attack for SAR Object Detection

Yiming Zhang, Weibo Qin, Feng Wang

Deep neural networks have demonstrated excellent performance in SAR target detection tasks but remain susceptible to adversarial attacks. Existing SAR-specific attack methods can effectively deceive detectors; however, they often introduce noticeable perturbations and are largely confined to digital domain, neglecting physical implementation constrains for attacking SAR systems. In this paper, a novel Adversarial Attenuation Patch (AAP) method is proposed that employs energy-constrained optimization strategy coupled with an attenuation-based deployment framework to achieve a seamless balance between attack effectiveness and stealthiness. More importantly, AAP exhibits strong potential for physical realization by aligning with signal-level electronic jamming mechanisms. Experimental results show that AAP effectively degrades detection performance while preserving high imperceptibility, and shows favorable transferability across different models. This study provides a physical grounded perspective for adversarial attacks on SAR target detection systems and facilitates the design of more covert and practically deployable attack strategies. The source code is made available at https://github.com/boremycin/SAAP.

comment: 5 pages, 4 figures. Source code is available at https://github.com/boremycin/SAAP

☆ PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding

Nan Wang, Zhiwei Jin, Chen Chen, Haonan Lu

Document understanding and GUI interaction are among the highest-value applications of Vision-Language Models (VLMs), yet they impose exceptionally heavy computational burden: fine-grained text and small UI elements demand high-resolution inputs that produce tens of thousands of visual tokens. We observe that this cost is largely wasteful -- across document and GUI benchmarks, only 22--71\% of image patches are pixel-unique, the rest being exact duplicates of another patch in the same image. We propose \textbf{PixelPrune}, which exploits this pixel-level redundancy through predictive-coding-based compression, pruning redundant patches \emph{before} the Vision Transformer (ViT) encoder. Because it operates in pixel space prior to any neural computation, PixelPrune accelerates both the ViT encoder and the downstream LLM, covering the full inference pipeline. The method is training-free, requires no learnable parameters, and supports pixel-lossless compression ($τ{=}0$) as well as controlled lossy compression ($τ{>}0$). Experiments across three model scales and document and GUI benchmarks show that PixelPrune maintains competitive task accuracy while delivering up to 4.2$\times$ inference speedup and 1.9$\times$ training acceleration. Code is available at https://github.com/OPPO-Mente-Lab/PixelPrune.

☆ A 4D Representation for Training-Free Agentic Reasoning from Monocular Laparoscopic Video

Maximilian Fehrentz, Nicolas Stellwag, Robert Wiebe, Nicole Thorisch, Fabian Grob, Patrick Remerscheid, Ken-Joel Simmoteit, Benjamin D. Killeen, Christian Heiliger, Nassir Navab

Spatiotemporal reasoning is a fundamental capability for artificial intelligence (AI) in soft tissue surgery, paving the way for intelligent assistive systems and autonomous robotics. While 2D vision-language models show increasing promise at understanding surgical video, the spatial complexity of surgical scenes suggests that reasoning systems may benefit from explicit 4D representations. Here, we propose a framework for equipping surgical agents with spatiotemporal tools based on an explicit 4D representation, enabling AI systems to ground their natural language reasoning in both time and 3D space. Leveraging models for point tracking, depth, and segmentation, we develop a coherent 4D model with spatiotemporally consistent tool and tissue semantics. A Multimodal Large Language Model (MLLM) then acts as an agent on tools derived from the explicit 4D representation (e.g., trajectories) without any fine-tuning. We evaluate our method on a new dataset of 134 clinically relevant questions and find that the combination of a general purpose reasoning backbone and our 4D representation significantly improves spatiotemporal understanding and allows for 4D grounding. We demonstrate that spatiotemporal intelligence can be "assembled" from 2D MLLMs and 3D computer vision models without additional training. Code, data, and examples are available at https://tum-ai.github.io/surg4d/

☆ Shape Representation using Gaussian Process mixture models

Panagiotis Sapoutzoglou, George Terzakis, Georgios Floros, Maria Pateraki

Traditional explicit 3D representations, such as point clouds and meshes, demand significant storage to capture fine geometric details and require complex indexing systems for surface lookups, making functional representations an efficient, compact, and continuous alternative. In this work, we propose a novel, object-specific functional shape representation that models surface geometry with Gaussian Process (GP) mixture models. Rather than relying on computationally heavy neural architectures, our method is lightweight, leveraging GPs to learn continuous directional distance fields from sparsely sampled point clouds. We capture complex topologies by anchoring local GP priors at strategic reference points, which can be flexibly extracted using any structural decomposition method (e.g. skeletonization, distance-based clustering). Extensive evaluations on the ShapeNetCore and IndustryShapes datasets demonstrate that our method can efficiently and accurately represent complex geometries.

comment: To appear in ISPRS 2026

☆ Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capture ICLR 2026

Yiming Ren, Yujing Sun, Aoru Xue, Kwok-Yan Lam, Yuexin Ma

Point cloud-based motion capture leverages rich spatial geometry and privacy-preserving sensing, but learning robust representations from noisy, unstructured point clouds remains challenging. Existing approaches face a struggle trade-off between point-based methods (geometrically detailed but noisy) and skeleton-based ones (robust but oversimplified). We address the fundamental challenge: how to construct an effective representation for human motion capture that can balance expressiveness and robustness. In this paper, we propose Sparkle, a structured representation unifying skeletal joints and surface anchors with explicit kinematic-geometric factorization. Our framework, SparkleMotion, learns this representation through hierarchical modules embedding geometric continuity and kinematic constraints. By explicitly disentangling internal kinematic structure from external surface geometry, SparkleMotion achieves state-of-the-art performance not only in accuracy but crucially in robustness and generalization under severe domain shifts, noise, and occlusion. Extensive experiments demonstrate our superiority across diverse sensor types and challenging real-world scenarios.

comment: Accepted at ICLR 2026

☆ Perturb-and-Restore: Simulation-driven Structural Augmentation Framework for Imbalance Chromosomal Anomaly Detection

Yilan Zhang, Hanbiao Chen, Changchun Yang, Yuetan Chu, Siyuan Chen, Jing Wu, Jingdong Hu, Na Li, Junkai Su, Yuxuan Chen, Ao Xu, Xin Gao, Aihua Yin

Detecting structural chromosomal abnormalities is crucial for accurate diagnosis and management of genetic disorders. However, collecting sufficient structural abnormality data is extremely challenging and costly in clinical practice, and not all abnormal types can be readily collected. As a result, deep learning approaches face significant performance degradation due to the severe imbalance and scarcity of abnormal chromosome data. To address this challenge, we propose a Perturb-and-Restore (P&R), a simulation-driven structural augmentation framework that effectively alleviates data imbalance in chromosome anomaly detection. The P&R framework comprises two key components: (1) Structure Perturbation and Restoration Simulation, which generates synthetic abnormal chromosomes by perturbing chromosomal banding patterns of normal chromosomes followed by a restoration diffusion network that reconstructs continuous chromosome content and edges, thus eliminating reliance on rare abnormal samples; and (2) Energy-guided Adaptive Sampling, an energy score-based online selection strategy that dynamically prioritizes high-quality synthetic samples by referencing the energy distribution of real samples. To evaluate our method, we construct a comprehensive structural anomaly dataset consisting of over 260,000 chromosome images, including 4,242 abnormal samples spanning 24 categories. Experimental results demonstrate that the P&R framework achieves state-of-the-art (SOTA) performance, surpassing existing methods with an average improvement of 8.92% in sensitivity, 8.89% in precision, and 13.79% in F1-score across all categories.

comment: This preprint version of the manuscript has been submitted to the IEEE Journal of Biomedical and Health Informatics (JBHI) for review

☆ MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer

Samuel Teodoro, Yun Chen, Agus Gunawan, Soo Ye Kim, Jihyong Oh, Munchurl Kim

Motion transfer enables controllable video generation by transferring temporal dynamics from a reference video to synthesize a new video conditioned on a target caption. However, existing Diffusion Transformer (DiT)-based methods are limited to single-object videos, restricting fine-grained control in real-world scenes with multiple objects. In this work, we introduce MotionGrounder, a DiT-based framework that firstly handles motion transfer with multi-object controllability. Our Flow-based Motion Signal (FMS) in MotionGrounder provides a stable motion prior for target video generation, while our Object-Caption Alignment Loss (OCAL) grounds object captions to their corresponding spatial regions. We further propose a new Object Grounding Score (OGS), which jointly evaluates (i) spatial alignment between source video objects and their generated counterparts and (ii) semantic consistency between each generated object and its target caption. Our experiments show that MotionGrounder consistently outperforms recent baselines across quantitative, qualitative, and human evaluations.

comment: Please visit our project page at https://kaist-viclab.github.io/motiongrounder-site/

☆ Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generation

Shuang Li, Chao Deng, Hang Chen, Liqun Liu, Zhenyu Hu, Te Cao, Mengge Xue, Yuan Chen, Peng Shu, Huan Yu, Jie Jiang

Subject-Driven Text-to-Image (T2I) Generation aims to preserve a subject's identity while editing its context based on a text prompt. A core challenge in this task is the "similarity-controllability paradox", where enhancing textual control often degrades the subject's fidelity, and vice-versa. We argue this paradox stems from the ambiguous role of text prompts, which are often tasked with describing both the subject and the desired modifications, leading to conflicting signals for the model. To resolve this, we propose DisCo, a novel framework that first Disntangles and then re-Couples visual and textual information. First, our textual-visual decoupling module isolates the sources of information: subject identity is extracted exclusively from the reference image with the entity word of the subject, while the text prompt is simplified to contain only the modification command, where the subject refers to general pronouns, eliminating descriptive ambiguity. However, this strict separation can lead to unnatural compositions between the subject and its contexts. We address this by designing a dedicated reward signal and using reinforcement learning to seamlessly recouple the visually-defined subject and the textually-generated context. Our approach effectively resolves the paradox, enabling simultaneous high-fidelity subject preservation and precise textual control. Extensive experiments demonstrate that our method achieves state-of-the-art performance, producing highly realistic and coherent images.

comment: Accepted by CVPR 2026 (Main)

☆ LinguDistill: Recovering Linguistic Ability in Vision- Language Models via Selective Cross-Modal Distillation

Patrick Amadeus Irawan, Erland Hilman Fuadi, Shanu Kumar, Alham Fikri Aji, Yova Kementchedjhieva

Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representation shift and cross-modal interference introduced during multimodal adaptation. Such loss is difficult to recover, even with targeted task-specific fine-tuning using standard objectives. Prior recovery approaches typically introduce additional modules that act as intermediate alignment layers to maintain or isolate modality-specific subspaces, which increases architectural complexity, adds parameters at inference time, and limits flexibility across models and settings. We propose LinguDistill, an adapter-free distillation method that restores linguistic capability by utilizing the original frozen LM as a teacher. We overcome the key challenge of enabling vision-conditioned teacher supervision by introducing layer-wise KV-cache sharing, which exposes the teacher to the student's multimodal representations without modifying the architecture of either model. We then selectively distill the teacher's strong linguistic signal on language-intensive data to recover language capability, while preserving the student's visual grounding on multimodal tasks. As a result, LinguDistill recovers $\sim$10% of the performance lost on language and knowledge benchmarks, while maintaining comparable performance on vision-heavy tasks. Our findings demonstrate that linguistic capability can be recovered without additional modules, providing an efficient and practical solution to modality-specific degradation in multimodal models.

☆ Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction

Patrick Glandorf, Thomas Norrenbrock, Bodo Rosenhahn

Vision Transformers (ViTs) have demonstrated state-ofthe-art performance in several benchmarks, yet their high computational costs hinders their practical deployment. Patch Pruning offers significant savings, but existing approaches restrict token reduction to deeper layers, leaving early-stage compression unexplored. This limits their potential for holistic efficiency. In this work, we present a novel Video Patch Pruning framework (VPP) that integrates temporal prior knowledge to enable efficient sparsity within early ViT layers. Our approach is motivated by the observation that prior features extracted from deeper layers exhibit strong foreground selectivity. Therefore we propose a fully differentiable module for temporal mapping to accurately select the most relevant patches in early network stages. Notably, the proposed method enables a patch reduction of up to 60% in dense prediction tasks, exceeding the capabilities of conventional image-based patch pruning, which typically operate around a 30% patch sparsity. VPP excels the high-sparsity regime, sustaining remarkable performance even when patch usage is reduced below 55%. Specifically, it preserves stable results with a maximal performance drop of 0.6% on the Youtube-VIS 2021 dataset.

comment: CVPR'26 Workshops

☆ Continual Vision-Language Learning for Remote Sensing: Benchmarking and Analysis

Xingxing Weng, Ruifeng Ni, Chao Pang, XiangYu Hao, Yishan Wang, Xiaokang Zhang, Wei Xu, Gui-Song Xia

Current remote sensing vision-language models (RS VLMs) demonstrate impressive performance in image interpretation but rely on static training data, limiting their ability to accommodate continuously emerging sensing modalities and downstream tasks. This exposes a fundamental challenge: enabling RS VLMs to continually adapt without catastrophic forgetting. Despite its practical importance, the continual learning capability of RS VLMs remains underexplored, and no dedicated benchmark currently exists. In this work, we present CLeaRS, a comprehensive benchmark for continual vision-language learning in remote sensing. CLeaRS comprises 10 curated subsets with over 207k image-text pairs, spanning diverse interpretation tasks, sensing modalities, and application scenarios. We further define three evaluation protocols: long-horizon, modality-incremental, and task-incremental settings, to systematically assess continual adaptation. Extensive benchmarking of diverse vision-language models reveals catastrophic forgetting across all settings. Moreover, representative continual learning methods, when adapted to RS VLMs, exhibit limited effectiveness in handling task, instruction, and modality transitions. Our findings underscore the need for developing continual learning methods tailored to RS VLMs.

comment: 23 pages, 7 figures, 9 tables

☆ Multicentric thrombus segmentation using an attention-based recurrent network with gradual modality dropout

Sofia Vargas-Ibarra, Vincent Vigneron, Hichem Maaref, Sonia Garcia-Salicetti

Detecting and delineating tiny targets in 3D brain scans is a central yet under-addressed challenge in medical imaging.In ischemic stroke, for instance, the culprit thrombus is small, low-contrast, and variably expressed across modalities(e.g., susceptibility-weighted T2 blooming, diffusion restriction on DWI/ADC), while real-world multi-center dataintroduce domain shifts, anisotropy, and frequent missing sequences. We introduce a methodology that couples an attention-based recurrent segmentation network (UpAttLLSTM), a training schedule that progressively increases the difficulty of hetero-modal learning, with gradual modality dropout, UpAttLLSTM aggregates context across slices via recurrent units (2.5D) and uses attention gates to fuse complementary cues across available sequences, making it robust to anisotropy and class imbalance. Gradual modality dropout systematically simulates site heterogeneity,noise, and missing modalities during training, acting as both augmentation and regularization to improve multi-center generalization. On a monocentric cohort, our approach detects thrombi in >90% of cases with a Dice score of 0.65. In a multi-center setting with missing modalities, it achieves-80% detection with a Dice score around 0.35. Beyond stroke, the proposed methodology directly transfers to other small-lesion tasks in 3D medical imaging where targets are scarce, subtle, and modality-dependent

☆ DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale

Sicheng Zuo, Zixun Xie, Wenzhao Zheng, Shaoqing Xu, Fang Li, Hanbing Li, Long Chen, Zhi-Xin Yang, Jiwen Lu

End-to-end autonomous driving has evolved from the conventional paradigm based on sparse perception into vision-language-action (VLA) models, which focus on learning language descriptions as an auxiliary task to facilitate planning. In this paper, we propose an alternative Vision-Geometry-Action (VGA) paradigm that advocates dense 3D geometry as the critical cue for autonomous driving. As vehicles operate in a 3D world, we think dense 3D geometry provides the most comprehensive information for decision-making. However, most existing geometry reconstruction methods (e.g., DVGT) rely on computationally expensive batch processing of multi-frame inputs and cannot be applied to online planning. To address this, we introduce a streaming Driving Visual Geometry Transformer (DVGT-2), which processes inputs in an online manner and jointly outputs dense geometry and trajectory planning for the current frame. We employ temporal causal attention and cache historical features to support on-the-fly inference. To further enhance efficiency, we propose a sliding-window streaming strategy and use historical caches within a certain interval to avoid repetitive computations. Despite the faster speed, DVGT-2 achieves superior geometry reconstruction performance on various datasets. The same trained DVGT-2 can be directly applied to planning across diverse camera configurations without fine-tuning, including closed-loop NAVSIM and open-loop nuScenes benchmarks.

comment: Code is available at \href{https://github.com/wzzheng/DVGT}

☆ Revisiting Human-in-the-Loop Object Retrieval with Pre-Trained Vision Transformers

Kawtar Zaher, Olivier Buisson, Alexis Joly

Building on existing approaches, we revisit Human-in-the-Loop Object Retrieval, a task that consists of iteratively retrieving images containing objects of a class-of-interest, specified by a user-provided query. Starting from a large unlabeled image collection, the aim is to rapidly identify diverse instances of an object category relying solely on the initial query and the user's Relevance Feedback, with no prior labels. The retrieval process is formulated as a binary classification task, where the system continuously learns to distinguish between relevant and non-relevant images to the query, through iterative user interaction. This interaction is guided by an Active Learning loop: at each iteration, the system selects informative samples for user annotation, thereby refining the retrieval performance. This task is particularly challenging in multi-object datasets, where the object of interest may occupy only a small region of the image within a complex, cluttered scene. Unlike object-centered settings where global descriptors often suffice, multi-object images require more adapted, localized descriptors. In this work, we formulate and revisit the Human-in-the-Loop Object Retrieval task by leveraging pre-trained ViT representations, and addressing key design questions, including which object instances to consider in an image, what form the annotations should take, how Active Selection should be applied, and which representation strategies best capture the object's features. We compare several representation strategies across multi-object datasets highlighting trade-offs between capturing the global context and focusing on fine-grained local object details. Our results offer practical insights for the design of effective interactive retrieval pipelines based on Active Learning for object class retrieval.

☆ Compact Keyframe-Optimized Multi-Agent Gaussian Splatting SLAM

Monica M. Q. Li, Pierre-Yves Lajoie, Jialiang Liu, Giovanni Beltrame

Efficient multi-agent 3D mapping is essential for robotic teams operating in unknown environments, but dense representations hinder real-time exchange over constrained communication links. In multi-agent Simultaneous Localization and Mapping (SLAM), systems typically rely on a centralized server to merge and optimize the local maps produced by individual agents. However, sharing these large map representations, particularly those generated by recent methods such as Gaussian Splatting, becomes a bottleneck in real-world scenarios with limited bandwidth. We present an improved multi-agent RGB-D Gaussian Splatting SLAM framework that reduces communication load while preserving map fidelity. First, we incorporate a compaction step into our SLAM system to remove redundant 3D Gaussians, without degrading the rendering quality. Second, our approach performs centralized loop closure computation without initial guess, operating in two modes: a pure rendered-depth mode that requires no data beyond the 3D Gaussians, and a camera-depth mode that includes lightweight depth images for improved registration accuracy and additional Gaussian pruning. Evaluation on both synthetic and real-world datasets shows up to 85-95\% reduction in transmitted data compared to state-of-the-art approaches in both modes, bringing 3D Gaussian multi-agent SLAM closer to practical deployment in real-world scenarios. Code: https://github.com/lemonci/coko-slam

☆ Multimodal Language Models Cannot Spot Spatial Inconsistencies

Om Khangaonkar, Hadi J. Rad, Hamed Pirsiavash

Spatial consistency is a fundamental property of the visual world and a key requirement for models that aim to understand physical reality. Despite recent advances, multimodal large language models (MLLMs) often struggle to reason about 3D geometry across multiple views. Rather than asking models to describe scene attributes, we introduce a more challenging task: given two views of the same scene, identify the object that violates 3D motion consistency. We propose a simple and scalable method for generating realistic, spatially inconsistent image pairs from multi-view scenes, enabling systematic evaluation of this capability. Our results show that state-of-the-art MLLMs significantly underperform human observers and exhibit substantial variability across different scene attributes, revealing a fragile and incomplete understanding of 3D structure. We hope our findings underscore the need for approaches that develop a more deeply grounded understanding of the physical world.

☆ HICT: High-precision 3D CBCT reconstruction from a single X-ray

Wen Ma, Jiaxiang Liu, Zikai Xiao, Ziyang Wang, Feng Yang, Zuozhu Liu

Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single low-dose panoramic X-ray is a promising alternative but remains challenging due to geometric inconsistencies and limited accuracy. We propose HiCT, a two-stage framework that first generates geometrically consistent multi-view projections from a single panoramic image using a video diffusion model, and then reconstructs high-fidelity CBCT from the projections using a ray-based dynamic attention network and an X-ray sampling strategy. To support this, we built XCT, a large-scale dataset combining public CBCT data with 500 paired PX-CBCT cases. Extensive experiments show that HiCT achieves state-of-the-art performance, delivering accurate and geometrically consistent reconstructions for clinical use.

☆ An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models

Lennart Maack, Alexander Schlaefer

Surgical video understanding is a crucial prerequisite for advancing Computer-Assisted Surgery. While vision-language models (VLMs) have recently been applied to the surgical domain, existing surgical vision-language datasets lack in capturing and evaluating complex, interleaved spatial-temporal dynamics. Creating large scale datasets that accurately represent fine-grained spatial-temporal relationships in surgical videos is challenging due to costly manual annotations or error-prone generation using large language models. To address this gap, we introduce the SurgSTU-Pipeline, a deterministic generation pipeline featuring temporal and spatial continuity filtering to reliably create surgical datasets for fine-grained spatial-temporal multimodal understanding. Applying this pipeline to publicly available surgical datasets, we create the SurgSTU dataset, comprising 7515 video clips densely extended with 150k fine-grained spatial-temporal question-answer samples. Our comprehensive evaluation shows that while state-of-the-art generalist VLMs struggle in zero-shot settings, their spatial-temporal capabilities can be improved through in-context learning. A fine-tuned VLM on the SurgSTU training dataset achieves highest performance among all spatial-temporal tasks, validating the dataset's efficacy to improve spatial-temporal understanding of VLMs in surgical videos. Code will be made publicly available.

☆ Using predefined vector systems to speed up neural network multimillion class classification

Nikita Gabdullin, Ilya Androsov

Label prediction in neural networks (NNs) has O(n) complexity proportional to the number of classes. This holds true for classification using fully connected layers and cosine similarity with some set of class prototypes. In this paper we show that if NN latent space (LS) geometry is known and possesses specific properties, label prediction complexity can be significantly reduced. This is achieved by associating label prediction with the O(1) complexity closest cluster center search in a vector system used as target for latent space configuration (LSC). The proposed method only requires finding indexes of several largest and lowest values in the embedding vector making it extremely computationally efficient. We show that the proposed method does not change NN training accuracy computational results. We also measure the time required by different computational stages of NN inference and label prediction on multiple datasets. The experiments show that the proposed method allows to achieve up to 11.6 times overall acceleration over conventional methods. Furthermore, the proposed method has unique properties which allow to predict the existence of new classes.

comment: 12 pages, 2 figures, 3 tables, 2 algorithms, 1 theorem, 1 lemma

☆ PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognition

Samar Ansari

Existing research on privacy-preserving Human Activity Recognition (HAR) typically evaluates methods against a binary paradigm: clear video versus a single privacy transformation. This limits cross-method comparability and obscures the nuanced relationship between privacy strength and recognition utility. We introduce \textit{PrivHAR-Bench}, a multi-tier benchmark dataset designed to standardize the evaluation of the \textit{Privacy-Utility Trade-off} in video-based action recognition. PrivHAR-Bench applies a graduated spectrum of visual privacy transformations: from lightweight spatial obfuscation to cryptographic block permutation, to a curated subset of 15 activity classes selected for human articulation diversity. Each of the 1,932 source videos is distributed across 9 parallel tiers of increasing privacy strength, with additional background-removed variants to isolate the contribution of human motion features from contextual scene bias. We provide lossless frame sequences, per-frame bounding boxes, estimated pose keypoints with joint-level confidence scores, standardized group-based train/test splits, and an evaluation toolkit computing recognition accuracy and privacy metrics. Empirical validation using R3D-18 demonstrates a measurable and interpretable degradation curve across tiers, with within-tier accuracy declining from 88.8\% (clear) to 53.5\% (encrypted, background-removed) and cross-domain accuracy collapsing to 4.8\%, establishing PrivHAR-Bench as a controlled benchmark for comparing privacy-preserving HAR methods under standardized conditions. The dataset, generation pipeline, and evaluation code are publicly available.

☆ IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models

Dong-Jae Lee, Sunghyun Baek, Junmo Kim

Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens. Existing token pruning methods mitigate this issue through empirical approaches while overlooking the internal mechanism of attention. In this paper, we propose a novel training free token pruning framework grounded in the dual form perspective of attention. We reformulate attention as an implicit linear layer whose weight matrix is the sum of rank 1 outer products, each generated by a single token's key value pair. Token pruning thus reduces to selecting an optimal subset of these rank 1 updates that best approximates the original dual weight matrix. Extending this perspective to standard softmax attention in LVLMs, we derive a novel metric quantifying both a token's information magnitude and information duplication. To efficiently select the subset with the proposed metric, we introduce Progressive Chunked Maximal Marginal Relevance. Extensive experiments demonstrate that our method achieves a better trade off between performance and efficiency, while providing another perspective on existing pruning approaches.

☆ A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR

Merveilles Agbeti-messan, Thierry Paquet, Clément Chatelain, Pierrick Tranouez, Stéphane Nicolas

End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts. While Transformer-based recognizers dominate current research, their quadratic complexity limits efficient paragraph-level transcription and large-scale deployment. We investigate linear-time State-Space Models (SSMs), specifically Mamba, as a scalable alternative to Transformer-based sequence modeling for OCR. We present to our knowledge, the first OCR architecture based on SSMs, combining a CNN visual encoder with bi-directional and autoregressive Mamba sequence modeling, and conduct a large-scale benchmark comparing SSMs with Transformer- and BiLSTM-based recognizers. Multiple decoding strategies (CTC, autoregressive, and non-autoregressive) are evaluated under identical training conditions alongside strong neural baselines (VAN, DAN, DANIEL) and widely used off-the-shelf OCR engines (PERO-OCR, Tesseract OCR, TrOCR, Gemini). Experiments on historical newspapers from the Bibliothèque nationale du Luxembourg, with newly released >99% verified gold-standard annotations, and cross-dataset tests on Fraktur and Antiqua lines, show that all neural models achieve low error rates (~2% CER), making computational efficiency the main differentiator. Mamba-based models maintain competitive accuracy while halving inference time and exhibiting superior memory scaling (1.26x vs 2.30x growth at 1000 chars), reaching 6.07% CER at the severely degraded paragraph level compared to 5.24% for DAN, while remaining 2.05x faster. We release code, trained models, and standardized evaluation protocols to enable reproducible research and guide practitioners in large-scale cultural heritage OCR.

☆ TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning

Soumya Shamarao Jahagirdar, Edson Araujo, Anna Kukleva, M. Jehanzeb Mirza, Saurabhchand Bhati, Samuel Thomas, Brian Kingsbury, Rogerio Feris, James R. Glass, Hilde Kuehne

Recent video reasoning models have shown strong results on temporal and multimodal understanding, yet they depend on large-scale supervised data and multi-stage training pipelines, making them costly to train and difficult to adapt to new domains. In this work, we leverage the paradigm of Test-Time Reinforcement Learning on video-language data to allow for adapting a pretrained model to incoming video samples at test-time without explicit labels. The proposed test-time adaptation for video approach (TTA-Vid) combines two components that work simultaneously: (1) a test-time adaptation that performs step-by-step reasoning at inference time on multiple frame subsets. We then use a batch-aware frequency-based reward computed across different frame subsets as pseudo ground truth to update the model. It shows that the resulting model trained on a single batch or even a single sample from a dataset, is able to generalize at test-time to the whole dataset and even across datasets. Because the adaptation occurs entirely at test time, our method requires no ground-truth annotations or dedicated training splits. Additionally, we propose a multi-armed bandit strategy for adaptive frame selection that learns to prioritize informative frames, guided by the same reward formulation. Our evaluation shows that TTA-Vid yields consistent improvements across various video reasoning tasks and is able to outperform current state-of-the-art methods trained on large-scale data. This highlights the potential of test-time reinforcement learning for temporal multimodal understanding.

☆ TP-Seg: Task-Prototype Framework for Unified Medical Lesion Segmentation

Jiawei Xu, Qiangqiang Zhou, Dandan Zhu, Yong Chen, Yugen Yi, Xiaoqi Zhao

Building a unified model with a single set of parameters to efficiently handle diverse types of medical lesion segmentation has become a crucial objective for AI-assisted diagnosis. Existing unified segmentation approaches typically rely on shared encoders across heterogeneous tasks and modalities, which often leads to feature entanglement, gradient interference, and suboptimal lesion discrimination. In this work, we propose TP-Seg, a task-prototype framework for unified medical lesion segmentation. On one hand, the task-conditioned adapter effectively balances shared and task-specific representations through a dual-path expert structure, enabling adaptive feature extraction across diverse medical imaging modalities and lesion types. On the other hand, the prototype-guided task decoder introduces learnable task prototypes as semantic anchors and employs a cross-attention mechanism to achieve fine-grained modeling of task-specific foreground and background semantics. Without bells and whistles, TP-Seg consistently outperforms specialized, general and unified segmentation methods across 8 different medical lesion segmentation tasks covering multiple imaging modalities, demonstrating strong generalization, scalability and clinical applicability.

☆ MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data ACM MM

Clémentine Grethen, Yuang Shi, Simone Gasparini, Géraldine Morin

Accurate perception of lunar surfaces is critical for modern lunar exploration missions. However, developing robust learning-based perception systems is hindered by the lack of datasets that provide both geometric and photometric supervision. Existing lunar datasets typically lack either geometric ground truth, photometric realism, illumination diversity, or large-scale coverage. In this paper, we introduce MoonAnything, a unified benchmark built on real lunar topography with physically-based rendering, providing the first comprehensive geometric and photometric supervision under diverse illumination with large scale. The benchmark comprises two complementary sub-datasets : i) LunarGeo provides stereo images with corresponding dense depth maps and camera calibration enabling 3D reconstruction and pose estimation; ii) LunarPhoto provides photorealistic images using a spatially-varying BRDF model, along with multi-illumination renderings under real solar configurations, enabling reflectance estimation and illumination-robust perception. Together, these datasets offer over 130K samples with comprehensive supervision. Beyond lunar applications, MoonAnything offers a unique setting and challenging testbed for algorithms under low-textured, high-contrast conditions and applies to other airless celestial bodies and could generalize beyond. We establish baselines using state-of-the-art methods and release the complete dataset along with generation tools to support community extension: https://github.com/clementinegrethen/MoonAnything.

comment: Accepted to ACM MMSys 2026

☆ CL-VISTA: Benchmarking Continual Learning in Video Large Language Models

Haiyang Guo, Yichen Shi, Fei Zhu, Wenzhuo Liu, Hongbo Zhao, Fanhu Zeng, Shijie Ma, Da-Han Wang, Xu-Yao Zhang

Video Large Language Models (Video-LLMs) require continual learning to adapt to non-stationary real-world data. However, existing benchmarks fall short of evaluating modern foundation models: many still rely on models without large-scale pre-training, and prevailing benchmarks typically partition a single dataset into sub-tasks, resulting in high task redundancy and negligible forgetting on pre-trained Video-LLMs. To address these limitations, we propose CL-VISTA, a benchmark tailored for continual video understanding of Video-LLMs. By curating 8 diverse tasks spanning perception, understanding, and reasoning, CL-VISTA induces substantial distribution shifts that effectively expose catastrophic forgetting. To systematically assess CL methods, we establish a comprehensive evaluation framework comprising 6 distinct protocols across 3 critical dimensions: performance, computational efficiency, and memory footprint. Notably, the performance dimension incorporates a general video understanding assessment to assess whether CL methods genuinely enhance foundational intelligence or merely induce task-specific overfitting. Extensive benchmarking of 10 mainstream CL methods reveals a fundamental trade-off: no single approach achieves universal superiority across all dimensions. Methods that successfully mitigate catastrophic forgetting tend to compromise generalization or incur prohibitive computational and memory overheads. We hope CL-VISTA provides critical insights for advancing continual learning in multimodal foundation models.

comment: Preprint

☆ When AI and Experts Agree on Error: Intrinsic Ambiguity in Dermatoscopic Images

Loris Cino, Pier Luigi Mazzeo, Alessandro Martella, Giulia Radi, Renato Rossi, Cosimo Distante

The integration of artificial intelligence (AI), particularly Convolutional Neural Networks (CNNs), into dermatological diagnosis demonstrates substantial clinical potential. While existing literature predominantly benchmarks algorithmic performance against human experts, our study adopts a novel perspective by investigating the intrinsic complexity of dermatoscopic images. Through rigorous experimentation with multiple CNN architectures, we isolated a subset of images systematically misclassified across all models-a phenomenon statistically proven to exceed random chance. To determine if these failures stem from algorithmic biases or inherent visual ambiguity, expert dermatologists independently evaluated these challenging cases alongside a control group. The results revealed a collapse in human diagnostic performance on the AI-misclassified images. First, agreement with ground-truth labels plummeted, with Cohen's kappa dropping to a mere 0.08 for the difficult images, compared to a 0.61 for the control group. Second, we observed a severe deterioration in expert consensus; inter-rater reliability among physicians fell from moderate concordance (Fleiss kappa = 0.456) on control images to only modest agreement (Fleiss kappa = 0.275) on difficult cases. We identified image quality as a primary driver of these dual systematic failures. To promote transparency and reproducibility, all data, code, and trained models have been made publicly available

☆ DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization

Zhengxian Yang, Fei Xie, Xutao Xue, Rui Zhang, Taicheng Huang, Yang Liu, Mengqi Ji, Tao Yu

3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering, greatly advancing VR/AR applications. Fisheye cameras, with their wider field of view (FOV), promise high-quality reconstructions from fewer inputs and have recently attracted much attention. However, since 3DGS relies on rasterization, most subsequent works involving fisheye camera inputs first undistort images before training, which introduces two problems: 1) Black borders at image edges cause information loss and negate the fisheye's large FOV advantage; 2) Undistortion's stretch-and-interpolate resampling spreads each pixel's value over a larger area, diluting detail density -- causes 3DGS overfitting these low-frequency zones, producing blur and floating artifacts. In this work, we integrate fisheye camera model into the original 3DGS framework, enabling native fisheye image input for training without preprocessing. Despite correct modeling, we observed that the reconstructed scenes still exhibit floaters at image edges: Distortion increases toward the periphery, and 3DGS's original per-iteration random-selecting-view optimization ignores the cross-view correlations of a Gaussian, leading to extreme shapes (e.g., oversized or elongated) that degrade reconstruction quality. To address this, we introduce a feature-overlap-driven cross-view joint optimization strategy that establishes consistent geometric and photometric constraints across views-a technique equally applicable to existing pinhole-camera-based pipelines. Our DirectFisheye-GS matches or surpasses state-of-the-art performance on public datasets.

comment: CVPR 2026

☆ LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics

Calvin Galagain, Martyna Poreba, François Goulette, Cyrill Stachniss

Panoptic segmentation is a key enabler for robotic perception, as it unifies semantic understanding with object-level reasoning. However, the increasing complexity of state-of-the-art models makes them unsuitable for deployment on resource-constrained platforms such as mobile robots. We propose a novel approach called LiPS that addresses the challenge of efficient-to-compute panoptic segmentation with a lightweight design that retains query-based decoding while introducing a streamlined feature extraction and fusion pathway. It aims at providing a strong panoptic segmentation performance while substantially lowering the computational demands. Evaluations on standard benchmarks demonstrate that LiPS attains accuracy comparable to much heavier baselines, while providing up to 4.5 higher throughput, measured in frames per second, and requiring nearly 6.8 times fewer computations. This efficiency makes LiPS a highly relevant bridge between modern panoptic models and real-world robotic applications.

comment: Submitted to IEEE ICIP 2026. Under review

☆ TALENT: Target-aware Efficient Tuning for Referring Image Segmentation

Shuo Jin, Siyue Yu, Bingfeng Zhang, Chao Yao, Meiqin Liu, Jimin Xiao

Referring image segmentation aims to segment specific targets based on a natural text expression. Recently, parameter-efficient tuning (PET) has emerged as a promising paradigm. However, existing PET-based methods often suffer from the fact that visual features can't emphasize the text-referred target instance but activate co-category yet unrelated objects. We analyze and quantify this problem, terming it the `non-target activation' (NTA) issue. To address this, we propose a novel framework, TALENT, which utilizes target-aware efficient tuning for PET-based RIS. Specifically, we first propose a Rectified Cost Aggregator (RCA) to efficiently aggregate text-referred features. Then, to calibrate `NTA' into accurate target activation, we adopt a Target-aware Learning Mechanism (TLM), including contextual pairwise consistency learning and target-centric contrastive learning. The former uses the sentence-level text feature to achieve a holistic understanding of the referent and constructs a text-referred affinity map to optimize the semantic association of visual features. The latter further enhances target localization to discover the distinct instance while suppressing associations with other unrelated ones. The two objectives work in concert and address `NTA' effectively. Extensive evaluations show that TALENT outperforms existing methods across various metrics (e.g., 2.5\% mIoU gains on G-Ref val set). Our codes will be released at: https://github.com/Kimsure/TALENT.

comment: Accepted by CVPR26 Findings

☆ Fluently Lying: Adversarial Robustness Can Be Substrate-Dependent

Daye Kang, Hyeongboo Baek

The primary tools used to monitor and defend object detectors under adversarial attack assume that when accuracy degrades, detection count drops in tandem. This coupling was assumed, not measured. We report a counterexample observed on a single model: under standard PGD, EMS-YOLO, a spiking neural network (SNN) object detector, retains more than 70% of its detections while mAP collapses from 0.528 to 0.042. We term this count-preserving accuracy collapse Quality Corruption (QC), to distinguish it from the suppression that dominates untargeted evaluation. Across four SNN architectures and two threat models (l-infinity and l-2), QC appears only in one of the four detectors tested (EMS-YOLO). On this model, all five standard defense components fail to detect or mitigate QC, suggesting the defense ecosystem may rely on a shared assumption calibrated on a single substrate. These results provide, to our knowledge, the first evidence that adversarial failure modes can be substrate-dependent.

comment: 14 pages, 4 figures, 3 tables

☆ KG-CMI: Knowledge graph enhanced cross-Mamba interaction for medical visual question answering

Xianyao Zheng, Hong Yu, Hui Cui, Changming Sun, Xiangyu Li, Ran Su, Leyi Wei, Jia Zhou, Junbo Wang, Qiangguo Jin

Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent methods fail to fully leverage domain-specific medical knowledge, making it difficult to accurately associate lesion features in medical images with key diagnostic criteria. Additionally, classification-based approaches typically rely on predefined answer sets. Treating Med-VQA as a simple classification problem limits its ability to adapt to the diversity of free-form answers and may overlook detailed semantic information in those answers. To address these challenges, we propose a knowledge graph enhanced cross-Mamba interaction (KG-CMI) framework, which consists of a fine-grained cross-modal feature alignment (FCFA) module, a knowledge graph embedding (KGE) module, a cross-modal interaction representation (CMIR) module, and a free-form answer enhanced multi-task learning (FAMT) module. The KG-CMI learns cross-modal feature representations for images and texts by effectively integrating professional medical knowledge through a graph, establishing associations between lesion features and disease knowledge. Moreover, FAMT leverages auxiliary knowledge from open-ended questions, improving the model's capability for open-ended Med-VQA. Experimental results demonstrate that KG-CMI outperforms existing state-of-the-art methods on three Med-VQA datasets, i.e., VQA-RAD, SLAKE, and OVQA. Additionally, we conduct interpretability experiments to further validate the framework's effectiveness.

☆ Towards Viewpoint-Robust End-to-End Autonomous Driving with 3D Foundation Model Priors

Hiroki Hashimoto, Hiromichi Goto, Hiroyuki Sugai, Hiroshi Kera, Kazuhiko Kawamoto

Robust trajectory planning under camera viewpoint changes is important for scalable end-to-end autonomous driving. However, existing models often depend heavily on the camera viewpoints seen during training. We investigate an augmentation-free approach that leverages geometric priors from a 3D foundation model. The method injects per-pixel 3D positions derived from depth estimates as positional embeddings and fuses intermediate geometric features through cross-attention. Experiments on the VR-Drive camera viewpoint perturbation benchmark show reduced performance degradation under most perturbation conditions, with clear improvements under pitch and height perturbations. Gains under longitudinal translation are smaller, suggesting that more viewpoint-agnostic integration is needed for robustness to camera viewpoint changes.

comment: Accepted at CVPR Workshop on Simulation for Autonomous Driving 2026

☆ HarassGuard: Detecting Harassment Behaviors in Social Virtual Reality with Vision-Language Models

Junhee Lee, Minseok Kim, Hwanjo Heo, Seungwon Woo, Jinwoo Kim

Social Virtual Reality (VR) platforms provide immersive social experiences but also expose users to serious risks of online harassment. Existing safety measures are largely reactive, while proactive solutions that detect harassment behavior during an incident often depend on sensitive biometric data, raising privacy concerns. In this paper, we present HarassGuard, a vision-language model (VLM) based system that detects physical harassment in social VR using only visual input. We construct an IRB-approved harassment vision dataset, apply prompt engineering, and fine-tune VLMs to detect harassment behavior by considering contextual information in social VR. Experimental results demonstrate that HarassGuard achieves competitive performance compared to state-of-the-art baselines (i.e., LSTM/CNN, Transformer), reaching an accuracy of up to 88.09% in binary classification and 68.85% in multi-class classification. Notably, HarassGuard matches these baselines while using significantly fewer fine-tuning samples (200 vs. 1,115), offering unique advantages in contextual reasoning and privacy-preserving detection.

comment: To appear in the 2026 TVCG Special Issue on the 2026 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)

☆ FecalFed: Privacy-Preserving Poultry Disease Detection via Federated Learning

Tien-Yu Chi

Early detection of highly pathogenic avian influenza (HPAI) and endemic poultry diseases is critical for global food security. While computer vision models excel at classifying diseases from fecal imaging, deploying these systems at scale is bottlenecked by farm data privacy concerns and institutional data silos. Furthermore, existing open-source agricultural datasets frequently suffer from severe, undocumented data contamination. In this paper, we introduce $\textbf{FecalFed}$, a privacy-preserving federated learning framework for poultry disease classification. We first curate and release $\texttt{poultry-fecal-fl}$, a rigorously deduplicated dataset of 8,770 unique images across four disease classes, revealing and eliminating a 46.89$\%$ duplication rate in popular public repositories. To simulate realistic agricultural environments, we evaluate FecalFed under highly heterogeneous, non-IID conditions (Dirichlet $α=0.5$). While isolated single-farm training collapses under this data heterogeneity, yielding only 64.86$\%$ accuracy, our federated approach recovers performance without centralizing sensitive data. Specifically, utilizing server-side adaptive optimization (FedAdam) with a Swin-Small architecture achieves 90.31$\%$ accuracy, closely approaching the centralized upper bound of 95.10\%. Furthermore, we demonstrate that an edge-optimized Swin-Tiny model maintains highly competitive performance at 89.74$\%$, establishing a highly efficient, privacy-first blueprint for on-farm avian disease monitoring.

comment: Accepted to the CVPR 2026 Workshop on Vision for Agriculture

☆ STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPO

Pukun Zhao, Longxiang Wang, Chen Chen, Peicheng Wang, Fanqing Zhou, Runze Li, Haojian Huang

Structured spatial navigation is a core benchmark for Large Language Models (LLMs) spatial reasoning. Existing paradigms like Visualization-of-Thought (VoT) are prone to cascading errors in complex topologies. To solve this, we propose STAR, a two-stage framework grounded on topological anchors, and introduce the RedMaze-23K dataset with human-inspired turnpoint annotations. The first stage uses supervised fine-tuning to help models internalize spatial semantics and prune redundant paths. The second adopts Spatial-aware Segment-level Direct Preference Optimization (SDPO) to refine self-correction in long-horizon navigation. Experiments show STAR achieves state-of-the-art performance among open-source models: its 32B variant outperforms DeepSeek-V3 (29.27% vs. 25.00%) and reaches 82.4% of GPT-4's performance.

comment: 9 pages, 6 figures, 4 tables, Accepted by ICME 2026

☆ Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning

Yichen Xie, Yixiao Wang, Shuqi Zhao, Cheng-En Wu, Masayoshi Tomizuka, Jianwen Xie, Hao-Shu Fang

The generalization ability of imitation learning policies for robotic manipulation is fundamentally constrained by the diversity of expert demonstrations, while collecting demonstrations across varied environments is costly and difficult in practice. In this paper, we propose a practical framework that exploits inherent scene diversity without additional human effort by scaling camera views during demonstration collection. Instead of acquiring more trajectories, multiple synchronized camera perspectives are used to generate pseudo-demonstrations from each expert trajectory, which enriches the training distribution and improves viewpoint invariance in visual representations. We analyze how different action spaces interact with view scaling and show that camera-space representations further enhance diversity. In addition, we introduce a multiview action aggregation method that allows single-view policies to benefit from multiple cameras during deployment. Extensive experiments in simulation and real-world manipulation tasks demonstrate significant gains in data efficiency and generalization compared to single-view baselines. Our results suggest that scaling camera views provides a practical and scalable solution for imitation learning, which requires minimal additional hardware setup and integrates seamlessly with existing imitation learning algorithms. The website of our project is https://yichen928.github.io/robot_multiview.

☆ TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detection

Zhijin He, Shuo Jin, Siyue Yu, Shuwei Wu, Bingfeng Zhang, Li Yu, Jimin Xiao

Co-salient Object Detection (CoSOD) aims to segment salient objects that consistently appear across a group of related images. Despite the notable progress achieved by recent training-based approaches, they still remain constrained by the closed-set datasets and exhibit limited generalization. However, few studies explore the potential of Vision Foundation Models (VFMs) to address CoSOD, which demonstrate a strong generalized ability and robust saliency understanding. In this paper, we investigate and leverage VFMs for CoSOD, and further propose a novel training-free method, TF-SSD, through the synergy between SAM and DINO. Specifically, we first utilize SAM to generate comprehensive raw proposals, which serve as a candidate mask pool. Then, we introduce a quality mask generator to filter out redundant masks, thereby acquiring a refined mask set. Since this generator is built upon SAM, it inherently lacks semantic understanding of saliency. To this end, we adopt an intra-image saliency filter that employs DINO's attention maps to identify visually salient masks within individual images. Moreover, to extend saliency understanding across group images, we propose an inter-image prototype selector, which computes similarity scores among cross-image prototypes to select masks with the highest score. These selected masks serve as final predictions for CoSOD. Extensive experiments show that our TF-SSD outperforms existing methods (e.g., 13.7\% gains over the recent training-free method). Codes are available at https://github.com/hzz-yy/TF-SSD.

comment: Accepted by CVPR26

☆ Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations

Youyu Chen, Junjun Jiang, Yueru Luo, Kui Jiang, Xianming Liu, Xu Yan, Dave Zhenyu Chen

With recent advances, Feed-forward Reconstruction Models (FFRMs) have demonstrated great potential in reconstruction quality and adaptiveness to multiple downstream tasks. However, the excessive reliance on multi-view geometric annotations, e.g. 3D point maps and camera poses, makes the fully-supervised training scheme of FFRMs difficult to scale up. In this paper, we propose Reliev3R, a weakly-supervised paradigm for training FFRMs from scratch without cost-prohibitive multi-view geometric annotations. Relieving the reliance on geometric sensory data and compute-exhaustive structure-from-motion preprocessing, our method draws 3D knowledge directly from monocular relative depths and image sparse correspondences given by zero-shot predictions of pretrained models. At the core of Reliev3R, we design an ambiguity-aware relative depth loss and a trigonometry-based reprojection loss to facilitate supervision for multi-view geometric consistency. Training from scratch with the less data, Reliev3R catches up with its fully-supervised sibling models, taking a step towards low-cost 3D reconstruction supervisions and scalable FFRMs.

comment: Accepted by CVPR2026

☆ Neuropsychiatric Deviations From Normative Profiles: An MRI-Derived Marker for Early Alzheimer's Disease Detection

Synne Hjertager Osenbroch, Lisa Ramona Rosvold, Yao Lu, Alvaro Fernandez-Quilez

Neuropsychiatric symptoms (NPS) such as depression and apathy are common in Alzheimer's disease (AD) and often precede cognitive decline. NPS assessments hold promise as early detection markers due to their correlation with disease progression and their non-invasive nature. Yet current tools cannot distinguish whether NPS are part of aging or early signs of AD, limiting their utility. We present a deep learning-based normative modelling framework to identify atypical NPS burden from structural MRI. A 3D convolutional neural network was trained on cognitively stable participants from the Alzheimer's Disease Neuroimaging Initiative, learning the mapping between brain anatomy and Neuropsychiatric Inventory Questionnaire (NPIQ) scores. Deviations between predicted and observed scores defined the Divergence from NPIQ scores (DNPI). Higher DNPI was associated with future AD conversion (adjusted OR=2.5; p < 0.01) and achieved predictive accuracy comparable to cerebrospinal fluid AB42 (AUC=0.74 vs 0.75). Our approach supports scalable, non-invasive strategies for early AD detection.

comment: Accepted and to be presented (ORAL) in ISBI 2026

♻ ☆ SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization

Ishrith Gowda, Chunwei Liu

Multi-site neuroimaging analysis is fundamentally confounded by scanner-induced covariate shifts, where the marginal distribution of voxel intensities $P(\mathbf{x})$ varies non-linearly across acquisition protocols while the conditional anatomy $P(\mathbf{y}|\mathbf{x})$ remains constant. This is particularly detrimental to radiomic reproducibility, where acquisition variance often exceeds biological pathology variance. Existing statistical harmonization methods (e.g., ComBat) operate in feature space, precluding spatial downstream tasks, while standard deep learning approaches are theoretically bounded by local effective receptive fields (ERF), failing to model the global intensity correlations characteristic of field-strength bias. We propose SA-CycleGAN-2.5D, a domain adaptation framework motivated by the $HΔH$-divergence bound of Ben-David et al., integrating three architectural innovations: (1) A 2.5D tri-planar manifold injection preserving through-plane gradients $\nabla_z$ at $O(HW)$ complexity; (2) A U-ResNet generator with dense voxel-to-voxel self-attention, surpassing the $O(\sqrt{L})$ receptive field limit of CNNs to model global scanner field biases; and (3) A spectrally-normalized discriminator constraining the Lipschitz constant ($K_D \le 1$) for stable adversarial optimization. Evaluated on 654 glioma patients across two institutional domains (BraTS and UPenn-GBM), our method reduces Maximum Mean Discrepancy (MMD) by 99.1% ($1.729 \to 0.015$) and degrades domain classifier accuracy to near-chance (59.7%). Ablation confirms that global attention is statistically essential (Cohen's $d = 1.32$, $p < 0.001$) for the harder heterogeneous-to-homogeneous translation direction. By bridging 2D efficiency and 3D consistency, our framework yields voxel-level harmonized images that preserve tumor pathophysiology, enabling reproducible multi-center radiomic analysis.

comment: 12 pages, 5 figures, 5 tables. Submitted to MICCAI 2026

♻ ☆ Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

Ryan Ramos, Vladan Stojnić, Giorgos Kordopatis-Zilos, Yuta Nakashima, Giorgos Tolias, Noa Garcia

Prior work has analyzed the robustness of visual encoders to image transformations and corruptions, particularly in cases where such alterations are not seen during training. When this occurs, they introduce a form of distribution shift at test time, often leading to performance degradation. The primary focus has been on severe corruptions that, when applied aggressively, distort useful signals necessary for accurate semantic predictions. We take a different perspective by analyzing parameters of the image acquisition process and transformations that may be subtle or even imperceptible to the human eye. We find that such parameters are systematically encoded in the learned visual representations and can be easily recovered. More strikingly, their presence can have a profound impact, either positively or negatively, on semantic predictions. This effect depends on whether there is a strong correlation or anti-correlation between semantic labels and these acquisition-based or processing-based labels. Our code and data are available at: https://github.com/ryan-caesar-ramos/visual-encoder-traces

comment: 8 main pages, supplementary attached, ICCV 2025 highlight

♻ ☆ ActErase: A Training-Free Paradigm for Precise Concept Erasure via Activation Redirection

Yi Sun, Xinhao Zhong, Hongyan Li, Yimin Zhou, Junhao Li, Bin Chen, Xuan Wang

Recent advances in text-to-image diffusion models have demonstrated remarkable generation capabilities, yet they raise significant concerns regarding safety, copyright, and ethical implications. Existing concept erasure methods address these risks by removing sensitive concepts from pre-trained models, but most of them rely on data-intensive and computationally expensive fine-tuning, which poses a critical limitation. To overcome these challenges, inspired by the observation that the model's activations are predominantly composed of generic concepts, with only a minimal component can represent the target concept, we propose a novel training-free method (ActErase) for efficient concept erasure. Specifically, the proposed method operates by identifying activation difference regions via prompt-pair analysis, extracting target activations and dynamically replacing input activations during forward passes. Comprehensive evaluations across three critical erasure tasks (nudity, artistic style, and object removal) demonstrates that our training-free method achieves state-of-the-art (SOTA) erasure performance, while effectively preserving the model's overall generative capability. Our approach also exhibits strong robustness against adversarial attacks, establishing a new plug-and-play paradigm for lightweight yet effective concept manipulation in diffusion models.

♻ ☆ LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting

Xuan Deng, Xiandong Meng, Hengyu Man, Qiang Zhu, Tiange Zhang, Debin Zhao, Xiaopeng Fan

Although 3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, its prohibitive storage overhead severely hinders practical deployment. Recent anchor-based 3DGS compression schemes reduce gaussian redundancy through some advanced context models. However, they overlook explicit geometric dependencies, leading to structural degradation and suboptimal ratedistortion performance. In this paper, we propose a Local Geometry-aware Hierarchical Context Compression framework for 3DGS(LG-HCC) that incorporates inter-anchor geometric correlations into anchor pruning and entropy coding for compact representation. Specifically, we introduce an Neighborhood-Aware Anchor Pruning (NAAP) strategy, which evaluates anchor importance via weighted neighborhood feature aggregation and then merges low-contribution anchors into salient neighbors, yielding a compact yet geometry-consistent anchor set. Moreover, we further develop a hierarchical entropy coding scheme, in which coarse-to-fine priors are exploited through a lightweight Geometry-Guided Convolution(GG-Conv) operator to enable spatially adaptive context modeling and rate-distortion optimization. Extensive experiments show that LG-HCC effectively alleviates structural preservation issues,achieving superior geometric integrity and rendering fidelity while reducing storage by up to 30.85x compared to the Scaffold-GS baseline on the Mip-NeRF360 dataset

comment: 10

♻ ☆ VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection

Huilin Deng, Hongchen Luo, Wei Zhai, Yang Cao, Yu Kang

Zero-shot anomaly detection (ZSAD) recognizes and localizes anomalies in previously unseen objects by establishing feature mapping between textual prompts and inspection images, demonstrating excellent research value in flexible industrial manufacturing. However, existing ZSAD methods are limited by closed-world settings, struggling to unseen defects with predefined prompts. Recently, adapting Multimodal Large Language Models (MLLMs) for Industrial Anomaly Detection (IAD) presents a viable solution. Unlike fixed-prompt methods, MLLMs exhibit a generative paradigm with open-ended text interpretation, enabling more adaptive anomaly analysis. However, this adaption faces inherent challenges as anomalies often manifest in fine-grained regions and exhibit minimal visual discrepancies from normal samples. To address these challenges, we propose a novel framework VMAD (Visual-enhanced MLLM Anomaly Detection) that enhances MLLM with visual-based IAD knowledge and fine-grained perception, simultaneously providing precise detection and comprehensive analysis of anomalies. Specifically, we design a Defect-Sensitive Structure Learning scheme that transfers patch-similarities cues from visual branch to our MLLM for improved anomaly discrimination. Besides, we introduce a novel visual projector, Locality-enhanced Token Compression, which mines multi-level features in local contexts to enhance fine-grained detection. Furthermore, we introduce the Real Industrial Anomaly Detection (RIAD), a comprehensive IAD dataset with detailed anomaly descriptions and analyses, offering a valuable resource for MLLM-based IAD development. Extensive experiments on zero-shot benchmarks, including MVTec-AD, Visa, WFDD, and RIAD datasets, demonstrate our superior performance over state-of-the-art methods. The code and dataset will be available soon.

♻ ☆ Unregistered Spectral Image Fusion: Unmixing, Adversarial Learning, and Recoverability

Jiahui Song, Sagar Shrestha, Xiao Fu

This paper addresses the fusion of a pair of spatially unregistered hyperspectral image (HSI) and multispectral image (MSI) covering roughly overlapping regions. HSIs offer high spectral but low spatial resolution, while MSIs provide the opposite. The goal is to integrate their complementary information to enhance both HSI spatial resolution and MSI spectral resolution. While hyperspectral-multispectral fusion (HMF) has been widely studied, the unregistered setting remains challenging. Many existing methods focus solely on MSI super-resolution, leaving HSI unchanged. Supervised deep learning approaches were proposed for HSI super-resolution, but rely on accurate training data, which is often unavailable. Moreover, theoretical analyses largely address the co-registered case, leaving unregistered HMF poorly understood. In this work, an unsupervised framework is proposed to simultaneously super-resolve both MSI and HSI. The method integrates coupled spectral unmixing for MSI super-resolution with latent-space adversarial learning for HSI super-resolution. Theoretical guarantees on the recoverability of the super-resolution MSI and HSI are established under reasonable generative models -- providing, to our best knowledge, the first such insights for unregistered HMF. The approach is validated on semi-real and real HSI-MSI pairs across diverse conditions.

♻ ☆ Spatial Reasoning is Not a Free Lunch: A Controlled Study on LLaVA ICLR 2026

Nahid Alam, Leema Krishna Murali, Siddhant Bharadwaj, Patrick Liu, Timothy Chung, Drishti Sharma, Akshata A., Kranthi Kiran, Wesley Tam, Bala Krishna S Vegesna

Vision-language models (VLMs) have advanced rapidly, yet they still struggle with basic spatial reasoning. Despite strong performance on general benchmarks, modern VLMs remain brittle at understanding 2D spatial relationships such as relative position, layout, and counting. We argue that this failure is not merely a data problem, but is closely tied to dominant design choices in current VLM pipelines: reliance on CLIP-style image encoders and the flattening of images into 1D token sequences with 1D positional encoding. We present a controlled diagnostic study within the LLaVA framework to isolate how these choices affect spatial grounding. We evaluate frontier models and LLaVA variants on a suite of spatial benchmarks, comparing CLIP-based encoders against alternatives trained with denser or generative objectives, as well as variants augmented with 2D positional encoding. Our results show consistent spatial performance gaps across models, and indicate that encoder objectives and positional structure shape spatial behavior, but do not fully resolve it.

comment: Accepted as a poster at ICLR 2026 workshop ICBINB, typo fixed

♻ ☆ TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation

Qingwen Zhang, Chenhan Jiang, Xiaomeng Zhu, Yunqi Miao, Yushan Zhang, Olov Andersson, Patric Jensfelt

Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the potential to provide more stable guidance by incorporating motion cues from past frames, yet naive extensions of two-frame objectives are ineffective because point correspondences vary abruptly across frames, producing inconsistent signals. In the paper, we present TeFlow, enabling multi-frame supervision for feed-forward models by mining temporally consistent supervision. TeFlow introduces a temporal ensembling strategy that forms reliable supervisory signals by aggregating the most temporally consistent motion cues from a candidate pool built across multiple frames. Extensive evaluations demonstrate that TeFlow establishes a new state-of-the-art for self-supervised feed-forward methods, achieving performance gains of up to 33\% on the challenging Argoverse 2 and nuScenes datasets. Our method performs on par with leading optimization-based methods, yet speeds up 150 times. The code is open-sourced at https://github.com/Kin-Zhang/TeFlow along with trained model weights.

comment: CVPR 2026; 16 pages, 8 figures

♻ ☆ Object Affordance Recognition and Grounding via Multi-scale Cross-modal Representation Learning

Xinhang Wan, Dongqiang Gou, Xinwang Liu, En Zhu, Xuming He

A core problem of Embodied AI is to learn object manipulation from observation, as humans do. To achieve this, it is important to localize 3D object affordance areas through observation such as images (3D affordance grounding) and understand their functionalities (affordance classification). Previous attempts usually tackle these two tasks separately, leading to inconsistent predictions due to lacking proper modeling of their dependency. In addition, these methods typically only ground the incomplete affordance areas depicted in images, failing to predict the full potential affordance areas, and operate at a fixed scale, resulting in difficulty in coping with affordances significantly varying in scale with respect to the whole object. To address these issues, we propose a novel approach that learns an affordance-aware 3D representation and employs a stage-wise inference strategy leveraging the dependency between grounding and classification tasks. Specifically, we first develop a cross-modal 3D representation through efficient fusion and multi-scale geometric feature propagation, enabling inference of full potential affordance areas at a suitable regional scale. Moreover, we adopt a simple two-stage prediction mechanism, effectively coupling grounding and classification for better affordance understanding. Experiments demonstrate the effectiveness of our method, showing improved performance in both affordance grounding and classification.

♻ ☆ RefTon: Reference person shot assist virtual Try-on

Liuzhuozheng Li, Yue Gong, Shanyuan Liu, Bo Cheng, Yuhang Ma, Leibucha Wu, Dengyang Jiang, Zanyi Wang, Dawei Leng, Yuhui Yin

We introduce RefTon, a flux-based person-to-person virtual try-on framework that enhances garment realism through unpaired visual references. Unlike conventional approaches that rely on complex auxiliary inputs such as body parsing and warped mask or require finely designed extract branches to process various input conditions, RefTon streamlines the process by directly generating try-on results from a source image and a target garment, without the need for structural guidance or auxiliary components to handle diverse inputs. Moreover, inspired by human clothing selection behavior, RefTon leverages additional reference images (the target garment worn on different individuals) to provide powerful guidance for refining texture alignment and maintaining the garment details. To enable this capability, we built a dataset containing unpaired reference images for training. Extensive experiments on public benchmarks demonstrate that RefTon achieves competitive or superior performance compared to state-of-the-art methods, while maintaining a simple and efficient person-to-person design.

comment: Accepted by CVPR 2026

♻ ☆ Beyond the Ground Truth: Enhanced Supervision for Image Restoration

Donghun Ryou, Inju Ha, Sanghyeok Chu, Bohyung Han

Deep learning-based image restoration has achieved significant success. However, when addressing real-world degradations, model performance is limited by the quality of groundtruth images in datasets due to practical constraints in data acquisition. To address this limitation, we propose a novel framework that enhances existing ground truth images to provide higher-quality supervision for real-world restoration. Our framework generates perceptually enhanced ground truth images using super-resolution by incorporating adaptive frequency masks, which are learned by a conditional frequency mask generator. These masks guide the optimal fusion of frequency components from the original ground truth and its super-resolved variants, yielding enhanced ground truth images. This frequency-domain mixup preserves the semantic consistency of the original content while selectively enriching perceptual details, preventing hallucinated artifacts that could compromise fidelity. The enhanced ground truth images are used to train a lightweight output refinement network that can be seamlessly integrated with existing restoration models. Extensive experiments demonstrate that our approach improves the quality of restored images. We further validate the effectiveness of both supervision enhancement and output refinement through user studies.

comment: Project page: https://hij1112.github.io/beyond-the-ground-truth/ Accepted to CVPR 2026

♻ ☆ Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising

Yiwen Shan, Haiyu Zhao, Peng Hu, Xi Peng, Yuanbiao Gou

Self-supervised real-world image denoising remains a fundamental challenge, arising from the antagonistic trade-off between decorrelating spatially structured noise and preserving high-frequency details. Existing blind-spot network (BSN) methods rely on pixel-shuffle downsampling (PD) to decorrelate noise, but aggressive downsampling fragments fine structures, while milder downsampling fails to remove correlated noise. To address this, we introduce Next-Scale Prediction (NSP), a novel self-supervised paradigm that decouples noise decorrelation from detail preservation. NSP constructs cross-scale training pairs, where BSN takes low-resolution, fully decorrelated sub-images as input to predict high-resolution targets that retain fine details. As a by-product, NSP naturally supports super-resolution of noisy images without retraining or modification. Extensive experiments demonstrate that NSP achieves state-of-the-art self-supervised denoising performance on real-world benchmarks, significantly alleviating the long-standing conflict between noise decorrelation and detail preservation. The code is available at https://github.com/XLearning-SCU/2026-CVPR-NSP.

♻ ☆ Pulp Motion: Framing-aware multimodal camera and human motion generation

Robin Courant, Xi Wang, David Loiseaux, Marc Christie, Vicky Kalogeiton

Treating human motion and camera trajectory generation separately overlooks a core principle of cinematography: the tight interplay between actor performance and camera work in the screen space. In this paper, we are the first to cast this task as a text-conditioned joint generation, aiming to maintain consistent on-screen framing while producing two heterogeneous, yet intrinsically linked, modalities: human motion and camera trajectories. We propose a simple, model-agnostic framework that enforces multimodal coherence via an auxiliary modality: the on-screen framing induced by projecting human joints onto the camera. This on-screen framing provides a natural and effective bridge between modalities, promoting consistency and leading to more precise joint distribution. We first design a joint autoencoder that learns a shared latent space, together with a lightweight linear transform from the human and camera latents to a framing latent. We then introduce auxiliary sampling, which exploits this linear transform to steer generation toward a coherent framing modality. To support this task, we also introduce the PulpMotion dataset, a human-motion and camera-trajectory dataset with rich captions, and high-quality human motions. Extensive experiments across DiT- and MAR-based architectures show the generality and effectiveness of our method in generating on-frame coherent human-camera motions, while also achieving gains on textual alignment for both modalities. Our qualitative results yield more cinematographically meaningful framings setting the new state of the art for this task. Code, models and data are available in our \href{https://www.lix.polytechnique.fr/vista/projects/2025_pulpmotion_courant/}{project page}.

comment: Project page: https://www.lix.polytechnique.fr/vista/projects/2025_pulpmotion_courant/

♻ ☆ EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval

Yuhan Chen, Pengwen Dai, Chuan Wang, Dayan Wu, Xiaochun Cao

Text-video retrieval tasks have seen significant improvements due to the recent development of large-scale vision-language pre-trained models. Traditional methods primarily focus on video representations or cross-modal alignment, while recent works shift toward enriching text expressiveness to better match the rich semantics in videos. However, these methods use only interactions between text and frames/video, and ignore rich interactions among the internal frames within a video, so the final expanded text cannot capture frame contextual information, leading to disparities between text and video. In response, we introduce Energy-Aware Fine-Grained Relationship Learning Network (EagleNet) to generate accurate and context-aware enriched text embeddings. Specifically, the proposed Fine-Grained Relationship Learning mechanism (FRL) first constructs a text-frame graph by the generated text candidates and frames, then learns relationships among texts and frames, which are finally used to aggregate text candidates into an enriched text embedding that incorporates frame contextual information. To further improve fine-grained relationship learning in FRL, we design Energy-Aware Matching (EAM) to model the energy of text-frame interactions and thus accurately capture the distribution of real text-video pairs. Moreover, for more effective cross-modal alignment and stable training, we replace the conventional softmax-based contrastive loss with the sigmoid loss. Extensive experiments have demonstrated the superiority of EagleNet across MSRVTT, DiDeMo, MSVD, and VATEX. Codes are available at https://github.com/draym28/EagleNet.

comment: Accepted at CVPR 2026

♻ ☆ Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens

Ciem Cornelissen, Sam Leroux, Pieter Simoens

Self-supervised learning has emerged as a powerful paradigm for learning visual representations without manual annotations, yet most methods still operate on a single modality and therefore miss the complementary structure available from heterogeneous sensors. We present Le MuMo JEPA, a self-supervised framework that learns unified representations from RGB images and aligned companion modalities. In our driving experiments, the second modality is camera-aligned LiDAR depth; we also evaluate RGB-thermal training and transfer on the Teledyne FLIR ADAS benchmark. Our approach extends LeJEPA to the multi-modal setting by learning fusion tokens that act as a latent bottleneck between modality-specific patch stems inside a shared transformer. Our default model employs a pruned fusion strategy: after an initial cross-modal attention layer, modality-specific tokens are dropped, forcing cross-modal information into the shared fusion-token grid as an efficient latent bottleneck before Sketched Isotropic Gaussian Regularization (SIGReg) is applied to the joint multimodal CLS embedding. On Waymo, Le MuMo JEPA gives the strongest performance-efficiency trade-off on downstream patch probes among the from-scratch multimodal baselines, improving CenterNet detection and dense depth while remaining competitive on segmentation. Under from-scratch training on nuScenes, Le MuMo JEPA remains the strongest model, and it also gives the best FLIR results, especially after Waymo-initialized fine-tuning. It also retains the best overall accuracy-efficiency balance in our study at substantially lower compute, memory, and estimated training time.

comment: 14 pages, 4 figures, supplementary material. Accepted at the CVPR 2026 Workshop on Unified Robotic Vision with Cross-Modal Sensing and Alignment (URVIS)

♻ ☆ CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models

Kesheng Chen, Yamin Hu, Qi Zhou, Zhenqian Zhu, Wenjian Luo

Vision-language models (VLMs) achieve strong performance on many benchmarks, yet a basic reliability question remains underexplored: when visual evidence conflicts with commonsense, do models follow what is shown or what commonsense suggests? A characteristic failure in this setting is that the model overrides visual evidence and outputs the commonsense alternative. We term this phenomenon \textbf{commonsense-driven hallucination} (CDH). To evaluate it, we introduce \textbf{CDH-Bench}, a benchmark designed to create explicit \textbf{visual evidence--commonsense conflicts}. CDH-Bench covers three dimensions: \textit{counting anomalies}, \textit{relational anomalies}, and \textit{attribute anomalies}. We evaluate frontier VLMs under \textit{binary Question Answering (QA)} and \textit{multiple-choice QA}, and report metrics including \textit{Counterfactual Accuracy} (CF-Acc), \textit{Commonsense Accuracy} (CS-Acc), \textit{Counterfactual Accuracy Drop} (CFAD), \textit{Commonsense Collapse Rate} (CCR), and \textit{Relative Prior Dependency} (RPD). Results show that even strong models remain vulnerable to prior-driven normalization under visual evidence--commonsense conflict. CDH-Bench provides a controlled diagnostic of visual fidelity under visual evidence--commonsense conflict.

♻ ☆ TempoControl: Temporal Attention Guidance for Text-to-Video Models

Shira Schiber, Ofir Lindenbaum, Idan Schwartz

Recent advances in generative video models have enabled the creation of high-quality videos based on natural language prompts. However, these models frequently lack fine-grained temporal control, meaning they do not allow users to specify when particular visual elements should appear within a generated sequence. In this work, we introduce TempoControl, a method that allows for temporal alignment of visual concepts during inference, without requiring retraining or additional supervision. TempoControl utilizes cross-attention maps, a key component of text-to-video diffusion models, to guide the timing of concepts through a novel optimization approach. Our method steers attention using three complementary principles: aligning its temporal pattern with a control signal (correlation), adjusting its strength where visibility is required (magnitude), and preserving semantic consistency (entropy). TempoControl provides precise temporal control while maintaining high video quality and diversity. We demonstrate its effectiveness across various applications, including temporal reordering of single and multiple objects, action timing, and audio-aligned video generation. Project page: https://shira-schiber.github.io/TempoControl/.

comment: Accepted CVPR'26

♻ ☆ D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models

Wenlun Zhang, Yunshan Zhong, Zihao Ding, Xinyu Li, Kentaro Yoshioka

Data-Free Quantization (DFQ) offers a practical solution for model compression without requiring access to real data, making it particularly attractive in privacy-sensitive scenarios. While DFQ has shown promise for unimodal models, its extension to Vision-Language Models such as Contrastive Language-Image Pre-training (CLIP) models remains underexplored. In this work, we reveal that directly applying existing DFQ techniques to CLIP results in substantial performance degradation due to two key limitations: insufficient semantic content and low intra-image diversity in synthesized samples. To tackle these challenges, we propose D4C, the first DFQ framework tailored for CLIP. D4C synthesizes semantically rich and structurally diverse pseudo images through three key components: 1) Prompt-Guided Semantic Injection aligns generated images with real-world semantics using text prompts; 2) Structural Contrastive Generation reproduces compositional structures of natural images by leveraging foreground-background contrastive synthesis; and 3) Perturbation-Aware Enhancement applies controlled perturbations to improve sample diversity and robustness. These components jointly empower D4C to synthesize images that are both semantically informative and structurally diverse, effectively bridging the performance gap of DFQ on CLIP. Extensive experiments validate the effectiveness of D4C, showing significant performance improvements on various bit-widths and models.

comment: Accepted to CVPRF 2026

♻ ☆ Variance-Based Pruning for Accelerating and Compressing Trained Networks

Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache

Increasingly expensive training of ever larger models such as Vision Transfomers motivate reusing the vast library of already trained state-of-the-art networks. However, their latency, high computational costs and memory demands pose significant challenges for deployment, especially on resource-constrained hardware. While structured pruning methods can reduce these factors, they often require costly retraining, sometimes for up to hundreds of epochs, or even training from scratch to recover the lost accuracy resulting from the structural modifications. Maintaining the provided performance of trained models after structured pruning and thereby avoiding extensive retraining remains a challenge. To solve this, we introduce Variance-Based Pruning, a simple and structured one-shot pruning technique for efficiently compressing networks, with minimal finetuning. Our approach first gathers activation statistics, which are used to select neurons for pruning. Simultaneously the mean activations are integrated back into the model to preserve a high degree of performance. On ImageNet-1k recognition tasks, we demonstrate that directly after pruning DeiT-Base retains over 70% of its original performance and requires only 10 epochs of fine-tuning to regain 99% of the original accuracy while simultaneously reducing MACs by 35% and model size by 36%, thus speeding up the model by 1.44x. The code is available at: https://github.com/boschresearch/variance-based-pruning

comment: Accepted as Oral at ICCV'25 (IEEE/CVF International Conference on Computer Vision)

♻ ☆ Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement

Ange-Clément Akazan, Abdoulaye Koroko, Verlon Roel Mbingui, Choukouriyah Arinloye, Hassan Fifen, Rose Bandolo

The success of deep learning in computer vision has been driven by models of increasing scale, from deep Convolutional Neural Networks (CNN) to large Vision Transformers (ViT). While effective, these architectures are parameter-intensive and demand significant computational resources, limiting deployment in resource-constrained environments. Inspired by Tiny Recursive Models (TRM), which show that small recursive networks can solve complex reasoning tasks through iterative state refinement, we introduce the \textbf{Vision Tiny Recursion Model (ViTRM)}: a parameter-efficient architecture that replaces the $L$-layer ViT encoder with a single tiny $k$-layer block ($k{=}3$) applied recursively $N$ times. Despite using up to $6 \times $ and $84 \times$ fewer parameters than CNN based models and ViT respectively, ViTRM maintains competitive performance on CIFAR-10 and CIFAR-100. This demonstrates that recursive computation is a viable, parameter-efficient alternative to architectural depth in vision.

♻ ☆ CHEEM: Continual Learning by Reuse, New, Adapt and Skip -- A Hierarchical Exploration-Exploitation Approach

Chinmay Savadikar, Michelle Dai, Tianfu Wu

To effectively manage the complexities of real-world dynamic environments, continual learning must incrementally acquire, update, and accumulate knowledge from a stream of tasks of different nature without suffering from catastrophic forgetting of prior knowledge. While this capability is innate to human cognition, it remains a significant challenge for modern deep learning systems. At the heart of this challenge lies the stability-plasticity dilemma: the need to balance leveraging prior knowledge, integrating novel information, and allocating model capacity adaptively based on task complexity and synergy. In this paper, we propose a novel exemplar-free class-incremental continual learning (ExfCCL) framework that addresses these issues through a Hierarchical Exploration-Exploitation (HEE) approach. The core of our method is a HEE-guided efficient neural architecture search (HEE-NAS) that enables a learning-to-adapt backbone via four primitive operations - reuse, new, adapt, and skip - thereby serving as an internal memory that dynamically updates selected components across streaming tasks. To address the task ID inference problem in ExfCCL, we exploit an external memory of task centroids proposed in the prior art. We term our method CHEEM (Continual Hierarchical-Exploration-Exploitation Memory). CHEEM is evaluated on the challenging MTIL and VDD benchmarks using both Tiny and Base Vision Transformers and a proposed holistic Figure-of-Merit (FoM) metric. It significantly outperforms state-of-the-art prompting-based continual learning methods, closely approaching full fine-tuning upper bounds. Furthermore, it learns adaptive model structures tailored to individual tasks in a semantically meaningful way. Our code is available at https://github.com/savadikarc/cheem .

comment: CVPR 2026

♻ ☆ OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport

Xiwen Chen, Wenhui Zhu, Gen Li, Xuanzhao Dong, Yujian Xiong, Hao Wang, Peijie Qiu, Qingquan Song, Zhipeng Wang, Shao Tang, Yalin Wang, Abolfazl Razi

Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual token pruning to accelerate inference, while existing pruning methods overlook the underlying distributional structure of visual representations. We propose OTPrune, a training-free framework that formulates pruning as distribution alignment via optimal transport (OT). By minimizing the 2-Wasserstein distance between the full and pruned token distributions, OTPrune preserves both local diversity and global representativeness while reducing inference cost. Moreover, we derive a tractable submodular objective that enables efficient optimization, and theoretically prove its monotonicity and submodularity, providing a principled foundation for stable and efficient pruning. We further provide a comprehensive analysis that explains how distributional alignment contributes to stable and semantically faithful pruning. Comprehensive experiments on wider benchmarks demonstrate that OTPrune achieves superior performance-efficiency tradeoffs compared to state-of-the-art methods. The code is available at https://github.com/xiwenc1/OTPrune.

comment: Accepted by CVPR2026

♻ ☆ CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting ICLR 2026

Zhigang Cheng, Mingchao Sun, Yu Liu, Zengye Ge, Luyang Tang, Mu Xu, Yangyan Li, Peng Pan

Level of Detail (LoD) is a fundamental technique in real-time computer graphics for managing the rendering costs of complex scenes while preserving visual fidelity. Traditionally, LoD is implemented using discrete levels (DLoD), where multiple, distinct versions of a model are swapped out at different distances. This long-standing paradigm, however, suffers from two major drawbacks: it requires significant storage for multiple model copies and causes jarring visual ``popping" artifacts during transitions, degrading the user experience. We argue that the explicit, primitive-based nature of the emerging 3D Gaussian Splatting (3DGS) technique enables a more ideal paradigm: Continuous LoD (CLoD). A CLoD approach facilitates smooth, seamless quality scaling within a single, unified model, thereby circumventing the core problems of DLOD. To this end, we introduce CLoD-GS, a framework that integrates a continuous LoD mechanism directly into a 3DGS representation. Our method introduces a learnable, distance-dependent decay parameter for each Gaussian primitive, which dynamically adjusts its opacity based on viewpoint proximity. This allows for the progressive and smooth filtering of less significant primitives, effectively creating a continuous spectrum of detail within one model. To train this model to be robust across all distances, we introduce a virtual distance scaling mechanism and a novel coarse-to-fine training strategy with rendered point count regularization. Our approach not only eliminates the storage overhead and visual artifacts of discrete methods but also reduces the primitive count and memory footprint of the final model. Extensive experiments demonstrate that CLoD-GS achieves smooth, quality-scalable rendering from a single model, delivering high-fidelity results across a wide range of performance targets.

comment: Accepted by ICLR 2026 poster

♻ ☆ SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark

Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Yang Song, Jiaojiao Jiang

Diffusion-based watermarking methods embed verifiable marks by manipulating the initial noise or the reverse diffusion trajectory. However, these methods share a critical assumption: verification can succeed only if the diffusion trajectory can be faithfully reconstructed. This reliance on trajectory recovery constitutes a fundamental and exploitable vulnerability. We propose $\underline{\mathbf{S}}$tochastic $\underline{\mathbf{Hi}}$dden-Trajectory De$\underline{\mathbf{f}}$lec$\underline{\mathbf{t}}$ion ($\mathbf{SHIFT}$), a training-free attack that exploits this common weakness across diverse watermarking paradigms. SHIFT leverages stochastic diffusion resampling to deflect the generative trajectory in latent space, making the reconstructed image statistically decoupled from the original watermark-embedded trajectory while preserving strong visual quality and semantic consistency. Extensive experiments on nine representative watermarking methods spanning noise-space, frequency-domain, and optimization-based paradigms show that SHIFT achieves 95%--100% attack success rates with nearly no loss in semantic quality, without requiring any watermark-specific knowledge or model retraining.

♻ ☆ Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology

Shravan Venkatraman, Muthu Subash Kavitha, Joe Dhanith P R, V Manikandarajan, Jia Wu

Histopathology image segmentation is essential for delineating tissue structures in skin cancer diagnostics, but modeling spatial context and inter-tissue relationships remains a challenge, especially in regions with overlapping or morphologically similar tissues. Current convolutional neural network (CNN)-based approaches operate primarily on visual texture, often treating tissues as independent regions and failing to encode biological context. To this end, we introduce Neural Tissue Relation Modeling (NTRM), a novel segmentation framework that augments CNNs with a tissue-level graph neural network to model spatial and functional relationships across tissue types. NTRM constructs a graph over predicted regions, propagates contextual information via message passing, and refines segmentation through spatial projection. Unlike prior methods, NTRM explicitly encodes inter-tissue dependencies, enabling structurally coherent predictions in boundary-dense zones. On the benchmark Histopathology Non-Melanoma Skin Cancer Segmentation Dataset, NTRM outperforms state-of-the-art methods, achieving a robust Dice similarity coefficient that is 4.9\% to 31.25\% higher than the best-performing models among the evaluated approaches. Our experiments indicate that relational modeling offers a principled path toward more context-aware and interpretable histological segmentation, compared to local receptive-field architectures that lack tissue-level structural awareness. Our code is available at https://github.com/shravan-18/NTRM.

comment: CVPR 2026 Workshops

♻ ☆ The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Weichen Fan, Haiwen Diao, Quan Wang, Dahua Lin, Ziwei Liu

Deep representations across modalities are inherently intertwined. In this paper, we systematically analyze the spectral characteristics of various semantic and pixel encoders. Interestingly, our study uncovers a highly inspiring and rarely explored correspondence between an encoder's feature spectrum and its functional role: semantic encoders primarily capture low-frequency components that encode abstract meaning, whereas pixel encoders additionally retain high-frequency information that conveys fine-grained detail. This heuristic finding offers a unifying perspective that ties encoder behavior to its underlying spectral structure. We define it as the Prism Hypothesis, where each data modality can be viewed as a projection of the natural world onto a shared feature spectrum, just like the prism. Building on this insight, we propose Unified Autoencoding (UAE), a model that harmonizes semantic structure and pixel details via an innovative frequency-band modulator, enabling their seamless coexistence. Extensive experiments demonstrate that UAE effectively unifies semantic abstraction and pixel-level fidelity within a single latent space, achieving state-of-the-art performance. Moreover, we show that UAE can be directly applied to pixel-space modeling, significantly improving both FID and IS over the vanilla JIT baseline. Our code is avaliable at: https://github.com/WeichenFan/UAE.

comment: Code link: https://github.com/WeichenFan/UAE

♻ ☆ SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy

Shi Li, Vinkle Srivastav, Nicolas Chanel, Saurav Sharma, Nabani Banik, Lorenzo Arboit, Kun Yuan, Pietro Mascagni, Nicolas Padoy

Surgical procedures are inherently complex and risky, requiring extensive expertise and constant focus to well navigate evolving intraoperative scenes. Computer-assisted systems such as surgical visual question answering (VQA) offer promises for education and intraoperative support. Current surgical VQA research largely focuses on static frame analysis, overlooking rich temporal semantics. Surgical video question answering is further challenged by low visual contrast, its highly knowledge-driven nature, diverse analytical needs spanning scattered temporal windows, and the hierarchy from basic perception to high-level intraoperative assessment. To address these challenges, we propose SurgTEMP, a multimodal LLM framework featuring (i) a query-guided token selection module that builds hierarchical visual memory (spatial and temporal memory banks) and (ii) a Surgical Competency Progression (SCP) training scheme. Together, these components enable effective modeling of variable-length surgical videos while preserving procedure-relevant cues and temporal coherence, and better support diverse downstream assessment tasks. To support model development, we introduce CholeVidQA-32K, a surgical video question answering dataset comprising 32K open-ended QA pairs and 3,855 video segments (approximately 128 h total) from laparoscopic cholecystectomy. The dataset is organized into a three-level hierarchy -- Perception, Assessment, and Reasoning -- spanning 11 tasks from instrument/action/anatomy perception to Critical View of Safety (CVS), intraoperative difficulty, skill proficiency, and adverse event assessment. In comprehensive evaluations against state-of-the-art open-source multimodal and video LLMs (fine-tuned and zero-shot), SurgTEMP achieves substantial performance improvements, advancing the state of video-based surgical VQA.

comment: 29 pages, 14 figures, 9 tables

♻ ☆ Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training

Xiangyang Luo, Qingyu Li, Yuming Li, Guanbo Huang, Yongjie Zhu, Wenyu Qin, Meng Wang, Pengfei Wan, Shao-Lun Huang

Recent advances in video generation models have achieved impressive results. However, these models heavily rely on the use of high-quality data that combines both high visual quality and high motion quality. In this paper, we identify a key challenge in video data curation: the Motion-Vision Quality Dilemma. We discovered that visual quality and motion intensity inherently exhibit a negative correlation, making it hard to obtain golden data that excels in both aspects. To address this challenge, we first examine the hierarchical learning dynamics of video diffusion models and conduct gradient-based analysis on quality-degraded samples. We discover that quality-imbalanced data can produce gradients similar to golden data at appropriate timesteps. Based on this, we introduce the novel concept of Timestep selection in Training Process. We propose Timestep-aware Quality Decoupling (TQD), which modifies the data sampling distribution to better match the model's learning process. For certain types of data, the sampling distribution is skewed toward higher timesteps for motion-rich data, while high visual quality data is more likely to be sampled during lower timesteps. Through extensive experiments, we demonstrate that TQD enables training exclusively on separated imbalanced data to achieve performance surpassing conventional training with better data, challenging the necessity of perfect data in video generation. Moreover, our method also boosts model performance when trained on high-quality data, showcasing its effectiveness across different data scenarios.

comment: Accepted to CVPR 2026

♻ ☆ Learning to Infer Parameterized Representations of Plants from 3D Scans

Samara Ghrer, Christophe Godin, Stefanie Wuhrer

Plants frequently contain numerous organs, organized in 3D branching systems defining the plant's architecture. Reconstructing the architecture of plants from unstructured observations is challenging because of self-occlusion and spatial proximity between organs, which are often thin structures. To achieve the challenging task, we propose an approach that allows to infer a parameterized representation of the plant's architecture from a given 3D scan of a plant. In addition to the plant's branching structure, this representation contains parametric information for each plant organ, and can therefore be used directly in a variety of tasks. In this data-driven approach, we train a recursive neural network with virtual plants generated using a procedural model. After training, the network allows to infer a parametric tree-like representation based on an input 3D point cloud. Our method is applicable to any plant that can be represented as binary axial tree. We quantitatively evaluate our approach on Chenopodium Album plants on reconstruction, segmentation and skeletonization, which are important problems in plant phenotyping. In addition to carrying out several tasks at once, our method achieves results on-par with strong baselines for each task. We apply our method, trained exclusively on synthetic data, to 3D scans and show that it generalizes well.

♻ ☆ HUMOF: Human Motion Forecasting in Interactive Social Scenes ICLR 2026

Caiyi Sun, Yujing Sun, Xiao Han, Zemin Yang, Jiawei Liu, Xinge Zhu, Siu Ming Yiu, Yuexin Ma

Complex scenes present significant challenges for predicting human behaviour due to the abundance of interaction information, such as human-human and humanenvironment interactions. These factors complicate the analysis and understanding of human behaviour, thereby increasing the uncertainty in forecasting human motions. Existing motion prediction methods thus struggle in these complex scenarios. In this paper, we propose an effective method for human motion forecasting in interactive scenes. To achieve a comprehensive representation of interactions, we design a hierarchical interaction feature representation so that high-level features capture the overall context of the interactions, while low-level features focus on fine-grained details. Besides, we propose a coarse-to-fine interaction reasoning module that leverages both spatial and frequency perspectives to efficiently utilize hierarchical features, thereby enhancing the accuracy of motion predictions. Our method achieves state-of-the-art performance across four public datasets. The source code will be available at https://github.com/scy639/HUMOF.

comment: Accepted by ICLR 2026

♻ ☆ EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?

Pierre Adorni, Minh-Tan Pham, Stéphane May, Sébastien Lefèvre

Recent advances in foundation models have shown great promise in domains such as natural language processing and computer vision, and similar efforts are now emerging in the Earth Observation community. These models aim to generalize across tasks with limited supervision, reducing the need for training separate models for each task. However, current strategies, which largely focus on scaling model size and dataset volume, require prohibitive computational and data resources, limiting accessibility to only a few large institutions. Moreover, this paradigm of ever-larger models stands in stark contrast with the principles of sustainable and environmentally responsible AI, as it leads to immense carbon footprints and resource inefficiency. In this work, we present a novel and efficient alternative: an Ensemble-of-Specialists framework for building Remote Sensing Foundation Models (RSFMs). Our method decomposes the training process into lightweight, task-specific ConvNeXtV2 specialists that can be frozen and reused. This modular approach offers strong advantages in efficiency, interpretability, and extensibility. Moreover, it naturally supports federated training, pruning, and continuous specialist integration, making it particularly well-suited for collaborative and resource-constrained settings. Our framework sets a new direction for building scalable and efficient RSFMs. All codes and pretrained models are available on the public repo at https://github.com/pierreadorni/EoS-FM .

♻ ☆ WAON: Large-Scale Japanese Image-Text Pair Dataset for Improving Model Performance on Japanese Cultural Tasks

Issa Sugiura, Shuhei Kurita, Yusuke Oda, Daisuke Kawahara, Yasuo Okabe, Naoaki Okazaki

Contrastive pre-training on large-scale image-text pair datasets has driven major advances in vision-language representation learning. Recent work shows that pretraining on global data followed by language or culture specific fine-tuning is effective for improving performance in target domains. With the availability of strong open-weight multilingual models such as SigLIP2, this paradigm has become increasingly practical. However, for Japanese, the scarcity of large-scale, high-quality image-text pair datasets tailored to Japanese language and cultural content remains a key limitation. To address this gap, we introduce WAON, the largest Japanese image-text pair dataset constructed from Japanese web content in Common Crawl, containing approximately 155 million examples. Our dataset construction pipeline employs filtering and deduplication to improve dataset quality. To improve the quality and reliability of evaluation on Japanese cultural tasks, we also construct WAON-Bench, a manually curated benchmark for Japanese cultural image classification comprising 374 classes, which addresses issues in the existing benchmark such as category imbalance and label-image mismatches. Our experiments demonstrate that fine-tuning on WAON improves model performance on Japanese cultural benchmarks more efficiently than existing datasets, achieving state-of-the-art results among publicly available models of comparable architecture. We release our dataset, model, and code.

comment: 14 pages, 7 figures

♻ ☆ Harnessing the Power of Local Representations for Few-Shot Classification

Shi Tang, Guiming Luo, Xinchen Ye, Zhiyi Xia

Generalizing to novel classes unseen during training is a key challenge of few-shot classification. Recent metric-based methods try to address this by local representations. However, they are unable to take full advantage of them due to (i) improper supervision for pretraining the feature extractor, and (ii) lack of adaptability in the metric for handling various possible compositions of local feature sets. In this work, we harness the power of local representations in improving novel-class generalization. For the feature extractor, we design a novel pretraining paradigm that learns randomly cropped patches by soft labels. It utilizes the class-level diversity of patches while diminishing the impact of their semantic misalignments to hard labels. To align network output with soft labels, we also propose a UniCon KL-Divergence that emphasizes the equal contribution of each base class in describing "non-base" patches. For the metric, we formulate measuring local feature sets as an entropy-regularized optimal transport problem to introduce the ability to handle sets consisting of homogeneous elements. Furthermore, we design a Modulate Module to endow the metric with the necessary adaptability. Our method achieves new state-of-the-art performance on three popular benchmarks. Moreover, it exceeds state-of-the-art transductive and cross-modal methods in the fine-grained scenario.

♻ ☆ A 3D Cross-modal Keypoint Descriptor for MR-US Matching and Registration

Daniil Morozov, Reuben Dorent, Nazim Haouchine

Intraoperative registration of real-time ultrasound (iUS) to preoperative Magnetic Resonance Imaging (MRI) remains an unsolved problem due to severe modality-specific differences in appearance, resolution, and field-of-view. To address this, we propose a novel 3D cross-modal keypoint descriptor for MRI-iUS matching and registration. Our approach employs a patient-specific matching-by-synthesis approach, generating synthetic iUS volumes from preoperative MRI. This enables supervised contrastive training to learn a shared descriptor space. A probabilistic keypoint detection strategy is then employed to identify anatomically salient and modality-consistent locations. During training, a curriculum-based triplet loss with dynamic hard negative mining is used to learn descriptors that are i) robust to iUS artifacts such as speckle noise and limited coverage, and ii) rotation-invariant. At inference, the method detects keypoints in MR and real iUS images and identifies sparse matches, which are then used to perform rigid registration. Our approach is evaluated using 3D MRI-iUS pairs from the ReMIND dataset. Experiments show that our approach outperforms state-of-the-art keypoint matching methods across 11 patients, with an average precision of 69.8%. For image registration, our method achieves a competitive mean Target Registration Error of 2.39 mm on the ReMIND2Reg benchmark. Compared to existing iUS-MR registration approaches, our framework is interpretable, requires no manual initialization, and shows robustness to iUS field-of-view variation. Code, data and model weights are available at https://github.com/morozovdd/CrossKEY.

comment: Accepted in IEEE Transactions on Medical Imaging

♻ ☆ Enhancing Floor Plan Recognition: A Hybrid Mix-Transformer and U-Net Approach for Precise Wall Segmentation

Dmitriy Parashchuk, Alexey Kaspshitskiy, Yuriy Karyakin

Automatic 3D reconstruction of indoor spaces from 2D floor plans necessitates high-precision semantic segmentation of structural elements, particularly walls. However, existing methods often struggle with detecting thin structures and maintaining geometric precision. To address this, we introduce MitUNet, a hybrid neural network designed to bridge the gap between global semantic context and fine-grained structural details. Our architecture combines a Mix-Transformer encoder with a U-Net decoder enhanced with spatial and channel attention blocks. Optimized with the Tversky loss function, this approach achieves a balance between precision and recall, ensuring accurate boundary recovery. Experiments on the CubiCasa5k dataset and the regional dataset demonstrate MitUNet's superiority in generating structurally correct masks with high boundary accuracy, outperforming standard models. This tool provides a robust foundation for automated 3D reconstruction pipelines. To ensure reproducibility and facilitate future research, the source code and the regional dataset are publicly available at https://github.com/aliasstudio/mitunet and https://doi.org/10.5281/zenodo.17871079, respectively.

comment: 11 pages, 5 figures, 3 tables

♻ ☆ Communicating about Space: Language-Mediated Spatial Integration Across Partial Views

Ankur Sikarwar, Debangan Mishra, Sudarshan Nikhil, Ponnurangam Kumaraguru, Aishwarya Agrawal

Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Language Models (MLLMs) can do the same, aligning distinct egocentric views through dialogue to form a coherent, allocentric mental model of a shared environment. To study this systematically, we introduce COSMIC, a benchmark for Collaborative Spatial Communication. In this setting, two static MLLM agents observe a 3D indoor environment from different viewpoints and exchange natural-language messages to solve spatial queries. COSMIC contains 899 diverse scenes and 1250 question-answer pairs spanning five tasks. We find a capability hierarchy, MLLMs are most reliable at identifying shared anchor objects across views, perform worse on relational reasoning, and largely fail at building globally consistent maps, performing near chance, even for frontier models. Moreover, we find thinking capability yields gains in anchor grounding, but is insufficient for higher-level spatial communication. To contextualize model behavior, we collect 250 human-human dialogues. Humans achieve 95% aggregate accuracy, while the best model, Gemini-3-Pro-Thinking, reaches 72%, leaving substantial room for improvement. Moreover, human conversations grow more precise as partners align on a shared spatial understanding, whereas MLLMs keep exploring without converging, suggesting limited capacity to form and sustain a robust shared mental model throughout the dialogue. Our code and data is available at https://github.com/ankursikarwar/Cosmic.

♻ ☆ EvalBlocks: A Modular Pipeline for Rapidly Evaluating Foundation Models in Medical Imaging

Jan Tagscherer, Sarah de Boer, Lena Philipp, Fennie van der Graaf, Dré Peeters, Joeran Bosma, Lars Leijten, Bogdan Obreja, Ewoud Smit, Alessa Hering

Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular, plug-and-play framework for efficient evaluation of foundation models during development. Built on Snakemake, EvalBlocks supports seamless integration of new datasets, foundation models, aggregation methods, and evaluation strategies. All experiments and results are tracked centrally and are reproducible with a single command, while efficient caching and parallel execution enable scalable use on shared compute infrastructure. Demonstrated on five state-of-the-art foundation models and three medical imaging classification tasks, EvalBlocks streamlines model evaluation, enabling researchers to iterate faster and focus on model innovation rather than evaluation logistics. The framework is released as open source software at https://github.com/DIAGNijmegen/eval-blocks.

comment: Accepted and published in BVM 2026 proceedings (Springer)

♻ ☆ Toward Physically Consistent Driving Video World Models under Challenging Trajectories

Jiawei Zhou, Zhenxin Zhu, Lingyi Du, Linye Lyu, Lijun Zhou, Zhanqian Wu, Hongcheng Luo, Zhuotao Tian, Bing Wang, Guang Chen, Hangjun Ye, Haiyang Sun, Yu Li

Video generation models have shown strong potential as world models for autonomous driving simulation. However, existing approaches are primarily trained on real-world driving datasets, which mostly contain natural and safe driving scenarios. As a result, current models often fail when conditioned on challenging or counterfactual trajectories-such as imperfect trajectories generated by simulators or planning systems-producing videos with severe physical inconsistencies and artifacts. To address this limitation, we propose PhyGenesis, a world model designed to generate driving videos with high visual fidelity and strong physical consistency. Our framework consists of two key components: (1) a physical condition generator that transforms potentially invalid trajectory inputs into physically plausible conditions, and (2) a physics-enhanced video generator that produces high-fidelity multi-view driving videos under these conditions. To effectively train these components, we construct a large-scale, physics-rich heterogeneous dataset. Specifically, in addition to real-world driving videos, we generate diverse challenging driving scenarios using the CARLA simulator, from which we derive supervision signals that guide the model to learn physically grounded dynamics under extreme conditions. This challenging-trajectory learning strategy enables trajectory correction and promotes physically consistent video generation. Extensive experiments demonstrate that PhyGenesis consistently outperforms state-of-the-art methods, especially on challenging trajectories. Our project page is available at: https://wm-research.github.io/PhyGenesis/.

♻ ☆ How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions

Na Min An, Eunki Kim, Wan Ju Kang, Sangryul Kim, James Thorne, Hyunjung Shim

For individuals with blindness or low vision (BLV), navigating complex environments can pose serious risks. Large Vision-Language Models (LVLMs) show promise for generating scene descriptions, but their effectiveness for BLV users remains underexplored. To address this gap, we conducted a user study with eight BLV participants to systematically evaluate preferences for six types of LVLM descriptions. While they helped to reduce fear and improve actionability, user ratings showed wide variation in sufficiency and conciseness. Furthermore, GPT-4o--despite its strong potential to refine descriptions--was not consistently preferred by participants. We use the insights obtained from the user study to build training data for building our new automatic evaluation metric that can capture BLV preferences effectively. Our findings underscore the urgent need for BLV-centered evaluation metrics and human-in-the-loop feedback to advance LVLM description quality for accessibility.

comment: This paper has been superseded by version 2 of arXiv:2510.00766

♻ ☆ Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning

Adrian Garcia-Castañeda, Jon Irureta, Jon Imaz, Aizea Lojo

Class Incremental Learning (CIL) poses a fundamental challenge: maintaining a balance between the plasticity required to learn new tasks and the stability needed to prevent catastrophic forgetting. While expansion-based methods effectively mitigate forgetting by adding task-specific parameters, they suffer from uncontrolled architectural growth and memory overhead. In this paper, we propose a novel dynamic scaling framework that adaptively manages model capacity through a cyclic "GRow, Assess, ComprEss" (GRACE) strategy. Crucially, we supplement backbone expansion with a novel saturation assessment phase that evaluates the utilization of the model's capacity. This assessment allows the framework to make informed decisions to either expand the architecture or compress the backbones into a streamlined representation, preventing parameter explosion. Experimental results demonstrate that our approach achieves state-of-the-art performance across multiple CIL benchmarks, while reducing memory footprint by up to a 73% compared to purely expansionist models.

♻ ☆ Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?

Eunki Kim, Na Min An, Wan Ju Kang, Sangryul Kim, James Thorne, Hyunjung Shim

Large Vision-Language Models (LVLMs) demonstrate a promising direction for assisting individuals with blindness or low-vision (BLV). Yet, measuring their true utility in real-world scenarios is challenging because evaluating whether their descriptions are BLV-informative requires a fundamentally different approach from assessing standard scene descriptions. While the "VLM-as-a-metric" or "LVLM-as-a-judge" paradigm has emerged, existing evaluators still fall short of capturing the unique requirements of BLV-centric evaluation, lacking at least one of the following key properties: (1) High correlation with human judgments, (2) Long instruction understanding, (3) Score generation efficiency, and (4) Multi-dimensional assessment. To this end, we propose a unified framework to bridge the gap between automated evaluation and actual BLV needs. First, we conduct an in-depth user study with BLV participants to understand and quantify their navigational preferences, curating VL-GUIDEDATA, a large-scale BLV user-simulated preference dataset containing image-request-response-score pairs. We then leverage the dataset to develop an accessibility-aware evaluator, VL-GUIDE-S, which outperforms existing (L)VLM judges in both human alignment and inference efficiency. Notably, its effectiveness extends beyond a single domain, demonstrating strong performance across multiple fine-grained, BLV-critical dimensions. We hope our work lays as a foundation for automatic AI judges that advance safe, barrier-free navigation for BLV users.

comment: 42 pages, 14 figures, 28 tables

♻ ☆ From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering

Yu Zhao, Ying Zhang, Xuhui Sui, Baohang Zhou, Li Shen, Dacheng Tao

Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA methods either utilize implicit knowledge in multimodal large language models (MLLMs) via in-context learning or explicit knowledge via retrieval augmented generation. However, their reasoning processes remain implicit, without explicit multi-step trajectories from MLLMs. To address this gap, we provide a Hindsight Distilled Reasoning (HinD) framework with Knowledge Encouragement Preference Optimization, aiming at self-encouraging the knowledge reasoning ability inside the MLLM. First, we construct the Hindsight Teacher by prompting the MLLM to complete the reasoning process with knowing the right answer, obtaining Hindsight-Zero training data. Then, the Foresight Student, without knowing the answer, learns the golden trajectories from Hindsight: (1) Hindsight Distillation Fine-Tuning (HDFT) to self-distill the Hindsight-Zero into a modularized Chain-of-Thought (CoT) Generator and a Knowledge Generator for sequential steps and discrete facts generation, respectively; (2) Knowledge Encouragement Preference Optimization (KEPO) to encourage the under-confident but relevant knowledge inside the MLLM and suppress the over-confident but irrelevant one. Experiments on OK-VQA and A-OKVQA validate the effectiveness of HinD, showing that HinD with 7-8B MLLM achieves superior performance without commercial model APIs or retrieved knowledge.

♻ ☆ Attention-guided reference point shifting for Gaussian-mixture-based partial point set registration

Mizuki Kikkawa, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki

This study investigates the impact of the invariance of feature vectors for partial-to-partial point set registration under translation and rotation of input point sets, particularly in the realm of techniques based on deep learning and Gaussian mixture models (GMMs). We reveal both theoretical and practical problems associated with such deep-learning-based registration methods using GMMs, with a particular focus on the limitations of DeepGMR, a pioneering study in this line, to the partial-to-partial point set registration. Our primary goal is to uncover the causes behind such methods and propose a comprehensible solution for that. To address this, we introduce an attention-based reference point shifting (ARPS) layer, which robustly identifies a common reference point of two partial point sets, thereby acquiring transformation-invariant features. The ARPS layer employs a well-studied attention module to find a common reference point rather than the overlap region. Owing to this, it significantly enhances the performance of DeepGMR and its recent variant, UGMMReg. Furthermore, these extension models outperform even prior deep learning methods using attention blocks and Transformer to extract the overlap region or common reference points. We believe these findings provide deeper insights into registration methods using deep learning and GMMs.

comment: 16 pages, 9 figures, 7 tables

♻ ☆ Two-stage Vision Transformers and Hard Masking offer Robust Object Representations

Ananthu Aniraj, Cassio F. Dantas, Dino Ienco, Diego Marcos

Context can strongly affect object representations, sometimes leading to undesired biases, particularly when objects appear in out-of-distribution backgrounds at inference. At the same time, many object-centric tasks require to leverage the context for identifying the relevant image regions. We posit that this conundrum, in which context is simultaneously needed and a potential nuisance, can be addressed by an attention-based approach that uses learned binary attention masks to ensure that only attended image regions influence the prediction. To test this hypothesis, we evaluate a two-stage framework: stage 1 processes the full image to discover object parts and identify task-relevant regions, for which context cues are likely to be needed, while stage 2 leverages input attention masking to restrict its receptive field to these regions, enabling a focused analysis while filtering out potentially spurious information. Both stages are trained jointly, allowing stage 2 to refine stage 1. The explicit nature of the semantic masks also makes the model's reasoning auditable, enabling powerful test-time interventions to further enhance robustness. Extensive experiments across diverse benchmarks demonstrate that this approach significantly improves robustness against spurious correlations and out-of-distribution backgrounds. Code: https://github.com/ananthu-aniraj/ifam

comment: Accepted at ICPR 2026

♻ ☆ Refracting Reality: Generating Images with Realistic Transparent Objects

Yue Yin, Enze Tao, Dylan Campbell

Generative image models can produce convincingly real images, with plausible shapes, textures, layouts and lighting. However, one domain in which they perform notably poorly is in the synthesis of transparent objects, which exhibit refraction, reflection, absorption and scattering. Refraction is a particular challenge, because refracted pixel rays often intersect with surfaces observed in other parts of the image, providing a constraint on the color. It is clear from inspection that generative models have not distilled the laws of optics sufficiently well to accurately render refractive objects. In this work, we consider the problem of generating images with accurate refraction, given a text prompt. We synchronize the pixels within the object's boundary with those outside by warping and merging the pixels using Snell's Law of Refraction, at each step of the generation trajectory. For those surfaces that are not directly observed in the image, but are visible via refraction or reflection, we recover their appearance by synchronizing the image with a second generated image -- a panorama centered at the object -- using the same warping and merging procedure. We demonstrate that our approach generates much more optically-plausible images that respect the physical constraints.

comment: https://github.com/YueYin27/snellcaster.git

♻ ☆ Organizing Unstructured Image Collections using Natural Language

Mingxuan Liu, Zhun Zhong, Jun Li, Gianni Franchi, Subhankar Roy, Elisa Ricci

In this work, we introduce and study the novel task of Open-ended Semantic Multiple Clustering (OpenSMC). Given a large, unstructured image collection, the goal is to automatically discover several, diverse semantic clustering criteria (e.g., Activity or Location) from the images, and subsequently organize them according to the discovered criteria, without requiring any human input. Our framework, X-Cluster: eXploratory Clustering, treats text as a reasoning proxy: it concurrently scans the entire image collection, proposes candidate criteria in natural language, and groups images into meaningful clusters per criterion. This radically differs from previous works, which either assume predefined clustering criteria or fixed cluster counts. To evaluate X-Cluster, we create two new benchmarks, COCO-4C and Food-4C, each annotated with four distinct grouping criteria and corresponding cluster labels. Experiments show that X-Cluster can effectively reveal meaningful partitions on several datasets. Finally, we use X-Cluster to achieve various real-world applications, including uncovering hidden biases in text-to-image (T2I) generative models and analyzing image virality on social media. Project page: https://oatmealliu.github.io/xcluster.html

comment: Accepted to CVPR 2026 Findings. Project page: https://oatmealliu.github.io/xcluster.html

♻ ☆ ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View Hypergraph

Junhao Cai, Deyu Zeng, Junhao Pang, Lini Li, Zongze Wu, Xiaopin Zhong

Current text-to-3D generation methods excel in natural scenes but struggle with industrial applications due to two critical limitations: domain adaptation challenges where conventional LoRA fusion causes knowledge interference across categories, and geometric reasoning deficiencies where pairwise consistency constraints fail to capture higher-order structural dependencies essential for precision manufacturing. We propose a novel framework named ForgeDreamer addressing both challenges through two key innovations. First, we introduce a Multi-Expert LoRA Ensemble mechanism that consolidates multiple category-specific LoRA models into a unified representation, achieving superior cross-category generalization while eliminating knowledge interference. Second, building on enhanced semantic understanding, we develop a Cross-View Hypergraph Geometric Enhancement approach that captures structural dependencies spanning multiple viewpoints simultaneously. These components work synergistically improved semantic understanding, enables more effective geometric reasoning, while hypergraph modeling ensures manufacturing-level consistency. Extensive experiments on a custom industrial dataset demonstrate superior semantic generalization and enhanced geometric fidelity compared to state-of-the-art approaches. Code is available at https://github.com/Junhaocai27/ForgeDreamer

comment: Accepted to CVPR 2026 Findings!

♻ ☆ Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

Shuang Chen, Quanxin Shou, Hangting Chen, Yucheng Zhou, Kaituo Feng, Wenbo Hu, Yi-Fan Zhang, Yunlong Lin, Wenxuan Huang, Mingyang Song, Dasen Dai, Bolin Jiang, Manyuan Zhang, Shi-Xue Zhang, Zhengkai Jiang, Lucas Wang, Zhao Zhong, Yu Cheng, Nanyun Peng

Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, they still rely primarily on frozen parametric knowledge, which makes them struggle with real-world image generation involving long-tail and knowledge-intensive concepts. Inspired by the broad success of agents on real-world tasks, we explore agentic modeling to address this limitation. Specifically, we present Unify-Agent, a unified multimodal agent for world-grounded image synthesis, which reframes image generation as an agentic pipeline consisting of prompt understanding, multimodal evidence searching, grounded recaptioning, and final synthesis. To train our model, we construct a tailored multimodal data pipeline and curate 143K high-quality agent trajectories for world-grounded image synthesis, enabling effective supervision over the full agentic generation process. We further introduce FactIP, a benchmark covering 12 categories of culturally significant and long-tail factual concepts that explicitly requires external knowledge grounding. Extensive experiments show that our proposed Unify-Agent substantially improves over its base unified model across diverse benchmarks and real world generation tasks, while approaching the world knowledge capabilities of the strongest closed-source models. As an early exploration of agent-based modeling for world-grounded image synthesis, our work highlights the value of tightly coupling reasoning, searching, and generation for reliable open-world agentic image synthesis.

comment: Project Page: https://github.com/shawn0728/Unify-Agent

♻ ☆ Coupled Reconstruction of 2D Blood Flow and Vessel Geometry from Noisy Images via Physics-Informed Neural Networks and Quasi-Conformal Mapping

Han Zhang, Xue-Cheng Tai, Jean-Michel Morel, Raymond H. Chan

Blood flow imaging provides important information for hemodynamic behavior within the vascular system and plays an essential role in medical diagnosis and treatment planning. However, obtaining high-quality flow images remains a significant challenge. In this work, we address the problem of denoising flow images that may suffer from artifacts due to short acquisition times or device-induced errors. We formulate this task as an optimization problem, where the objective is to minimize the discrepancy between the modeled velocity field, constrained to satisfy the Navier-Stokes equations, and the observed noisy velocity data. To solve this problem, we decompose it into two subproblems: a fluid subproblem and a geometry subproblem. The fluid subproblem leverages a Physics-Informed Neural Network to reconstruct the velocity field from noisy observations, assuming a fixed domain. The geometry subproblem aims to infer the underlying flow region by optimizing a quasi-conformal mapping that deforms a reference domain. These two subproblems are solved in an alternating Gauss-Seidel fashion, iteratively refining both the velocity field and the domain. Upon convergence, the framework yields a high-quality reconstruction of the flow image. We validate the proposed method through experiments on synthetic flow data in a converging channel geometry under varying levels of Gaussian noise, and on real-like flow data in an aortic geometry with signal-dependent noise. The results demonstrate the effectiveness and robustness of the approach. Additionally, ablation studies are conducted to assess the influence of key hyperparameters.

♻ ☆ Representation Learning with Semantic-aware Instance and Sparse Token Alignments

Phuoc-Nguyen Bui, Toan Duc Nguyen, Junghyun Bum, Duc-Tai Le, Hyunseung Choo

Medical contrastive vision-language pre-training (VLP) has demonstrated significant potential in improving performance on downstream tasks. Traditional approaches typically employ contrastive learning, treating paired image-report samples as positives and unpaired ones as negatives. However, in medical datasets, there can be substantial similarities between images or reports from different patients. Rigidly treating all unpaired samples as negatives, can disrupt the underlying semantic structure and negatively impact the quality of the learned representations. In this paper, we propose a multi-level alignment framework, Representation Learning with Semantic-aware Instance and Sparse Token Alignments (SISTA) by exploiting the semantic correspondence between medical image and radiology reports at two levels, i.e., image-report and patch-word levels. Specifically, we improve the conventional contrastive learning by incorporating inter-report similarity to eliminate the false negatives and introduce a method to effectively align image patches with relevant word tokens. Experimental results demonstrate the effectiveness of the proposed framework in improving transfer performance across different datasets on three downstream tasks: image classification, image segmentation, and object detection. Notably, our framework achieves significant improvements in fine-grained tasks even with limited labeled data. Codes and pre-trained models will be made available.

comment: Accepted to ICPR 2026

♻ ☆ Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution

Xun Zhang, Kaicheng Yang, Hongliang Lu, Haotong Qin, Yong Guo, Yulun Zhang

Recently, Diffusion Transformers (DiTs) have emerged in Real-World Image Super-Resolution (Real-ISR) to generate high-quality textures, yet their heavy inference burden hinders real-world deployment. While Post-Training Quantization (PTQ) is a promising solution for acceleration, existing methods in super-resolution mostly focus on U-Net architectures, whereas generic DiT quantization is typically designed for text-to-image tasks. Directly applying these methods to DiT-based super-resolution models leads to severe degradation of local textures. Therefore, we propose Q-DiT4SR, the first PTQ framework specifically tailored for DiT-based Real-ISR. We propose H-SVD, a hierarchical SVD that integrates a global low-rank branch with a local block-wise rank-1 branch under a matched parameter budget. We further propose Variance-aware Spatio-Temporal Mixed Precision: VaSMP allocates cross-layer weight bit-widths in a data-free manner based on rate-distortion theory, while VaTMP schedules intra-layer activation precision across diffusion timesteps via dynamic programming (DP) with minimal calibration. Experiments on multiple real-world datasets demonstrate that our Q-DiT4SR achieves SOTA performance under both W4A6 and W4A4 settings. Notably, the W4A4 quantization configuration reduces model size by 5.8$\times$ and computational operations by 6.14$\times$. Our code and models will be available at https://github.com/xunzhang1128/Q-DiT4SR.

comment: Our code and models will be available at https://github.com/xunzhang1128/Q-DiT4SR

♻ ☆ Conditional Polarization Guidance for Camouflaged Object Detection

QIfan Zhang, Hao Wang, Xiangrong Qin, Ruijie Li

Camouflaged object detection (COD) aims to identify targets that are highly blended with their backgrounds. Recent works have shown that the optical characteristics of polarization cues play a significant role in improving camouflaged object detection. However, most existing polarization-based approaches depend on complex visual encoders and fusion mechanisms, leading to increased model complexity and computational overhead, while failing to fully explore how polarization can explicitly guide hierarchical RGB representation learning. To address these limitations, we propose CPGNet, an asymmetric RGB-polarization framework that introduces a conditional polarization guidance mechanism to explicitly regulate RGB feature learning for camouflaged object detection. Specifically, we design a lightweight polarization interaction module that jointly models these complementary cues and generates reliable polarization guidance in a unified manner. Unlike conventional feature fusion strategies, the proposed conditional guidance mechanism dynamically modulates RGB features using polarization priors, enabling the network to focus on subtle discrepancies between camouflaged objects and their backgrounds. Furthermore, we introduce a polarization edge-guided frequency refinement strategy that enhances high-frequency components under polarization constraints, effectively breaking camouflage patterns. Finally, we develop an iterative feedback decoder to perform coarse-to-fine feature calibration and progressively refine camouflage prediction. Extensive experiments on polarization datasets across multiple tasks, along with evaluations on non-polarization datasets, demonstrate that CPGNet consistently outperforms state-of-the-art methods.

comment: 11 pages, 10 figures, 4 tables

♻ ☆ WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks

Ziyuan He, Zhiqing Guo, Liejun Wang, Gaobo Yang, Yunfeng Diao, Dan Ma

Deepfake technology poses increasing risks such as privacy invasion and identity theft. To address these threats, we propose WaveGuard, a proactive watermarking framework that enhances robustness and imperceptibility via frequency-domain embedding and graph-based structural consistency. Specifically, we embed watermarks into high-frequency sub-bands using Dual-Tree Complex Wavelet Transform (DT-CWT) and employ a Structural Consistency Graph Neural Network (SC-GNN) to preserve visual quality. We also design an attention module to refine embedding precision. Experimental results on face swap and reenactment tasks demonstrate that WaveGuard outperforms state-of-the-art methods in both robustness and visual quality. Code is available at https://github.com/vpsg-research/WaveGuard.

comment: 14 pages, 6 figures, 7 tables

♻ ☆ Cross-Camera Distracted Driver Classification through Feature Disentanglement and Contrastive Learning

Luigi Celona, Simone Bianco, Paolo Napoletano

The classification of distracted drivers is pivotal for ensuring safe driving. Previous studies demonstrated the effectiveness of neural networks in automatically predicting driver distraction, fatigue, and potential hazards. However, recent research has uncovered a significant loss of accuracy in these models when applied to samples acquired under conditions that differ from the training data. In this paper, we introduce a robust model designed to withstand changes in camera position within the vehicle. Our Driver Behavior Monitoring Network (DBMNet) relies on a lightweight backbone and integrates a disentanglement module to discard camera view information from features, coupled with contrastive learning to enhance the encoding of various driver actions. Experiments conducted using a leave-one-camera-out protocol on the daytime and nighttime subsets of the 100-Driver dataset validate the effectiveness of our approach. Cross-dataset and cross-camera experiments conducted on three benchmark datasets, namely AUCDD-V1, EZZ2021 and SFD, demonstrate the superior generalization capabilities of the proposed method. Overall DBMNet achieves an improvement of 7% in Top-1 accuracy compared to existing efficient approaches. Moreover, a quantized version of the DBMNet and all considered methods has been deployed on a Coral Dev Board board. In this deployment scenario, DBMNet outperforms alternatives, achieving the lowest average error while maintaining a compact model size, low memory footprint, fast inference time, and minimal power consumption.

♻ ☆ Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models AAAI 2026

Hao Tang, Yu Liu, Shuanglin Yan, Fei Shen, Shengfeng He, Jing Qin

Reliable zero-shot detection of out-of-distribution (OOD) inputs is critical for deploying vision-language models in open-world settings. However, the lack of labeled negatives in zero-shot OOD detection necessitates proxy signals that remain effective under distribution shift. Existing negative-label methods rely on a fixed set of textual proxies, which (i) sparsely sample the semantic space beyond in-distribution (ID) classes and (ii) remain static while only visual features drift, leading to cross-modal misalignment and unstable predictions. In this paper, we propose CoEvo, a training- and annotation-free test-time framework that performs bidirectional, sample-conditioned adaptation of both textual and visual proxies. Specifically, CoEvo introduces a proxy-aligned co-evolution mechanism to maintain two evolving proxy caches, which dynamically mines contextual textual negatives guided by test images and iteratively refines visual proxies, progressively realigning cross-modal similarities and enlarging local OOD margins. Finally, we dynamically re-weight the contributions of dual-modal proxies to obtain a calibrated OOD score that is robust to distribution shift. Extensive experiments on standard benchmarks demonstrate that CoEvo achieves state-of-the-art performance, improving AUROC by 1.33% and reducing FPR95 by 45.98% on ImageNet-1K compared to strong negative-label baselines.

comment: Accepted by AAAI 2026

♻ ☆ Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack

Nanxiang Jiang, Zhaoxin Fan, Enhan Kang, Daiheng Gao, Yun Zhou, Yanxia Chang, Zheng Zhu, Yeying Jin, Wenjun Wu

Recent advances in text-to-image (T2I) diffusion models have enabled impressive generative capabilities, but they also raise significant safety concerns due to the potential to produce harmful or undesirable content. While concept erasure has been explored as a mitigation strategy, most existing approaches and corresponding attack evaluations are tailored to Stable Diffusion (SD) and exhibit limited effectiveness when transferred to next-generation rectified flow transformers such as Flux. In this work, we present ReFlux, the first concept attack method specifically designed to assess the robustness of concept erasure in the latest rectified flow-based T2I framework. Our approach is motivated by the observation that existing concept erasure techniques, when applied to Flux, fundamentally rely on a phenomenon known as attention localization. Building on this insight, we propose a simple yet effective attack strategy that specifically targets this property. At its core, a reverse-attention optimization strategy is introduced to effectively reactivate suppressed signals while stabilizing attention. This is further reinforced by a velocity-guided dynamic that enhances the robustness of concept reactivation by steering the flow matching process, and a consistency-preserving objective that maintains the global layout and preserves unrelated content. Extensive experiments consistently demonstrate the effectiveness and efficiency of the proposed attack method, establishing a reliable benchmark for evaluating the robustness of concept erasure strategies in rectified flow transformers.

♻ ☆ Improving Multimodal Sentiment Analysis via Modality Optimization and Dynamic Primary Modality Selection

Dingkang Yang, Mingcheng Li, Xuecheng Wu, Zhaoyu Chen, Kaixun Jiang, Keliang Liu, Peng Zhai, Lihua Zhang

Multimodal Sentiment Analysis (MSA) aims to predict sentiment from language, acoustic, and visual data in videos. However, imbalanced unimodal performance often leads to suboptimal fused representations. Existing approaches typically adopt fixed primary modality strategies to maximize dominant modality advantages, yet fail to adapt to dynamic variations in modality importance across different samples. Moreover, non-language modalities suffer from sequential redundancy and noise, degrading model performance when they serve as primary inputs. To address these issues, this paper proposes a modality optimization and dynamic primary modality selection framework (MODS). First, a Graph-based Dynamic Sequence Compressor (GDC) is constructed, which employs capsule networks and graph convolution to reduce sequential redundancy in acoustic/visual modalities. Then, we develop a sample-adaptive Primary Modality Selector (MSelector) for dynamic dominance determination. Finally, a Primary-modality-Centric Cross-Attention (PCCA) module is designed to enhance dominant modalities while facilitating cross-modal interaction. Extensive experiments on four benchmark datasets demonstrate that MODS outperforms state-of-the-art methods, achieving superior performance by effectively balancing modality contributions and eliminating redundant noise.

♻ ☆ ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion

Remy Sabathier, David Novotny, Niloy J. Mitra, Tom Monnier

Generating animated 3D objects is at the heart of many applications, yet most advanced works are typically difficult to apply in practice because of their limited setup, their long runtime, or their limited quality. We introduce ActionMesh, a generative model that predicts production-ready 3D meshes "in action" in a feed-forward manner. Drawing inspiration from early video models, our key insight is to modify existing 3D diffusion models to include a temporal axis, resulting in a framework we dubbed "temporal 3D diffusion". Specifically, we first adapt the 3D diffusion stage to generate a sequence of synchronized latents representing time-varying and independent 3D shapes. Second, we design a temporal 3D autoencoder that translates a sequence of independent shapes into the corresponding deformations of a pre-defined reference shape, allowing us to build an animation. Combining these two components, ActionMesh generates animated 3D meshes from different inputs like a monocular video, a text description, or even a 3D mesh with a text prompt describing its animation. Besides, compared to previous approaches, our method is fast and produces results that are rig-free and topology consistent, hence enabling rapid iteration and seamless applications like texturing and retargeting. We evaluate our model on standard video-to-4D benchmarks (Consistent4D, Objaverse) and report state-of-the-art performances on both geometric accuracy and temporal consistency, demonstrating that our model can deliver animated 3D meshes with unprecedented speed and quality.

comment: CVPR 2026. Project webpage with code and videos: https://remysabathier.github.io/actionmesh/ . V2 update includes more baseline models with a larger evaluation set on our new publicly released benchmark ActionBench, and {3D+video}-to-animated-mesh qualitative comparison in supplemental

♻ ☆ CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning

Qi Song, Honglin Li, Yingchen Yu, Haoyi Zhou, Lin Yang, Song Bai, Qi She, Zilong Huang, Yunqing Zhao

Recent releases such as o3 highlight human-like "thinking with images" reasoning that combines tool use with stepwise verification, yet most open-source approaches still rely on text-only chains, rigid visual schemas, or single-step pipelines, limiting flexibility, interpretability, and transferability on complex tasks. We introduce CodeDance, which explores executable code as a general solver for visual reasoning. Unlike fixed-schema calls (e.g., only predicting bounding-box coordinates), CodeDance defines, composes, and executes code to orchestrate multiple tools, compute intermediate results, and render visual artifacts (e.g., boxes, lines, plots) that support transparent, self-checkable reasoning. To guide this process, we introduce a reward for balanced and adaptive tool calling, which balances exploration with efficiency and mitigates tool overuse. Interestingly, beyond the expected capabilities taught by atomic supervision, we empirically observe novel emergent behaviors during RL training: CodeDance demonstrates novel tool invocations, unseen compositions, and cross-task transfer. These behaviors arise without task-specific fine-tuning, suggesting a general and scalable mechanism for executable visual reasoning. Extensive experiments across reasoning benchmarks (e.g., visual search, math, chart QA) show that CodeDance not only consistently outperforms schema-driven and text-only baselines, but also surpasses closed models such as GPT-4o and larger open-source models.

comment: CVPR 2026. Project page: https://codedance-vl.github.io/

♻ ☆ BigEarthNet.txt: A Large-Scale Multi-Sensor Image-Text Dataset and Benchmark for Earth Observation

Johann-Ludwig Herzog, Mathis Jürgen Adler, Leonard Hackel, Yan Shu, Angelos Zavras, Ioannis Papoutsis, Paolo Rota, Begüm Demir

Vision-langugage models (VLMs) have shown strong performance in computer vision (CV), yet their performance on remote sensing (RS) data remains limited due to the lack of large-scale, multi-sensor RS image-text datasets with diverse textual annotations. Existing datasets predominantly include aerial Red-Green-Blue imagery, with short or weakly grounded captions, and provide limited diversity in annotation types. To address this limitation, we introduce BigEarthNet$.$txt, a large-scale, multi-sensor image-text dataset designed to advance instruction-driven image-text learning in Earth observation across multiple tasks. BigEarthNet$.$txt contains 464044 co-registered Sentinel-1 synthetic aperture radar and Sentinel-2 multispectral images with 9.6M text annotations, including: i) geographically anchored captions describing land-use/land-cover (LULC) classes, their spatial relations, and environmental context; ii) visual question answering pairs relevant for different tasks; and iii) referring expression detection instructions for bounding box prediction. Through a comparative statistical analysis, we demonstrate that BigEarthNet$.$txt surpasses existing RS image-text datasets in textual richness and annotation type variety. We further establish a manually-verified benchmark split to evaluate VLMs in RS and CV. The results show the limitations of these models on tasks that involve complex LULC classes, whereas fine-tuning using BigEarthNet$.$txt results in consistent performance gains across all considered tasks.

comment: For details, see https://txt.bigearth.net

♻ ☆ Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion

Songwei Liu, Chao Zeng, Chenqian Yan, Xurui Peng, Xing Wang, Fangmin Chen, Xing Mei

Diffusion models have transformed image synthesis by establishing unprecedented quality and creativity benchmarks. Nevertheless, their large-scale deployment faces challenges due to computationally intensive iterative denoising processes. Although post-training quantization (PTQ) provides an effective pathway for accelerating sampling, the iterative nature of diffusion models causes stepwise quantization errors to accumulate progressively during generation, inevitably compromising output fidelity. To address this challenge, we develop a theoretical framework that mathematically formulates error propagation in Diffusion Models (DMs), deriving per-step quantization error propagation equations and establishing the first closed-form solution for cumulative error. Building on this theoretical foundation, we propose a timestep-aware cumulative error compensation scheme. Extensive experiments on multiple image datasets demonstrate that our compensation strategy effectively mitigates error propagation, significantly enhancing existing PTQ methods. Specifically, it achieves a 1.2 PSNR improvement over SVDQuant on SDXL W4A4, while incurring only an additional $<$ 0.5\% time overhead.

♻ ☆ Exploring Self-Supervised Learning with U-Net Masked Autoencoders and EfficientNet-B7 for Improved Gastrointestinal Abnormality Classification in Video Capsule Endoscopy

Vamshi Krishna Kancharla, Pavan Kumar Kaveti, Dasari Naga Raju

Video Capsule Endoscopy (VCE) has become an indispensable diagnostic tool for gastrointestinal (GI) disorders due to its non-invasive nature and ability to capture high-resolution images of the small intestine. However, the enormous volume of data generated during a single procedure makes manual inspection labor-intensive, time-consuming, and prone to inter-observer variability. Automated analysis using deep learning offers a promising solution, but its effectiveness is often limited by data imbalance and the high cost of labeled medical data. In this work, we propose a novel framework that combines self-supervised learning through a U-Net-based masked autoencoder with supervised feature extraction using EfficientNet-B7 for multi-class abnormality classification in VCE images. The U-Net model is first trained in a self-supervised manner using Gaussian noise removal and masked reconstruction to learn robust visual representations without requiring annotations. The learned encoder features are then fused with EfficientNet-B7 features to form a rich, discriminative representation for classification. We evaluate our approach on the Capsule Vision 2024 Challenge dataset consisting of ten abnormality classes and a dominant normal class. Experimental results demonstrate that the proposed fusion framework achieves a validation accuracy of 94\%, outperforming standalone architectures and attention-based fusion variants. The study highlights the effectiveness of self-supervised representation learning and feature fusion in addressing class imbalance and improving diagnostic accuracy in real-world medical imaging scenarios.

comment: Capsule Vision 2024 Challenge

♻ ☆ Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA

Zexi Wu, Baolu Li, Jing Dai, Yiming Zhang, Yue Ma, Qinghe Wang, Xu Jia, Hongming Xu

Achieving semantic alignment across diverse video generation conditions remains a significant challenge. Methods that rely on explicit structural guidance often enforce rigid spatial constraints that limit semantic flexibility, whereas models tailored for individual control types lack interoperability and adaptability. These design bottlenecks hinder progress toward flexible and efficient semantic video generation. To address this, we propose Video2LoRA, a scalable and generalizable framework for semantic-controlled video generation that conditions on a reference video. Video2LoRA employs a lightweight hypernetwork to predict personalized LoRA weights for each semantic input, which are combined with auxiliary matrices to form adaptive LoRA modules integrated into a frozen diffusion backbone. This design enables the model to generate videos consistent with the reference semantics while preserving key style and content variations, eliminating the need for any per-condition training. Notably, the final model weights less than 150MB, making it highly efficient for storage and deployment. Video2LoRA achieves coherent, semantically aligned generation across diverse conditions and exhibits strong zero-shot generalization to unseen semantics.

comment: 10 pages

♻ ☆ CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer

Wenbo Nie, Zixiang Li, Renshuai Tao, Bin Wu, Yunchao Wei, Yao Zhao

Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods have made great strides, most of them operate at global level but overlook region-wise and even pixel-wise semantic correspondence. To address this, we propose CoCoDiff, a novel training-free and low-cost style transfer framework that leverages pretrained latent diffusion models to achieve fine-grained, semantically consistent stylization. We identify that correspondence cues within generative diffusion models are under-explored and that content consistency across semantically matched regions is often neglected. CoCoDiff introduces a pixel-wise semantic correspondence module that mines intermediate diffusion features to construct a dense alignment map between content and style images. Furthermore, a cycle-consistency module then enforces structural and perceptual alignment across iterations, yielding object and region level stylization that preserves geometry and detail. Despite requiring no additional training or supervision, CoCoDiff delivers state-of-the-art visual quality and strong quantitative results, outperforming methods that rely on extra training or annotations.

♻ ☆ Low-Resolution Editing is All You Need for High-Resolution Editing

Junsung Lee, Hyunsoo Lee, Yong Jae Lee, Bohyung Han

High-resolution content creation is rapidly emerging as a central challenge in both the vision and graphics communities. Images serve as the most fundamental modality for visual expression, and content generation that aligns with the user intent requires effective, controllable high-resolution image manipulation mechanisms. However, existing approaches remain limited to low-resolution settings, typically supporting only up to 1K resolution. In this work, we introduce the task of high-resolution image editing and propose a test-time optimization framework to address it. Our method performs patch-wise optimization on high-resolution source images, followed by a fine-grained detail transfer module and a novel synchronization strategy to maintain consistency across patches. Extensive experiments show that our method produces high-quality edits, facilitating high-resolution content creation.

comment: CVPR 2026

♻ ☆ MOLM: Mixture of LoRA Markers ICLR 2026

Samar Fares, Nurbek Tastan, Noor Hussein, Karthik Nandakumar

Generative models can generate photorealistic images at scale. This raises urgent concerns about the ability to detect synthetically generated images and attribute these images to specific sources. While watermarking has emerged as a possible solution, existing methods remain fragile to realistic distortions, susceptible to adaptive removal, and expensive to update when the underlying watermarking key changes. We propose a general watermarking framework that formulates the encoding problem as key-dependent perturbation of the parameters of a generative model. Within this framework, we introduce Mixture of LoRA Markers (MOLM), a routing-based instantiation in which binary keys activate lightweight LoRA adapters inside residual and attention blocks. This design avoids key-specific re-training and achieves the desired properties such as imperceptibility, fidelity, verifiability, and robustness. Experiments on Stable Diffusion and FLUX show that MOLM preserves image quality while achieving robust key recovery against distortions, compression and regeneration, averaging attacks, and black-box adversarial attacks on the extractor.

comment: ICLR 2026

♻ ☆ RANGER: A Monocular Zero-Shot Semantic Navigation Framework through Visual Contextual Adaptation

Ming-Ming Yu, Yi Chen, Börje F. Karlsson, Wenjun Wu

Efficient target localization and autonomous navigation in complex environments are fundamental to real-world embodied applications. While recent advances in multimodal foundation models have enabled zero-shot object goal navigation, allowing robots to search for arbitrary objects without fine-tuning, existing methods face two key limitations: (1) heavy reliance on ground-truth depth and pose information, which restricts applicability in real-world scenarios; and (2) lack of visual in-context learning (VICL) capability to extract geometric and semantic priors from environmental context, as in a short traversal video. To address these challenges, we propose RANGER, a novel zero-shot, open-vocabulary semantic navigation framework that operates using only a monocular camera. Leveraging powerful 3D foundation models, RANGER eliminates the dependency on depth and pose while exhibiting strong VICL capability. By simply observing a short video of the target environment, the system can also significantly improve task efficiency without requiring architectural modifications or task-specific retraining. The framework integrates several key components: keyframe-based 3D reconstruction, semantic point cloud generation, vision-language model (VLM)-driven exploration value estimation, high-level adaptive waypoint selection, and low-level action execution. Experiments on the HM3D benchmark and real-world environments demonstrate that RANGER achieves competitive performance in terms of navigation success rate and exploration efficiency, while showing superior VICL adaptability, with no previous 3D mapping of the environment required.

comment: Accepted at ICRA 2026

2026-03-31

Sound 15

☆ Covertly improving intelligibility with data-driven adaptations of speech timing

Paige Tuttösí, Angelica Lim, H. Henny Yeung, Yue Wang, Jean-Julien Aucouturier

Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speech. However, it remains unclear whether this strategy actually makes speech more intelligible. Here, we take advantage of recent advancements in machine-generated speech allowing more precise control of speech rate in order to systematically examine how targeted speech-rate adjustments may improve comprehension. We first use reverse-correlation experiments to show that the temporal influence of speech rate prior to a target vowel contrast (ex. the tense-lax distinction) in fact manifests in a scissor-like pattern, with opposite effects in early versus late context windows; this pattern is remarkably stable both within individuals and across native L1-English listeners and L2-English listeners with French, Mandarin, and Japanese L1s. Second, we show that this speech rate structure not only facilitates L2 listeners' comprehension of the target vowel contrast, but that native listeners also rely on this pattern in challenging acoustic conditions. Finally, we build a data-driven text-to-speech algorithm that replicates this temporal structure on novel speech sequences. Across a variety of sentences and vowel contrasts, listeners remained unaware that such targeted slowing improved word comprehension. Strikingly, participants instead judged the common strategy of global slowing as clearer, even though it actually increased comprehension errors. Together, these results show that targeted adjustments to speech rate significantly aid intelligibility under challenging conditions, while often going unnoticed. More generally, this paper provides a data-driven methodology to improve the accessibility of machine-generated speech which can be extended to other aspects of speech comprehension and a wide variety of listeners and environments.

☆ SIREN: Spatially-Informed Reconstruction of Binaural Audio with Vision ICASSP 2026

Mingyeong Song, Seoyeon Ko, Junhyug Noh

Binaural audio delivers spatial cues essential for immersion, yet most consumer videos are monaural due to capture constraints. We introduce SIREN, a visually guided mono to binaural framework that explicitly predicts left and right channels. A ViT-based encoder learns dual-head self-attention to produce a shared scene map and end-to-end L/R attention, replacing hand-crafted masks. A soft, annealed spatial prior gently biases early L/R grounding, and a two-stage, confidence-weighted waveform-domain fusion (guided by mono reconstruction and interaural phase consistency) suppresses crosstalk when aggregating multi-crop and overlapping windows. Evaluated on FAIR-Play and MUSIC-Stereo, SIREN yields consistent gains on time-frequency and phase-sensitive metrics with competitive SNR. The design is modular and generic, requires no task-specific annotations, and integrates with standard audio-visual pipelines.

comment: 5 pages, 1 figure, to appear in ICASSP 2026

☆ A Comprehensive Corpus of Biomechanically Constrained Piano Chords: Generation, Analysis, and Implications for Voicing and Psychoacoustics

Mahesh Ramani

I present the generation and analysis of the largest known open-source corpus of playable piano chords (approximately 19.3 million entries). This dataset enumerates the two-handed search space subject to biomechanical constraints (two hands, each with 1.5 octave reach) to an unprecedented extent. To demonstrate the corpus's utility, the relationship between voicing shape and psychoacoustic targets was modeled. Harmonicity proved intrinsic to pitch-class identity: voicing statistics added negligible variance ($ΔR^2 \approx 0.014\%$, $p \approx 0.13$). Conversely, voicing significantly predicted dissonance ($ΔR^2 \approx 6.75\%$, $p \approx 0.0008$). Crucially, skewness ($β\approx +0.145$) was approximately 5.8$\times$ more effective than spread ($β\approx -0.025$) at predicting roughness. The analysis challenges the pedagogical emphasis on ``spread'': skewness is a stronger predictor of dissonance than spread. This suggests that clarity in ``open voicings'' is driven less by width than by negative skewness; achieving lower-register clearance by placing wide gaps at the bottom and allowing tighter clustering in the treble. The results demonstrate the corpus's ability to enable future research, especially in areas such as generative modeling, voice-leading topology, and psychoacoustic analysis.

comment: 10 pages, 3 figures

☆ LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space

Detai Xin, Shujie Hu, Chengzuo Yang, Chen Huang, Guoqiao Yu, Guanglu Wan, Xunliang Cai

We present LongCat-AudioDiT, a novel, non-autoregressive diffusion-based text-to-speech (TTS) model that achieves state-of-the-art (SOTA) performance. Unlike previous methods that rely on intermediate acoustic representations such as mel-spectrograms, the core innovation of LongCat-AudioDiT lies in operating directly within the waveform latent space. This approach effectively mitigates compounding errors and drastically simplifies the TTS pipeline, requiring only a waveform variational autoencoder (Wav-VAE) and a diffusion backbone. Furthermore, we introduce two critical improvements to the inference process: first, we identify and rectify a long-standing training-inference mismatch; second, we replace traditional classifier-free guidance with adaptive projection guidance to elevate generation quality. Experimental results demonstrate that, despite the absence of complex multi-stage training pipelines or high-quality human-annotated datasets, LongCat-AudioDiT achieves SOTA zero-shot voice cloning performance on the Seed benchmark while maintaining competitive intelligibility. Specifically, our largest variant, LongCat-AudioDiT-3.5B, outperforms the previous SOTA model (Seed-TTS), improving the speaker similarity (SIM) scores from 0.809 to 0.818 on Seed-ZH, and from 0.776 to 0.797 on Seed-Hard. Finally, through comprehensive ablation studies and systematic analysis, we validate the effectiveness of our proposed modules. Notably, we investigate the interplay between the Wav-VAE and the TTS backbone, revealing the counterintuitive finding that superior reconstruction fidelity in the Wav-VAE does not necessarily lead to better overall TTS performance. Code and model weights are released to foster further research within the speech community.

comment: Code and model weights are available at https://github.com/meituan-longcat/LongCat-AudioDiT

☆ Real-Time Band-Grouped Vocal Denoising Using Sigmoid-Driven Ideal Ratio Masking

Daniel Williams

Real-time, deep learning-based vocal denoising has seen significant progress over the past few years, demonstrating the capability of artificial intelligence in preserving the naturalness of the voice while increasing the signal-to-noise ratio (SNR). However, many deep learning approaches have high amounts of latency and require long frames of context, making them difficult to configure for live applications. To address these challenges, we propose a sigmoid-driven ideal ratio mask trained with a spectral loss to encourage an increased SNR and maximized perceptual quality of the voice. The proposed model uses a band-grouped encoder-decoder architecture with frequency attention and achieves a total latency of less than 10,ms, with PESQ-WB improvements of 0.21 on stationary noise and 0.12 on nonstationary noise.

☆ Audio Hallucination Attacks: Probing the Reliability of Large Audio Language Models

Ashish Seth, Sonal Kumar, Ramaneswaran Selvakumar, Nishit Anand, Utkarsh Tyagi, Prem Seetharaman, Ramani Duraiswami, Dinesh Manocha

Large Audio Language Models (LALMs) achieve strong performance on audio-language tasks; however, their reliability in real-world settings remains underexplored. We introduce Audio Hallucination Attacks (AHA), an attack suite called AHA-Eval, comprising 6.5K QA pairs designed to test whether LALMs genuinely ground their responses in the audio input. AHA targets two attack surfaces: (i) query-based attacks, which exploit question structure to induce hallucinations about absent sounds, and (ii) audio-based attacks, which inject synthetic speech describing non-existent events into the audio stream. Evaluating state-of-the-art LALMs, including Audio Flamingo 3 and Gemini 3 Pro, we observe high attack success rates of 95.35% and 79.65%, respectively, revealing a reliability gap that is hidden by standard benchmark performance. To mitigate this, we propose a 120K QA post-alignment dataset, AHA-Guard, which successfully reduces attack success rates by up to 49%.

☆ Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition INTERSPEECH2026

Lukuang Dong, Ziwei Li, Saierdaer Yusuyin, Xianyu Zhao, Zhijian Ou

Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing while keeping language-specific orthography in a separate module. While large language models (LLMs) are promising for P2G, multilingual P2G remains challenging due to language-aware generation and severe cross-language data imbalance. We study multilingual LLM-based P2G on the ten-language CV-Lang10 benchmark. We examine robustness strategies that account for S2P uncertainty, including DANP and Simplified SKM (S-SKM). S-SKM is a Monte Carlo approximation that avoids CTC-based S2P probability weighting in P2G training. Robust training and low-resource oversampling reduce the average WER from 10.56% to 7.66%.

comment: Update after INTERSPEECH2026 submission

☆ Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation

Ui-Hyeop Shin, Hyung-Min Park

Speech separation in realistic acoustic environments remains challenging because overlapping speakers, background noise, and reverberation must be resolved simultaneously. Although recent time-frequency (TF) domain models have shown strong performance, most still rely on late-split architectures, where speaker disentanglement is deferred to the final stage, creating an information bottleneck and weakening discriminability under adverse conditions. To address this issue, we propose SR-CorrNet, an asymmetric encoder-decoder framework that introduces the separation-reconstruction (SepRe) strategy into a TF dual-path backbone. The encoder performs coarse separation from mixture observations, while the weight-shared decoder progressively reconstructs speaker-discriminative features with cross-speaker interaction, enabling stage-wise refinement. To complement this architecture, we formulate speech separation as a structured correlation-to-filter problem: spatio-spectro-temporal correlations computed from the observations are used as input features, and the corresponding deep filters are estimated to recover target signals. We further incorporate an attractor-based dynamic split module to adapt the number of output streams to the actual speaker configuration. Experimental results on WSJ0-2/3/4/5Mix, WHAMR!, and LibriCSS demonstrate consistent improvements across anechoic, noisy-reverberant, and real-recorded conditions in both single- and multi-channel settings, highlighting the effectiveness of TF-domain SepRe with correlation-based filter estimation for speech separation.

comment: Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing (T-ASLP)

☆ IQRA 2026: Interspeech Challenge on Automatic Assessment Pronunciation for Modern Standard Arabic (MSA)

Yassine El Kheir, Amit Meghanani, Mostafa Shahin, Omnia Ibrahim, Shammur Absar Chowdhury, Nada AlMarwani, Youssef Elshahawy, Ahmed Ali

We present the findings of the second edition of the IQRA Interspeech Challenge, a challenge on automatic Mispronunciation Detection and Diagnosis (MDD) for Modern Standard Arabic (MSA). Building on the previous edition, this iteration introduces \textbf{Iqra\_Extra\_IS26}, a new dataset of authentic human mispronounced speech, complementing the existing training and evaluation resources. Submitted systems employed a diverse range of approaches, spanning CTC-based self-supervised learning models, two-stage fine-tuning strategies, and using large audio-language models. Compared to the first edition, we observe a substantial jump of \textbf{0.28 in F1-score}, attributable both to novel architectures and modeling strategies proposed by participants and to the additional authentic mispronunciation data made available. These results demonstrate the growing maturity of Arabic MDD research and establish a stronger foundation for future work in Arabic pronunciation assessment.

comment: 5 pages paper

☆ Vocal Prognostic Digital Biomarkers in Monitoring Chronic Heart Failure: A Longitudinal Observational Study

Fan Wu, Matthias P. Nägele, Daryush D. Mehta, Elgar Fleisch, Frank Ruschitzka, Andreas J. Flammer, Filipe Barata

Objective: This study aimed to evaluate which voice features can predict health deterioration in patients with chronic HF. Background: Heart failure (HF) is a chronic condition with progressive deterioration and acute decompensations, often requiring hospitalization and imposing substantial healthcare and economic burdens. Current standard-of-care (SoC) home monitoring, such as weight tracking, lacks predictive accuracy and requires high patient engagement. Voice is a promising non-invasive biomarker, though prior studies have mainly focused on acute HF stages. Methods: In a 2-month longitudinal study, 32 patients with HF collected daily voice recordings and SoC measures of weight and blood pressure at home, with biweekly questionnaires for health status. Acoustic analysis generated detailed vowel and speech features. Time-series features were extracted from aggregated lookback windows (e.g., 7 days) to predict next-day health status. Explainable machine learning with nested cross-validation identified top vocal biomarkers, and a case study illustrated model application. Results: A total of 21,863 recordings were analyzed. Acoustic vowel features showed strong correlations with health status. Time-series voice features within the lookback window outperformed corresponding standard care measures, achieving peak sensitivity and specificity of 0.826 and 0.782 versus 0.783 and 0.567 for SoC metrics. Key prognostic voice features identifying deterioration included delayed energy shift, low energy variability, and higher shimmer variability in vowels, along with reduced speaking and articulation rate, lower phonation ratio, decreased voice quality, and increased formant variability in speech. Conclusion: Voice-based monitoring offers a non-invasive approach to detect early health changes in chronic HF, supporting proactive and personalized care.

☆ MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control ICLR 2026

Sahil Kumar, Namrataben Patel, Honggang Wang, Youshan Zhang

MambaVoiceCloning (MVC) asks whether the conditioning path of diffusion-based TTS can be made fully SSM-only at inference, removing all attention and explicit RNN-style recurrence layers across text, rhythm, and prosody, while preserving or improving quality under controlled conditions. MVC combines a gated bidirectional Mamba text encoder, a Temporal Bi-Mamba supervised by a lightweight alignment teacher discarded after training, and an Expressive Mamba with AdaLN modulation, yielding linear-time O(T) conditioning with bounded activation memory and practical finite look-ahead streaming. Unlike prior Mamba-TTS systems that remain hybrid at inference, MVC removes attention-based duration and style modules under a fixed StyleTTS2 mel-diffusion-vocoder backbone. Trained on LJSpeech/LibriTTS and evaluated on VCTK, CSS10 (ES/DE/FR), and long-form Gutenberg passages, MVC achieves modest but statistically reliable gains over StyleTTS2, VITS, and Mamba-attention hybrids in MOS/CMOS, F0 RMSE, MCD, and WER, while reducing encoder parameters to 21M and improving throughput by 1.6x. Diffusion remains the dominant latency source, but SSM-only conditioning improves memory footprint, stability, and deployability.

comment: Accepted at ICLR 2026

♻ ☆ Audio Language Model for Deepfake Detection Grounded in Acoustic Chain-of-Thought

Runkun Chen, Yixiong Fang, Pengyu Chang, Yuante Li, Massa Baali, Bhiksha Raj

Deepfake speech detection systems are often limited to binary classification tasks and struggle to generate interpretable reasoning or provide context-rich explanations for their decisions. These models primarily extract latent embeddings for authenticity detection but fail to leverage structured acoustic evidence such as prosodic, spectral, and physiological attributes in a meaningful manner. This paper introduces CoLMbo-DF, a Feature-Guided Audio Language Model that addresses these limitations by integrating robust deepfake detection with explicit acoustic chain-of-thought reasoning. By injecting structured textual representations of low-level acoustic features directly into the model prompt, our approach grounds the model's reasoning in interpretable evidence and improves detection accuracy. To support this framework, we introduce a novel dataset of audio pairs paired with chain-of-thought annotations. Experiments show that our method, trained on a lightweight open-source language model, significantly outperforms existing audio language model baselines despite its smaller scale, marking a significant advancement in explainable deepfake speech detection.

♻ ☆ Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis

Yushen Chen, Junzhe Liu, Yujie Tu, Zhikang Niu, Yuzhe Liang, Chunyu Qiang, Chen Zhang, Kai Yu, Xie Chen

Arabic spans over 30 spoken varieties, yet no open-source text-to-speech system unifies them. Key barriers include substantial cross-dialect lexical and phonological divergence, scarce synthesis-grade data, and the absence of a standardized multi-dialect evaluation benchmark. We present Habibi, a unified-dialectal Arabic TTS framework that addresses all three. Through a multi-step curation pipeline, we repurpose open-source ASR corpora into TTS training data covering 12+ regional dialects. A linguistically-informed curriculum learning strategy - progressing from Modern Standard Arabic to dialectal data - enables robust zero-shot synthesis without text diacritization. We further release the first standardized multi-dialect Arabic TTS benchmark, comprising over 11,000 utterances across 7 dialect subsets with manually verified transcripts. On this benchmark, our unified model matches or surpasses per-dialect specialized models. Both automatic metrics and human evaluations confirm that Habibi is highly competitive with ElevenLabs' Eleven v3 (alpha) in intelligibility, speaker similarity, and naturalness. Extensive ablations (~8,000 H100 GPU hours, 30+ configurations) validate each design choice. We open-source all checkpoints, training and inference code, and benchmark data - the first such release for multi-dialect Arabic TTS - at https://SWivid.github.io/Habibi/ .

♻ ☆ EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response

Chenpei Huang, Lingfeng Yao, Kyu In Lee, Lan Emily Zhang, Xun Chen, Miao Pan

Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic environment, enabling engaging applications such as audio dubbing and auditory immersive virtual reality (VR). Recovering similar room impulse response (RIR) directly from reverberant speech offers more accessible and flexible AEM solution. However, this capability also introduces vulnerabilities of arbitrary ``relocation" if misused by malicious user, such as facilitating advanced voice spoofing attacks or undermining the authenticity of recorded evidence. To address this issue, we propose EchoMark, the first deep learning-based AEM framework that generates perceptually similar RIRs with embedded watermark. Our design tackle the challenges posed by variable RIR characteristics, such as different durations and energy decays, by operating in the latent domain. By jointly optimizing the model with a perceptual loss for RIR reconstruction and a loss for watermark detection, EchoMark achieves both high-quality environment transfer and reliable watermark recovery. Experiments on diverse datasets validate that EchoMark achieves room acoustic parameter matching performance comparable to FiNS, the state-of-the-art RIR estimator. Furthermore, a high Mean Opinion Score (MOS) of 4.22 out of 5, watermark detection accuracy exceeding 99\%, and bit error rates (BER) below 0.3\% collectively demonstrate the effectiveness of EchoMark in preserving perceptual quality while ensuring reliable watermark embedding.

♻ ☆ POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation

Xuanchen Li, Chenrui Cui, Tianrui Wang, Meng Ge, Zikang Huang, Yizhou Peng, Jin Li, Yuheng Lu, Yu Jiang, Nyima Tashi, Longbiao Wang, Jianwu Dang

Speech Large Language Models have achieved breakthroughs in multilingual speech-to-text translation. However, existing approaches often overlook semantic commonalities across source languages, leading to biased translation performance. In this work, we propose POTSA (Parallel Optimal Transport for Speech Alignment), a new framework based on cross-lingual parallel speech pairs and Optimal Transport, designed to bridge high- and low-resource translation gaps. First, we introduce a Bias Compensation module to coarsely align initial speech representations. Second, we impose token-level OT constraints on a Q-Former using parallel pairs to establish fine-grained representation consistency. Then, we apply a layer scheduling strategy to focus OT constraints on semantically beneficial layers. Experiments on FLEURS show our method achieves SOTA performance, with +1.29 BLEU over five common languages and +2.93 BLEU on zero-shot languages, using only 10 hours of parallel speech per language.

Audio and Speech Processing 9

☆ An Information-Theoretic Method for Dynamic System Identification With Output-Only Damping Estimation

Marios Impraimakis, Feiyu Zhou, Andrew Plummer

The system identification capabilities of a novel information-theoretic method are examined here. Specifically, this work uses information-theoretic metrics and vibration-based measurements to enhance damping estimation accuracy in mechanical systems. The method refers to a key limitation in system identification, signal processing, monitoring, and alert systems. These systems integrate various components, including sensors, data acquisition devices, and alert mechanisms. They are designed to operate in an environment to calculate key parameters such as peak accelerations and duration of high acceleration values. The current operational modal identification methods, though, suffer from limitations related to obtaining poor damping estimates due to their empirical nature. This has a significant impact on alert warning systems. This occurs when their duration is misestimated; specifically, when using the vibration amplitudes as an indicator of danger alerts for monitoring systems in damage or anomaly detection scenarios. To this end, approaches based on the Shannon entropy and the Kullback-Leibler divergence concept are proposed. The primary objective is to monitor the vibration levels in near real-time and provide immediate alerts when predefined thresholds are exceeded. In considering the proposed approach, both new real-world data from the multi-axis simulation table at the University of Bath, as well as the benchmark International Association for Structural Control-American Society of Civil Engineers (IASC-ASCE) structural health monitoring problem are considered. Importantly, the approach is shown to select the optimal model, which accurately captures the correct alert duration, providing a powerful tool for system identification and monitoring.

comment: 18 pages, 16 figures, 4 tables. Published in Journal of Dynamic Systems, Measurement, and Control (ASME), 2026. Licensed under CC BY 4.0

☆ A Comprehensive Corpus of Biomechanically Constrained Piano Chords: Generation, Analysis, and Implications for Voicing and Psychoacoustics

Mahesh Ramani

comment: 10 pages, 3 figures

☆ LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space

Detai Xin, Shujie Hu, Chengzuo Yang, Chen Huang, Guoqiao Yu, Guanglu Wan, Xunliang Cai

comment: Code and model weights are available at https://github.com/meituan-longcat/LongCat-AudioDiT

☆ Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition INTERSPEECH2026

Lukuang Dong, Ziwei Li, Saierdaer Yusuyin, Xianyu Zhao, Zhijian Ou

comment: Update after INTERSPEECH2026 submission

☆ Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation

Ui-Hyeop Shin, Hyung-Min Park

comment: Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing (T-ASLP)

☆ IQRA 2026: Interspeech Challenge on Automatic Assessment Pronunciation for Modern Standard Arabic (MSA)

Yassine El Kheir, Amit Meghanani, Mostafa Shahin, Omnia Ibrahim, Shammur Absar Chowdhury, Nada AlMarwani, Youssef Elshahawy, Ahmed Ali

comment: 5 pages paper

♻ ☆ Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis

Yushen Chen, Junzhe Liu, Yujie Tu, Zhikang Niu, Yuzhe Liang, Chunyu Qiang, Chen Zhang, Kai Yu, Xie Chen

♻ ☆ VAANI: Capturing the language landscape for an inclusive digital India

Sujith Pulikodan, Abhayjeet Singh, Agneedh Basu, Nihar Desai, Pavan Kumar J, Pranav D Bhat, Raghu Dharmaraju, Ritika Gupta, Sathvik Udupa, Saurabh Kumar, Sumit Sharma, Vaibhav Vishwakarma, Visruth Sanka, Dinesh Tewari, Harsh Dhand, Amrita Kamat, Sukhwinder Singh, Shikhar Vashishth, Partha Talukdar, Raj Acharya, Prasanta Kumar Ghosh

Project VAANI is an initiative to create an India-representative multi-modal dataset that comprehensively maps India's linguistic diversity, starting with 165 districts across the country in its first two phases. Speech data is collected through a carefully structured process that uses image-based prompts to encourage spontaneous responses. Images are captured through a separate process that encompasses a broad range of topics, gathered from both within and across districts. The collected data undergoes a rigorous multi-stage quality evaluation, including both automated and manual checks to ensure highest possible standards in audio quality and transcription accuracy. Following this thorough validation, we have open-sourced around 289K images, approximately 31,270 hours of audio recordings, and around 2,067 hours of transcribed speech, encompassing 112 languages from 165 districts from 31 States and Union territories. Notably, significant of these languages are being represented for the first time in a dataset of this scale, making the VAANI project a groundbreaking effort in preserving and promoting linguistic inclusivity. This data can be instrumental in building inclusive speech models for India, and in advancing research and development across speech, image, and multimodal applications.

♻ ☆ EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response

Chenpei Huang, Lingfeng Yao, Kyu In Lee, Lan Emily Zhang, Xun Chen, Miao Pan

Computer Vision and Pattern Recognition 150

☆ OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation

Yuheng Liu, Xin Lin, Xinke Li, Baihan Yang, Chen Wang, Kalyan Sunkavalli, Yannick Hold-Geoffroy, Hao Tan, Kai Zhang, Xiaohui Xie, Zifan Shi, Yiwei Hu

Modeling scenes using video generation models has garnered growing research interest in recent years. However, most existing approaches rely on perspective video models that synthesize only limited observations of a scene, leading to issues of completeness and global consistency. We propose OmniRoam, a controllable panoramic video generation framework that exploits the rich per-frame scene coverage and inherent long-term spatial and temporal consistency of panoramic representation, enabling long-horizon scene wandering. Our framework begins with a preview stage, where a trajectory-controlled video generation model creates a quick overview of the scene from a given input image or video. Then, in the refine stage, this video is temporally extended and spatially upsampled to produce long-range, high-resolution videos, thus enabling high-fidelity world wandering. To train our model, we introduce two panoramic video datasets that incorporate both synthetic and real-world captured videos. Experiments show that our framework consistently outperforms state-of-the-art methods in terms of visual quality, controllability, and long-term scene consistency, both qualitatively and quantitatively. We further showcase several extensions of this framework, including real-time video generation and 3D reconstruction. Code is available at https://github.com/yuhengliu02/OmniRoam.

comment: Code is available at https://github.com/yuhengliu02/OmniRoam

☆ Video Models Reason Early: Exploiting Plan Commitment for Maze Solving

Kaleb Newman, Tyler Zhu, Olga Russakovsky

Video diffusion models exhibit emergent reasoning capabilities like solving mazes and puzzles, yet little is understood about how they reason during generation. We take a first step towards understanding this and study the internal planning dynamics of video models using 2D maze solving as a controlled testbed. Our investigations reveal two findings. Our first finding is early plan commitment: video diffusion models commit to a high-level motion plan within the first few denoising steps, after which further denoising alters visual details but not the underlying trajectory. Our second finding is that path length, not obstacle density, is the dominant predictor of maze difficulty, with a sharp failure threshold at 12 steps. This means video models can only reason over long mazes by chaining together multiple sequential generations. To demonstrate the practical benefits of our findings, we introduce Chaining with Early Planning, or ChEaP, which only spends compute on seeds with promising early plans and chains them together to tackle complex mazes. This improves accuracy from 7% to 67% on long-horizon mazes and by 2.5x overall on hard tasks in Frozen Lake and VR-Bench across Wan2.2-14B and HunyuanVideo-1.5. Our analysis reveals that current video models possess deeper reasoning capabilities than previously recognized, which can be elicited more reliably with better inference-time scaling.

☆ Benchmarking PhD-Level Coding in 3D Geometric Computer Vision

Wenyi Li, Renkai Luo, Yue Yu, Huan-ang Gao, Mingju Gao, Li Yuan, Chaoyou Fu, Hao Zhao

AI-assisted coding has rapidly reshaped software practice and research workflows, yet today's models still struggle to produce correct code for complex 3D geometric vision. If models could reliably write such code, the research of our community would change substantially. To measure progress toward that goal, we introduce GeoCodeBench, a PhD-level benchmark that evaluates coding for 3D vision. Each problem is a fill-in-the-function implementation task curated from representative papers at recent venues: we first let a tool propose candidate functions from official repositories, then perform careful human screening to select core 3D geometric components. For every target, we generate diverse, edge-case unit tests, enabling fully automatic, reproducible scoring. We evaluate eight representative open- and closed-source models to reflect the current ecosystem. The best model, GPT-5, attains only 36.6% pass rate, revealing a large gap between current capabilities and dependable 3D scientific coding. GeoCodeBench organizes tasks into a two-level hierarchy: General 3D capability (geometric transformations and mechanics/optics formulation) and Research capability (novel algorithm implementation and geometric logic routing). Scores are positively correlated across these axes, but research-oriented tasks are markedly harder. Context ablations further show that "more paper text" is not always better: cutting off at the Method section statistically outperforms full-paper inputs, highlighting unresolved challenges in long-context scientific comprehension. Together, these findings position GeoCodeBench as a rigorous testbed for advancing from generic coding to trustworthy 3D geometric vision coding.

comment: Accepted by CVPR 2026; Project page: https://geocodebench.github.io/

☆ Conditional Polarization Guidance for Camouflaged Object Detection

QIfan Zhang, Hao Wang, Xiangrong Qin, Ruijie Li

comment: 11 pages, 10 figures, 4 tables

☆ SurgNavAR: An Augmented Reality Surgical Navigation Framework for Optical See-Through Head Mounted Displays

Abdullah Thabit, Mohamed Benmahdjoub, Rafiuddin Jinabade, Hizirwan S. Salim, Marie-Lise C. van Veelen, Mark G. van Vledder, Eppo B. Wolvius, Theo van Walsum

Augmented reality (AR) devices with head mounted displays (HMDs) facilitate the direct superimposition of 3D preoperative imaging data onto the patient during surgery. To use an HMD-AR device as a stand-alone surgical navigation system, the device should be able to locate the patient and surgical instruments, align preoperative imaging data with the patient, and visualize navigation data in real time during surgery. Whereas some of the technologies required for this are known, integration in such devices is cumbersome and requires specific knowledge and expertise, hampering scientific progress in this field. This work therefore aims to present and evaluate an integrated HMD-based AR surgical navigation framework that is adaptable to diverse surgical applications. The framework tracks 2D patterns as reference markers attached to the patient and surgical instruments. It allows for the calibration of surgical tools using pivot and reference-based calibration techniques. It enables image-to-patient registration using point-based matching and manual positioning. The integrated functionalities of the framework are evaluated on two HMD devices, the HoloLens 2 and Magic Leap 2, with two surgical use cases being evaluated in a phantom setup: AR-guided needle insertion and rib fracture localization. The framework was able to achieve a mean tooltip calibration accuracy of 1 mm, a registration accuracy of 3 mm, and a targeting accuracy below 5 mm on the two surgical use cases. The framework presents an easy-to-use configurable tool for HMD-based AR surgical navigation, which can be extended and adapted to many surgical applications. The framework is publicly available at https://github.com/abdullahthabit/SurgNavAR.

comment: This work has been submitted to the IEEE for possible publication

☆ Trimodal Deep Learning for Glioma Survival Prediction: A Feasibility Study Integrating Histopathology, Gene Expression, and MRI

Iain Swift, JingHua Ye

Multimodal deep learning has improved prognostic accuracy for brain tumours by integrating histopathology and genomic data, yet the contribution of volumetric MRI within unified survival frameworks remains unexplored. This pilot study extends a bimodal framework by incorporating Fluid Attenuated Inversion Recovery (FLAIR) MRI from BraTS2021 as a third modality. Using the TCGA-GBMLGG cohort (664 patients), we evaluate three unimodal models, nine bimodal configurations, and three trimodal configurations across early, late, and joint fusion strategies. In this small cohort setting, trimodal early fusion achieves an exploratory Composite Score (CS = 0.854), with a controlled $Δ$CS of +0.011 over the bimodal baseline on identical patients, though this difference is not statistically significant (p = 0.250, permutation test). MRI achieves reasonable unimodal discrimination (CS = 0.755) but does not substantially improve bimodal pairs, while providing measurable uplift in the three-way combination. All MRI containing experiments are constrained to 19 test patients, yielding wide bootstrap confidence intervals (e.g. [0.400,1.000]) that preclude definitive conclusions. These findings provide preliminary evidence that a third imaging modality may add prognostic value even with limited sample sizes, and that additional modalities require sufficient multimodal context to contribute effectively.

comment: 6 pages, 1 figure, submitted to the IEEE CBMS 2026 conference, still waiting for notification

☆ Learning Structural-Functional Brain Representations through Multi-Scale Adaptive Graph Attention for Cognitive Insight ICASSP 2026

Badhan Mazumder, Sir-Lord Wiafe, Aline Kotoski, Vince D. Calhoun, Dong Hye Ye

Understanding how brain structure and function interact is key to explaining intelligence yet modeling them jointly is challenging as the structural and functional connectome capture complementary aspects of organization. We introduced Multi-scale Adaptive Graph Network (MAGNet), a Transformer-style graph neural network framework that adaptively learns structure-function interactions. MAGNet leverages source-based morphometry from structural MRI to extract inter-regional morphological features and fuses them with functional network connectivity from resting-state fMRI. A hybrid graph integrates direct and indirect pathways, while local-global attention refines connectivity importance and a joint loss simultaneously enforces cross-modal coherence and optimizes the prediction objective end-to-end. On the ABCD dataset, MAGNet outperformed relevant baselines, demonstrating effective multimodal integration for advancing our understanding of cognitive function.

comment: Preprint version of the paper accepted to the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026). This is the author's accepted manuscript. The final published version will appear in IEEE Xplore

☆ Scaling Video Pretraining for Surgical Foundation Models

Sicheng Lu, Zikai Xiao, Jianhui Wei, Danyu Sun, Qi Lu, Keli Hu, Yang Feng, Jian Wu, Zongxin Yang, Zuozhu Liu

Surgical video understanding is essential for computer-assisted interventions, yet existing surgical foundation models remain constrained by limited data scale, procedural diversity, and inconsistent evaluation, often lacking a reproducible training pipeline. We propose SurgRec, a scalable and reproducible pretraining recipe for surgical video understanding, instantiated with two variants: SurgRec-MAE and SurgRec-JEPA. We curate a large multi-source corpus of 10,535 videos and 214.5M frames spanning endoscopy, laparoscopy, cataract, and robotic surgery. Building on this corpus, we develop a unified pretraining pipeline with balanced sampling and standardize a reproducible benchmark across 16 downstream datasets and four clinical domains with consistent data splits. Across extensive comparisons against SSL baselines and vision-language models, SurgRec consistently achieves superior performance across downstream datasets. In contrast, VLMs prove unreliable for fine-grained temporal recognition, exhibiting both performance gaps and sensitivity to prompt phrasing. Our work provides a reproducible, scalable foundation for the community to build more general surgical video models. All code, models, and data will be publicly released.

☆ SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy

Shi Li, Vinkle Srivastav, Nicolas Chanel, Saurav Sharma, Nabani Banik, Lorenzo Arboit, Kun Yuan, Pietro Mascagni, Nicolas Padoy

comment: 29 pages, 14 figures, 9 tables

☆ NeuroBRIDGE: Behavior-Conditioned Koopman Dynamics with Riemannian Alignment for Early Substance Use Initiation Prediction from Longitudinal Functional Connectome ICASSP 2026

Badhan Mazumder, Sir-Lord Wiafe, Vince D. Calhoun, Dong Hye Ye

Early identification of adolescents at risk for substance use initiation (SUI) is vital yet difficult, as most predictors treat connectivity as static or cross-sectional and miss how brain networks change over time and with behavior. We proposed NeuroBRIDGE (Behavior conditioned RIemannian Koopman Dynamics on lonGitudinal connEctomes), a novel graph neural network-based framework that aligns longitudinal functional connectome in a Riemannian tangent space and couples dual-time attention with behavioral-conditioned Koopman dynamics to capture temporal change. Evaluated on ABCD, NeuroBRIDGE improved future SUI prediction over relevant baselines while offering interpretable insights into neural pathways, refining our understanding of neurodevelopmental risk and informing targeted prevention.

☆ Detecting Unknown Objects via Energy-based Separation for Open World Object Detection

Jun-Woo Heo, Keonhee Park, Gyeong-Moon Park

In this work, we tackle the problem of Open World Object Detection (OWOD). This challenging scenario requires the detector to incrementally learn to classify known objects without forgetting while identifying unknown objects without supervision. Previous OWOD methods have enhanced the unknown discovery process and employed memory replay to mitigate catastrophic forgetting. However, since existing methods heavily rely on the detector's known class predictions for detecting unknown objects, they struggle to effectively learn and recognize unknown object representations. Moreover, while memory replay mitigates forgetting of old classes, it often sacrifices the knowledge of newly learned classes. To resolve these limitations, we propose DEUS (Detecting Unknowns via energy-based Separation), a novel framework that addresses the challenges of Open World Object Detection. DEUS consists of Equiangular Tight Frame (ETF)-Subspace Unknown Separation (EUS) and an Energy-based Known Distinction (EKD) loss. EUS leverages ETF-based geometric properties to create orthogonal subspaces, enabling cleaner separation between known and unknown object representations. Unlike prior energy-based approaches that consider only the known space, EUS utilizes energies from both spaces to better capture distinct patterns of unknown objects. Furthermore, EKD loss enforces the separation between previous and current classifiers, thus minimizing knowledge interference between previous and newly learned classes during memory replay. We thoroughly validate DEUS on OWOD benchmarks, demonstrating outstanding performance improvements in unknown detection while maintaining competitive known class performance.

comment: 8 pages, Accepted at CVPR 2026

☆ EC-Bench: Enumeration and Counting Benchmark for Ultra-Long Videos

Fumihiko Tsuchiya, Taiki Miyanishi, Mahiro Ukai, Nakamasa Inoue, Shuhei Kurita, Yusuke Iwasawa, Yutaka Matsuo

Counting in long videos remains a fundamental yet underexplored challenge in computer vision. Real-world recordings often span tens of minutes or longer and contain sparse, diverse events, making long-range temporal reasoning particularly difficult. However, most existing video counting benchmarks focus on short clips and evaluate only the final numerical answer, providing little insight into what should be counted or whether models consistently identify relevant instances across time. We introduce EC-Bench, a benchmark that jointly evaluates enumeration, counting, and temporal evidence grounding in long-form videos. EC-Bench contains 152 videos longer than 30 minutes and 1,699 queries paired with explicit evidence spans. Across 22 multimodal large language models (MLLMs), the best model achieves only 29.98% accuracy on Enumeration and 23.74% on Counting, while human performance reaches 78.57% and 82.97%, respectively. Our analysis reveals strong relationships between enumeration accuracy, temporal grounding, and counting performance. These results highlight fundamental limitations of current MLLMs and establish EC-Bench as a challenging benchmark for long-form quantitative video reasoning.

comment: The first two authors are equally contributed. The data and code are publicly available at: https://github.com/matsuolab/EC-Bench

☆ Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance

Vanessa Emanuela Guarino, Claudia Winklmayr, Jannik Franzen, Josef Lorenz Rumberger, Manuel Pfeuffer, Sonja Greven, Klaus Maier-Hein, Carsten T. Lüth, Christoph Karg, Dagmar Kainmueller

Uncertainty Quantification (UQ) is crucial for ensuring the reliability of automated image segmentations in safety-critical domains like biomedical image analysis or autonomous driving. In segmentation, UQ generates pixel-wise uncertainty scores that must be aggregated into image-level scores for downstream tasks like Out-of-Distribution (OoD) or failure detection. Despite routine use of aggregation strategies, their properties and impact on downstream task performance have not yet been comprehensively studied. Global Average is the default choice, yet it does not account for spatial and structural features of segmentation uncertainty. Alternatives like patch-, class- and threshold-based strategies exist, but lack systematic comparison, leading to inconsistent reporting and unclear best practices. We address this gap by (1) formally analyzing properties, limitations, and pitfalls of common strategies; (2) proposing novel strategies that incorporate spatial uncertainty structure and (3) benchmarking their performance on OoD and failure detection across ten datasets that vary in image geometry and structure. We find that aggregators leveraging spatial structure yield stronger performance in both downstream tasks studied. However, the performance of individual aggregators depends heavily on dataset characteristics, so we (4) propose a meta-aggregator that integrates multiple aggregators and performs robustly across datasets.

comment: 27 pages, 13 figures, 6 tables. Accepted at CVPR 2026 (The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026)

☆ Gloria: Consistent Character Video Generation via Content Anchors

Yuhang Yang, Fan Zhang, Huaijin Pi, Shuai Guo, Guowei Xu, Wei Zhai, Yang Cao, Zheng-Jun Zha

Digital characters are central to modern media, yet generating character videos with long-duration, consistent multi-view appearance and expressive identity remains challenging. Existing approaches either provide insufficient context to preserve identity or leverage non-character-centric information as the memory, leading to suboptimal consistency. Recognizing that character video generation inherently resembles an outside-looking-in scenario. In this work, we propose representing the character visual attributes through a compact set of anchor frames. This design provides stable references for consistency, while reference-based video generation inherently faces challenges of copy-pasting and multi-reference conflicts. To address these, we introduce two mechanisms: Superset Content Anchoring, providing intra- and extra-training clip cues to prevent duplication, and RoPE as Weak Condition, encoding positional offsets to distinguish multiple anchors. Furthermore, we construct a scalable pipeline to extract these anchors from massive videos. Experiments show our method generates high-quality character videos exceeding 10 minutes, and achieves expressive identity and appearance consistency across views, surpassing existing methods.

comment: Accepted by CVPR2026 Main, project: https://yyvhang.github.io/Gloria_Page/

☆ End-to-End Image Compression with Segmentation Guided Dual Coding for Wind Turbines

Raül Pérez-Gonzalo, Andreas Espersen, Søren Forchhammer, Antonio Agudo

Transferring large volumes of high-resolution images during wind turbine inspections introduces a bottleneck in assessing and detecting severe defects. Efficient coding must preserve high fidelity in blade regions while aggressively compressing the background. In this work, we propose an end-to-end deep learning framework that jointly performs segmentation and dual-mode (lossy and lossless) compression. The segmentation module accurately identifies the blade region, after which our region-of-interest (ROI) compressor encodes it at superior quality compared to the rest of the image. Unlike conventional ROI schemes that merely allocate more bits to salient areas, our framework integrates: (i) a robust segmentation network (BU-Netv2+P) with a CRF-regularized loss for precise blade localization, (ii) a hyperprior-based autoencoder optimized for lossy compression, and (iii) an extended bits-back coder with hierarchical models for fully lossless blade reconstruction. Furthermore, our ROI framework removes the sequential dependency in bits-back coding by reusing background-coded bits, enabling parallelized and efficient dual-mode compression. To the best of our knowledge, this is the first fully integrated learning-based ROI codec combining segmentation, lossy, and lossless compression, ensuring that subsequent defect detection is not compromised. Experiments on a large-scale wind turbine dataset demonstrate superior compression performance and efficiency, offering a practical solution for automated inspections.

comment: Accepted to TNNLS 2026

☆ Abstraction in Style

Min Lu, Yuanfeng He, Anthony Chen, Jianhuang He, Pu Wang, Daniel Cohen-Or, Hui Huang

Artistic styles often embed abstraction beyond surface appearance, involving deliberate reinterpretation of structure rather than mere changes in texture or color. Conventional style transfer methods typically preserve the input geometry and therefore struggle to capture this deeper abstraction behavior, especially for illustrative and nonphotorealistic styles. In this work, we introduce Abstraction in Style (AiS), a generative framework that separates structural abstraction from visual stylization. Given a target image and a small set of style exemplars, AiS first derives an intermediate abstraction proxy that reinterprets the target's structure in accordance with the abstraction logic exhibited by the style. The proxy captures semantic structure while relaxing geometric fidelity, enabling subsequent stylization to operate on an abstracted representation rather than the original image. In a second stage, the abstraction proxy is rendered to produce the final stylized output, preserving visual coherence with the reference style. Both stages are implemented using a shared image space analogy, enabling transformations to be learned from visual exemplars without explicit geometric supervision. By decoupling abstraction from appearance and treating abstraction as an explicit, transferable process, AiS supports a wider range of stylistic transformations, improves controllability, and enables more expressive stylization.

comment: siggraph 2026 conditionally accepted paper

☆ Training deep learning based dynamic MR image reconstruction using synthetic fractals

Anirudh Raman, Olivier Jaubert, Mark Wrobel, Tina Yao, Ruaraidh Campbell, Rebecca Baker, Ruta Virsinskaite, Daniel Knight, Michael Quail, Jennifer Steeden, Vivek Muthurangu

Purpose: To investigate whether synthetically generated fractal data can be used to train deep learning (DL) models for dynamic MRI reconstruction, thereby avoiding the privacy, licensing, and availability limitations associated with cardiac MR training datasets. Methods: A training dataset was generated using quaternion Julia fractals to produce 2D+time images. Multi-coil MRI acquisition was simulated to generate paired fully sampled and radially undersampled k-space data. A 3D UNet deep artefact suppression model was trained using these fractal data (F-DL) and compared with an identical model trained on cardiac MRI data (CMR-DL). Both models were evaluated on prospectively acquired radial real-time cardiac MRI from 10 patients. Reconstructions were compared against compressed sensing(CS) and low-rank deep image prior (LR-DIP). All reconstrctuions were ranked for image quality, while ventricular volumes and ejection fraction were compared with reference breath-hold cine MRI. Results: There was no significant difference in qualitative ranking between F-DL and CMR-DL (p=0.9), while both outperformed CS and LR-DIP (p<0.001). Ventricular volumes and function derived from F-DL were similar to CMR-DL, showing no significant bias and accptable limits of agreement compared to reference cine imaging. However, LR-DIP had a signifcant bias (p=0.016) and wider lmits of agreement. Conclusion: DL models trained using synthetic fractal data can reconstruct real-time cardiac MRI with image quality and clinical measurements comparable to models trained on true cardiac MRI data. Fractal training data provide an open, scalable alternative to clinical datasets and may enable development of more generalisable DL reconstruction models for dynamic MRI.

☆ Diffusion-Based Feature Denoising with NNMF for Robust handwritten digit multi-class classification

Hiba Adil Al-kharsan, Róbert Rajkó

This work presents a robust multi-class classification framework for handwritten digits that combines diffusion-driven feature denoising with a hybrid feature representation. Inspired by our previous work on brain tumor classification, the proposed approach operates in a feature space to improve the robustness to noise and adversarial attacks. First, the input images are converted into tight, interpretable exemplification using Nonnegative Matrix Factorization (NNMF). In parallel, special deep features are extracted using a computational neural network (CNN). These integral features are combined into a united hybrid representation. To improve robustness, a step diffusion operation is used in the feature space by gradually adding Gaussian noise. A feature denoiser network is trained to reverse this operation and rebuild clean representations from tilted inputs. The courteous features are then applied for multi-class classification. The suggested method is evaluated in both baseline and adversarial settings using AutoAttack. The experimental outcome present that the diffusion-based hybrid model is both effective and robust, the CNN baseline models outperforming while maintain powerful classification performance. These results explain the activity of feature-level diffusion defense for reliable multi-class handwritten digit classification.

☆ Less Is More? Selective Visual Attention to High-Importance Regions for Multimodal Radiology Summarization

Mst. Fahmida Sultana Naznin, Adnan Ibney Faruq, Mushfiqur Rahman, Niloy Kumar Mondal, Md. Mehedi Hasan Shawon, Md Rakibul Hasan

Automated radiology report summarization aims to distill verbose findings into concise clinical impressions, but existing multimodal models often struggle with visual noise and fail to meaningfully improve over strong text-only baselines in the FINDINGS $\to$ IMPRESSION transformation. We challenge two prevailing assumptions: (1) that more visual input is always better, and (2) that multimodal models add limited value when findings already contain rich image-derived detail. Through controlled ablations on MIMIC-CXR benchmark, we show that selectively focusing on pathology-relevant visual patches rather than full images yields substantially better performance. We introduce ViTAS, Visual-Text Attention Summarizer, a multi-stage pipeline that combines ensemble-guided MedSAM2 lung segmentation, bidirectional cross-attention for multi-view fusion, Shapley-guided adaptive patch clustering, and hierarchical visual tokenization feeding a ViT. ViTAS achieves SOTA results with 29.25% BLEU-4 and 69.83% ROUGE-L, improved factual alignment in qualitative analysis, and the highest expert-rated human evaluation scores. Our findings demonstrate that less but more relevant visual input is not only sufficient but superior for multimodal radiology summarization.

☆ DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA

Yi Chen, Yuying Ge, Hui Zhou, Mingyu Ding, Yixiao Ge, Xihui Liu

The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping vision-language features to low-level actions. This paradigm underutilizes the VLM's potential in high-level decision making and introduces training instability, frequently degrading its rich semantic representations. To address these limitations, we introduce DIAL, a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck. Specifically, a VLM-based System-2 performs latent world modeling by synthesizing latent visual foresight within the VLM's native feature space; this foresight explicitly encodes intent and serves as the structural bottleneck. A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions via latent inverse dynamics. To ensure optimization stability, we employ a two-stage training paradigm: a decoupled warmup phase where System-2 learns to predict latent futures while System-1 learns motor control under ground-truth future guidance within a unified feature space, followed by seamless end-to-end joint optimization. This enables action-aware gradients to refine the VLM backbone in a controlled manner, preserving pre-trained knowledge. Extensive experiments on the RoboCasa GR1 Tabletop benchmark show that DIAL establishes a new state-of-the-art, achieving superior performance with 10x fewer demonstrations than prior methods. Furthermore, by leveraging heterogeneous human demonstrations, DIAL learns physically grounded manipulation priors and exhibits robust zero-shot generalization to unseen objects and novel configurations during real-world deployment on a humanoid robot.

comment: Project page: https://xpeng-robotics.github.io/dial

☆ Toward Generalizable Whole Brain Representations with High-Resolution Light-Sheet Data

Minyoung E. Kim, Dae Hee Yun, Aditi V. Patel, Madeline Hon, Webster Guan, Taegeon Lee, Brian Nguyen

Unprecedented visual details of biological structures are being revealed by subcellular-resolution whole-brain 3D microscopy data, enabled by recent advances in intact tissue processing and light-sheet fluorescence microscopy (LSFM). These volumetric data offer rich morphological and spatial cellular information, however, the lack of scalable data processing and analysis methods tailored to these petabyte-scale data poses a substantial challenge for accurate interpretation. Further, existing models for visual tasks such as object detection and classification struggle to generalize to this type of data. To accelerate the development of suitable methods and foundational models, we present CANVAS, a comprehensive set of high-resolution whole mouse brain LSFM benchmark data, encompassing six neuronal and immune cell-type markers, along with cell annotations and a leaderboard. We also demonstrate challenges in generalization of baseline models built on existing architectures, especially due to the heterogeneity in cellular morphology across phenotypes and anatomical locations in the brain. To the best of our knowledge, CANVAS is the first and largest LSFM benchmark that captures intact mouse brain tissue at subcellular level, and includes extensive annotations of cells throughout the brain.

comment: 21 pages, 12 figures. Accepted at CVPR 2026

☆ AutoFormBench: Benchmark Dataset for Automating Form Understanding

Gaurab Baral, Junxiu Zhou

Automated processing of structured documents such as government forms, healthcare records, and enterprise invoices remains a persistent challenge due to the high degree of layout variability encountered in real-world settings. This paper introduces AutoFormBench, a benchmark dataset of 407 annotated real-world forms spanning government, healthcare, and enterprise domains, designed to train and evaluate form element detection models. We present a systematic comparison of classical OpenCV approaches and four YOLO architectures (YOLOv8, YOLOv11, YOLOv26-s, and YOLOv26-l) for localizing and classifying fillable form elements. specifically checkboxes, input lines, and text boxes across diverse PDF document types. YOLOv11 demonstrates consistently superior performance in both F1 score and Jaccard accuracy across all element classes and tolerance levels.

comment: 9 pages, 3 figures, 2 tables

☆ SceneTeract: Agentic Functional Affordances and VLM Grounding in 3D Scenes

Léopold Maillard, Francis Engelmann, Tom Durand, Boxiao Pan, Yang You, Or Litany, Leonidas Guibas, Maks Ovsjanikov

Embodied AI depends on interactive 3D environments that support meaningful activities for diverse users, yet assessing their functional affordances remains a core challenge. We introduce SceneTeract, a framework that verifies 3D scene functionality under agent-specific constraints. Our core contribution is a grounded verification engine that couples high-level semantic reasoning with low-level geometric checks. SceneTeract decomposes complex activities into sequences of atomic actions and validates each step against accessibility requirements (e.g., reachability, clearance, and navigability) conditioned on an embodied agent profile, using explicit physical and geometric simulations. We deploy SceneTeract to perform an in-depth evaluation of (i) synthetic indoor environments, uncovering frequent functional failures that prevent basic interactions, and (ii) the ability of frontier Vision-Language Models (VLMs) to reason about and predict functional affordances, revealing systematic mismatches between semantic confidence and physical feasibility even for the strongest current models. Finally, we leverage SceneTeract as a reward engine for VLM post-training, enabling scalable distillation of geometric constraints into reasoning models. We release the SceneTeract verification suite and data to bridge perception and physical reality in embodied 3D scene understanding.

comment: Project page: https://sceneteract.github.io/

☆ Multi-Feature Fusion Approach for Generative AI Images Detection

Abderrezzaq Sendjasni, Mohamed-Chaker Larabi

The rapid evolution of Generative AI (GenAI) models has led to synthetic images of unprecedented realism, challenging traditional methods for distinguishing them from natural photographs. While existing detectors often rely on single-feature spaces, such as statistical regularities, semantic embeddings, or texture patterns, these approaches tend to lack robustness when confronted with diverse and evolving generative models. In this work, we investigate and systematically evaluate a multi-feature fusion framework that combines complementary cues from three distinct spaces: (1) Mean Subtracted Contrast Normalized (MSCN) features capturing low-level statistical deviations; (2) CLIP embeddings encoding high-level semantic coherence; and (3) Multi-scale Local Binary Patterns (MLBP) characterizing mid-level texture anomalies. Through extensive experiments on four benchmark datasets covering a wide range of generative models, we show that individual feature spaces exhibit significant performance variability across different generators. Crucially, the fusion of all three representations yields superior and more consistent performance, particularly in a challenging mixed-model scenario. Compared to state-of-the-art methods, the proposed framework yields consistently improved performance across all evaluated datasets. Overall, this work highlights the importance of hybrid representations for robust GenAI image detection and provides a principled framework for integrating complementary visual cues.

comment: This work has been submitted to IEEE Transactions for possible publication

☆ MAPLE: Multi-Path Adaptive Propagation with Level-Aware Embeddings for Hierarchical Multi-Label Image Classification

Boshko Koloski, Marjan Stoimchev, Jurica Levatić, Dragi Kocev, Sašo Džeroski

Hierarchical multi-label classification (HMLC) is essential for modeling structured label dependencies in remote sensing. Yet existing approaches struggle in multi-path settings, where images may activate multiple taxonomic branches, leading to underuse of hierarchical information. We propose MAPLE (Multi-Path Adaptive Propagation with Level-Aware Embeddings), a framework that integrates (i) hierarchical semantic initialization from graph-aware textual descriptions, (ii) graph-based structure encoding via graph convolutional networks (GCNs), and (iii) adaptive multi-modal fusion that dynamically balances semantic priors and visual evidence. An adaptive level-aware objective automatically selects appropriate losses per hierarchy level. Evaluations on CORINE-aligned remote sensing datasets (AID, DFC-15, and MLRSNet) show consistent improvements of up to +42% in few-shot regimes while adding only 2.6% parameter overhead, demonstrating that MAPLE effectively and efficiently models hierarchical semantics for Earth observation (EO).

comment: REO: Advances in Representation Learning for Earth Observation, accepted workshow paper at EurIPS

☆ From Skeletons to Semantics: Design and Deployment of a Hybrid Edge-Based Action Detection System for Public Safety

Ganen Sethupathy, Lalit Dumka, Jan Schagen

Public spaces such as transport hubs, city centres, and event venues require timely and reliable detection of potentially violent behaviour to support public safety. While automated video analysis has made significant progress, practical deployment remains constrained by latency, privacy, and resource limitations, particularly under edge-computing conditions. This paper presents the design and demonstrator-based deployment of a hybrid edge-based action detection system that combines skeleton-based motion analysis with vision-language models for semantic scene interpretation. Skeleton-based processing enables continuous, privacy-aware monitoring with low computational overhead, while vision-language models provide contextual understanding and zero-shot reasoning capabilities for complex and previously unseen situations. Rather than proposing new recognition models, the contribution focuses on a system-level comparison of both paradigms under realistic edge constraints. The system is implemented on a GPU-enabled edge device and evaluated with respect to latency, resource usage, and operational trade-offs using a demonstrator-based setup. The results highlight the complementary strengths and limitations of motioncentric and semantic approaches and motivate a hybrid architecture that selectively augments fast skeletonbased detection with higher-level semantic reasoning. The presented system provides a practical foundation for privacy-aware, real-time video analysis in public safety applications.

comment: Preprint version of a manuscript currently under review at IEEE Access

☆ Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration

Fengyang Xiao, Peng Hu, Lei Xu, XingE Guo, Guanyi Qin, Yuqi Shen, Chengyu Fang, Rihan Zhang, Chunming He, Sina Farsiu

Real-world image restoration aims to restore high-quality (HQ) images from degraded low-quality (LQ) inputs captured under uncontrolled conditions. Existing methods typically depend on ground-truth (GT) supervision, assuming that GT provides perfect reference quality. However, GT can still contain images with inconsistent perceptual fidelity, causing models to converge to the average quality level of the training data rather than achieving the highest perceptual quality attainable. To address these problems, we propose a novel framework, termed IQPIR, that introduces an Image Quality Prior (IQP)-extracted from pre-trained No-Reference Image Quality Assessment (NR-IQA) models-to guide the restoration process toward perceptually optimal outputs explicitly. Our approach synergistically integrates IQP with a learned codebook prior through three key mechanisms: (1) a quality-conditioned Transformer, where NR-IQA-derived scores serve as conditioning signals to steer the predicted representation toward maximal perceptual quality. This design provides a plug-and-play enhancement compatible with existing restoration architectures without structural modification; and (2) a dual-branch codebook structure, which disentangles common and HQ-specific features, ensuring a comprehensive representation of both generic structural information and quality-sensitive attributes; and (3) a discrete representation-based quality optimization strategy, which mitigates over-optimization effects commonly observed in continuous latent spaces. Extensive experiments on real-world image restoration demonstrate that our method not only surpasses cutting-edge methods but also serves as a generalizable quality-guided enhancement strategy for existing methods. The code is available.

comment: Accepted by CVPR

☆ TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios

Qiucheng Yu, Ruijie Xu, Mingang Chen, Xuequan Lu, Jianfeng Dong, Chaochao Lu, Xin Tan

Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment. However, existing benchmarks suffer from three fundamental limitations: (1) heavy reliance on synthetic datasets constructed via simulation software, creating a significant domain gap with real-world environments; (2) oversimplified safety tasks with artificial constraints on hazard and scene types, thereby limiting model generalization; and (3) absence of rigorous evaluation protocols to thoroughly assess model capabilities in complex home safety scenarios. To address these challenges, we introduce TSHA (\textbf{T}rustworthy \textbf{S}afety \textbf{H}azards \textbf{A}ssessment), a comprehensive benchmark comprising 81,809 carefully curated training samples drawn from four complementary sources: existing indoor datasets, internet images, AIGC images, and newly captured images. This benchmark set also includes a highly challenging test set with 1707 samples, comprising not only a carefully selected subset from the training distribution but also newly added videos and panoramic images containing multiple safety hazards, used to evaluate the model's robustness in complex safety scenarios. Extensive experiments on 23 popular VLMs demonstrate that current VLMs lack robust capabilities for safety hazard assessment. Importantly, models trained on the TSHA training set not only achieve a significant performance improvement of up to +18.3 points on the TSHA test set but also exhibit enhanced generalizability across other benchmarks, underscoring the substantial contribution and importance of the TSHA benchmark.

☆ SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark

Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Yang Song, Jiaojiao Jiang

☆ GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis

Thomas Tanay, Mohammed Brahimi, Michal Nazarczuk, Qingwen Zhang, Sibi Catley-Chandar, Arthur Moreau, Zhensong Zhang, Eduardo Pérez-Pellitero

Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view information is hard to exploit. Diffusion-based approaches that integrate camera control into large pre-trained models can produce visually plausible videos but frequently suffer from geometric inconsistencies across both static and dynamic areas. Both families of methods also require substantial computational resources. Building on the success of generalizable models for static novel view synthesis, we adapt the framework to dynamic inputs and propose a new model with two key components: (1) a recurrent loop that enables unbounded and asynchronous mapping between input and target videos and (2) an efficient use of plane sweeps over dynamic inputs to disentangle camera and scene motion, and achieve fine-grained, six-degrees-of-freedom camera controls. We train and evaluate our model on the UCSD dataset and on Kubric-4D-dyn, a new monocular dynamic dataset featuring longer, higher resolution sequences with more complex scene dynamics than existing alternatives. Our model outperforms four Gaussian Splatting-based scene-specific approaches, as well as two diffusion-based approaches in reconstructing fine-grained geometric details across both static and dynamic regions.

comment: CVPR Findings 2026

☆ Leveraging Synthetic Data for Enhancing Egocentric Hand-Object Interaction Detection

Rosario Leonardi, Antonino Furnari, Francesco Ragusa, Giovanni Maria Farinella

In this work, we explore the role of synthetic data in improving the detection of Hand-Object Interactions from egocentric images. Through extensive experimentation and comparative analysis on VISOR, EgoHOS, and ENIGMA-51 datasets, our findings demonstrate the potential of synthetic data to significantly improve HOI detection, particularly when real labeled data are scarce or unavailable. By using synthetic data and only 10% of the real labeled data, we achieve improvements in Overall AP over models trained exclusively on real data, with gains of +5.67% on VISOR, +8.24% on EgoHOS, and +11.69% on ENIGMA-51. Furthermore, we systematically study how aligning synthetic data to specific real-world benchmarks with respect to objects, grasps, and environments, showing that the effectiveness of synthetic data consistently improves with better synthetic-real alignment. As a result of this work, we release a new data generation pipeline and the new HOI-Synth benchmark, which augments existing datasets with synthetic images of hand-object interaction. These data are automatically annotated with hand-object contact states, bounding boxes, and pixel-wise segmentation masks. All data, code, and tools for synthetic data generation are available at: https://fpv-iplab.github.io/HOI-Synth/.

☆ Compressive sensing inspired self-supervised single-pixel imaging

Jijun Lu, Yifan Chen, Libang Chen, Yiqiang Zhou, Ye Zheng, Mingliang Chen, Zhe Sun, Xuelong Li

Single-pixel imaging (SPI) is a promising imaging modality with distinctive advantages in strongly perturbed environments. Existing SPI methods lack physical sparsity constraints and overlook the integration of local and global features, leading to severe noise vulnerability, structural distortions and blurred details. To address these limitations, we propose SISTA-Net, a compressive sensing-inspired self-supervised method for single-pixel imaging. SISTA-Net unfolds the Iterative Shrinkage-Thresholding Algorithm (ISTA) into an interpretable network consisting of a data fidelity module and a proximal mapping module. The fidelity module adopts a hybrid CNN-Visual State Space Model (VSSM) architecture to integrate local and global feature modeling, enhancing reconstruction integrity and fidelity. We leverage deep nonlinear networks as adaptive sparse transforms combined with a learnable soft-thresholding operator to impose explicit physical sparsity in the latent domain, enabling noise suppression and robustness to interference even at extremely low sampling rates. Extensive experiments on multiple simulation scenarios demonstrate that SISTA-Net outperforms state-of-the-art methods by 2.6 dB in PSNR. Real-world far-field underwater tests yield a 3.4 dB average PSNR improvement, validating its robust anti-interference capability.

comment: 10 pages, 9 figures, 2 algorithms, 2 tables, journal paper

☆ FED-Bench: A Cross-Granular Benchmark for Disentangled Evaluation of Facial Expression Editing

Fengjian Xue, Xuecheng Wu, Heli Sun, Yunyun Shi, Shi Chen, Liangyu Fu, Jinheng Xie, Dingkang Yang, Hao Wang, Junxiao Xue, Liang He

Facial expression image editing requires fine-grained control to strictly preserve human identity and background while precisely manipulating expression. However, existing editing benchmarks primarily focus on general scenarios, lacking high-quality facial images and corresponding editing instructions. Furthermore, current evaluation metrics exhibit systemic biases in this task, often favoring lazy editing or overfit editing. To bridge these gaps, we propose FED-Bench, a comprehensive benchmark featuring rigorous testing and an accurate evaluation suite. First, we carefully construct a benchmark of 747 triplets through a cascaded and scalable pipeline, each comprising an original image, an editing instruction, and a ground-truth image for precise evaluation. Second, we introduce FED-Score, a cross-granularity evaluation protocol that disentangles assessment into three dimensions: Alignment for verifying instruction following, Fidelity for testing image quality and identity preservation, and Relative Expression Gain for quantifying the magnitude of expression changes, effectively mitigating the aforementioned evaluation biases. Third, we benchmark 18 image editing models, revealing that current approaches struggle to simultaneously achieve high fidelity and accurate expression manipulation, with fine-grained instruction following identified as the primary bottleneck. Finally, leveraging the scalable characteristic of introduced benchmark engine, we provide a 20k+ in-the-wild facial training set and demonstrate its effectiveness by fine-tuning a baseline model that achieves significant performance gains. Our benchmark and related code will be made publicly open soon.

☆ Exploring the Impact of Skin Color on Skin Lesion Segmentation

Kuniko Paxton, Medina Kapo, Amila Akagić, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos

Skin cancer, particularly melanoma, remains a major cause of morbidity and mortality, making early detection critical. AI-driven dermatology systems often rely on skin lesion segmentation as a preprocessing step to delineate the lesion from surrounding skin and support downstream analysis. While fairness concerns regarding skin tone have been widely studied for lesion classification, the influence of skin tone on the segmentation stage remains under-quantified and is frequently assessed using coarse, discrete skin tone categories. In this work, we evaluate three strong segmentation architectures (UNet, DeepLabV3 with a ResNet50 backbone, and DINOv2) on two public dermoscopic datasets (HAM10000 and ISIC2017) and introduce a continuous pigment or contrast analysis that treats pixel-wise ITA values as distributions. Using Wasserstein distances between within-image distributions for skin-only, lesion-only, and whole-image regions, we quantify lesion skin contrast and relate it to segmentation performance across multiple metrics. Within the range represented in these datasets, global skin tone metrics (Fitzpatrick grouping or mean ITA) show weak association with segmentation quality. In contrast, low lesion-skin contrast is consistently associated with larger segmentation errors in models, indicating that boundary ambiguity and low contrast are key drivers of failure. These findings suggest that fairness improvements in dermoscopic segmentation should prioritize robust handling of low-contrast lesions, and the distribution-based pigment measures provide a more informative audit signal than discrete skin-tone categories.

☆ SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition

Ning Wang, Tieyue Wu, Naeha Sharif, Farid Boussaid, Guangming Zhu, Lin Mei, Mohammed Bennamoun, zhang liang

Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typically align skeleton features with textual embeddings within a shared latent space. However, the absence of contextual cues, such as objects involved in the action, introduces an inherent gap between skeleton and semantic representations, making it difficult to distinguish visually similar actions. To address this, we propose SkeletonContext, a prompt-based framework that enriches skeletal motion representations with language-driven contextual semantics. Specifically, we introduce a Cross-Modal Context Prompt Module, which leverages a pretrained language model to reconstruct masked contextual prompts under guidance derived from LLMs. This design effectively transfers linguistic context to the skeleton encoder for instance-level semantic grounding and improved cross-modal alignment. In addition, a Key-Part Decoupling Module is incorporated to decouple motion-relevant joint features, ensuring robust action understanding even in the absence of explicit object interactions. Extensive experiments on multiple benchmarks demonstrate that SkeletonContext achieves state-of-the-art performance under both conventional and generalized zero-shot settings, validating its effectiveness in reasoning about context and distinguishing fine-grained, visually similar actions.

comment: Accepted by CVPR 2026

☆ A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models ICLR 2026

Lixin Xiu, Xufang Luo, Hideki Nakayama

Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or from reliance on unimodal priors. To address this attribution gap, we introduce a novel framework using partial information decomposition (PID) to quantitatively measure the "information spectrum" of LVLMs -- decomposing a model's decision-relevant information into redundant, unique, and synergistic components. By adapting a scalable estimator to modern LVLM outputs, our model-agnostic pipeline profiles 26 LVLMs on four datasets across three dimensions -- breadth (cross-model & cross-task), depth (layer-wise information dynamics), and time (learning dynamics across training). Our analysis reveals two key results: (i) two task regimes (synergy-driven vs. knowledge-driven) and (ii) two stable, contrasting family-level strategies (fusion-centric vs. language-centric). We also uncover a consistent three-phase pattern in layer-wise processing and identify visual instruction tuning as the key stage where fusion is learned. Together, these contributions provide a quantitative lens beyond accuracy-only evaluation and offer insights for analyzing and designing the next generation of LVLMs. Code and data are available at https://github.com/RiiShin/pid-lvlm-analysis .

comment: Accepted at ICLR 2026. Project page: https://riishin.github.io/pid-lvlm-iclr26/

☆ Clinical DVH metrics as a loss function for 3D dose prediction in head and neck radiotherapy

Ruochen Gao, Marius Staring, Frank Dankers

Purpose: Deep-learning-based three-dimensional (3D) dose prediction is widely used in automated radiotherapy workflows. However, most existing models are trained with voxel-wise regression losses, which are poorly aligned with clinical plan evaluation criteria based on dose-volume histogram (DVH) metrics. This study aims to develop a clinically guided loss formulation that directly optimizes clinically used DVH metrics while remaining computationally efficient for head and neck (H\&N) dose prediction. Methods: We propose a clinical DVH metric loss (CDM loss) that incorporates differentiable \textit{D-metrics} and surrogate \textit{V-metrics}, together with a lossless bit-mask region-of-interest (ROI) encoding to improve training efficiency. The method was evaluated on 174 H\&N patients using a temporal split (137 training, 37 testing). Results: Compared with MAE- and DVH-curve based losses, CDM loss substantially improved target coverage and satisfied all clinical constraints. Using a standard 3D U-Net, the PTV Score was reduced from 1.544 (MAE) to 0.491 (MAE + CDM), while OAR sparing remained comparable. Bit-mask encoding reduced training time by 83\% and lowered GPU memory usage. Conclusion: Directly optimizing clinically used DVH metrics enables 3D dose predictions that are better aligned with clinical treatment planning criteria than conventional voxel-wise or DVH-curve-based supervision. The proposed CDM loss, combined with efficient ROI bit-mask encoding, provides a practical and scalable framework for H\&N dose prediction.

comment: 19 pages

☆ CoRe-DA: Contrastive Regression for Unsupervised Domain Adaptation in Surgical Skill Assessment

Dimitrios Anastasiou, Razvan Caramalau, Jialang Xu, Runlong He, Freweini Tesfai, Matthew Boal, Nader Francis, Danail Stoyanov, Evangelos B. Mazomenos

Vision-based surgical skill assessment (SSA) enables objective and scalable evaluation of operative performance. Progress in this field is constrained by the high cost and time demands for manual annotation of quantitative skill scores, as well as the poor generalization of existing regression models to new surgical tasks and environments. Meanwhile, appreciable volumes of unlabeled video data are now available, motivating the development of unsupervised domain adaptation (UDA) methods for SSA. We introduce the first benchmark for UDA in SSA regression, spanning four datasets across dry-lab and clinical settings as well as open and robotic surgery. We evaluate eight representative models under challenging domain shifts and propose CoRe-DA, a novel contrastive regression-based adaptation framework. Our method learns domain-invariant representations through relative-score supervision and target-domain self-training. Comprehensive experiments across two UDA settings show that CoRe-DA is superior to state-of-the-art methods, achieving Spearman Correlation Coefficients of 0.46 and 0.41 on dry-lab and clinical target datasets, respectively, without using any labeled target data for training. Overall, CoRe-DA enables scalable SSA with reliable cross-domain generalization, where existing methods underperform. Our code and datasets will be released at https://github.com/anastadimi/CoRe-DA.

☆ CutClaw: Agentic Hours-Long Video Editing via Music Synchronization

Shifang Zhao, Yihan Hu, Ying Shan, Yunchao Wei, Xiaodong Cun

Editing the video content with audio alignment forms a digital human-made art in current social media. However, the time-consuming and repetitive nature of manual video editing has long been a challenge for filmmakers and professional content creators alike. In this paper, we introduce CutClaw, an autonomous multi-agent framework designed to edit hours-long raw footage into meaningful short videos that leverages the capabilities of multiple Multimodal Language Models~(MLLMs) as an agent system. It produces videos with synchronized music, followed by instructions, and a visually appealing appearance. In detail, our approach begins by employing a hierarchical multimodal decomposition that captures both fine-grained details and global structures across visual and audio footage. Then, to ensure narrative consistency, a Playwriter Agent orchestrates the whole storytelling flow and structures the long-term narrative, anchoring visual scenes to musical shifts. Finally, to construct a short edited video, Editor and Reviewer Agents collaboratively optimize the final cut via selecting fine-grained visual content based on rigorous aesthetic and semantic criteria. We conduct detailed experiments to demonstrate that CutClaw significantly outperforms state-of-the-art baselines in generating high-quality, rhythm-aligned videos. The code is available at: https://github.com/GVCLab/CutClaw.

comment: Project Code: https://github.com/GVCLab/CutClaw

☆ STRADAViT: Towards a Foundational Model for Radio Astronomy through Self-Supervised Transfer

Andrea DeMarco, Ian Fenech Conti, Hayley Camilleri, Ardiana Bushi, Simone Riggi

Next-generation radio astronomy surveys are producing millions of resolved sources, but robust morphology analysis remains difficult across heterogeneous telescopes and imaging pipelines. We present STRADAViT, a self-supervised Vision Transformer continued-pretraining framework for transferable radio astronomy image encoders. STRADAViT combines a mixed-survey pretraining dataset, radio astronomy-aware view generation, and controlled continued pretraining through reconstruction-only, contrastive-only, and two-stage branches. Pretraining uses 512x512 radio astronomy cutouts from MeerKAT, ASKAP, LOFAR/LoTSS, and SKA data. We evaluate transfer with linear probing and fine-tuning on three morphology benchmarks: MiraBest, LoTSS DR2, and Radio Galaxy Zoo. Relative to the initialization used for continued pretraining, the best two-stage STRADAViT models improve Macro-F1 in all reported linear-probe settings and in most fine-tuning settings, with the largest gain on RGZ DR1. Relative to strong DINOv2 baselines, gains are selective but remain positive on LoTSS DR2 and RGZ DR1 under linear probing, and on MiraBest and RGZ DR1 under fine-tuning. A targeted DINOv2-initialized HCL ablation further shows that the adaptation recipe is not specific to a single starting point. The released STRADAViT checkpoint remains the preferred model because it offers competitive transfer at lower token count and downstream cost than the DINOv2-based alternative. These results show that radio astronomy-aware view generation and staged continued pretraining provide a stronger starting point than out-of-the-box Vision Transformers for radio astronomy transfer.

comment: 19 pages

☆ Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors

Pengfei Zhou, Xiangyue Zhang, Xukun Shen, Yong Hu

Masked generative models have become a strong paradigm for text-to-motion synthesis, but they still treat motion frames too uniformly during masking, attention, and decoding. This is a poor match for motion, where local dynamic complexity varies sharply over time. We show that current masked motion generators degrade disproportionately on dynamically complex motions, and that frame-wise generation error is strongly correlated with motion dynamics. Motivated by this mismatch, we introduce the Motion Spectral Descriptor (MSD), a simple and parameter-free measure of local dynamic complexity computed from the short-time spectrum of motion velocity. Unlike learned difficulty predictors, MSD is deterministic, interpretable, and derived directly from the motion signal itself. We use MSD to make masked motion generation complexity-aware. In particular, MSD guides content-focused masking during training, provides a spectral similarity prior for self-attention, and can additionally modulate token-level sampling during iterative decoding. Built on top of masked motion generators, our method, DynMask, improves motion generation most clearly on dynamically complex motions while also yielding stronger overall FID on HumanML3D and KIT-ML. These results suggest that respecting local motion complexity is a useful design principle for masked motion generation. Project page: https://xiangyue-zhang.github.io/DynMask

☆ MacTok: Robust Continuous Tokenization for Image Generation

Hengyu Zeng, Xin Gao, Guanghao Li, Yuxiang Yan, Jiaoyang Ruan, Junpeng Ma, Haoyu Albert Wang, Jian Pu

Continuous image tokenizers enable efficient visual generation, and those based on variational frameworks can learn smooth, structured latent representations through KL regularization. Yet this often leads to posterior collapse when using fewer tokens, where the encoder fails to encode informative features into the compressed latent space. To address this, we introduce \textbf{MacTok}, a \textbf{M}asked \textbf{A}ugmenting 1D \textbf{C}ontinuous \textbf{Tok}enizer that leverages image masking and representation alignment to prevent collapse while learning compact and robust representations. MacTok applies both random masking to regularize latent learning and DINO-guided semantic masking to emphasize informative regions in images, forcing the model to encode robust semantics from incomplete visual evidence. Combined with global and local representation alignment, MacTok preserves rich discriminative information in a highly compressed 1D latent space, requiring only 64 or 128 tokens. On ImageNet, MacTok achieves a competitive gFID of 1.44 at 256$\times$256 and a state-of-the-art 1.52 at 512$\times$512 with SiT-XL, while reducing token usage by up to 64$\times$. These results confirm that masking and semantic guidance together prevent posterior collapse and achieve efficient, high-fidelity tokenization.

☆ Self-Supervised Federated Learning under Data Heterogeneity for Label-Scarce Diatom Classification

Mingkun Tan, Xilu Wang, Michael Kloster, Tim W. Nattkemper

Label-scarce visual classification under decentralized and heterogeneous data is a fundamental challenge in pattern recognition, especially when sites exhibit partially overlapping class sets. While self-supervised federated learning (SSFL) offers a promising solution, existing studies commonly assume the same data heterogeneity pattern throughout pre-training and fine-tuning. Moreover, current partitioning schemes often fail to generate pure partially class-disjoint data settings, limiting controllable simulation of real-world label-space heterogeneity. In this work, we introduce SSFL for diatom classification as a representative real-world instance and systematically investigate stage-specific data heterogeneity. We study cross-site variation in unlabeled data volume during pre-training and label-space misalignment during downstream fine-tuning. To study the latter in a controllable setting, we propose PreDi, a partitioning scheme that disentangles label-space heterogeneity into two orthogonal dimensions, namely class Prevalence and class-set size Disparity, enabling separate analysis of their effects. Guided by the resulting insights, we further propose PreP-WFL (Prevalence-based Personalized Weighted Federated Learning) to adaptively strengthen rare-class representations in low-prevalence scenarios. Extensive experiments show that SSFL consistently outperforms local-only training under both homogeneous and heterogeneous settings. The pronounced heterogeneity in unlabeled data volume is associated with improved representation pre-training, whereas under label-space heterogeneity, prevalence dominates performance and disparity has a smaller effect. PreP-WFL effectively mitigates this degradation, with gains increasing as prevalence decreases. These findings provide a mechanistic basis for characterizing label-space heterogeneity in decentralized recognition systems.

comment: 22 pages, 9 figures

☆ Storing Less, Finding More: How Novelty Filtering Improves Cross-Modal Retrieval on Edge Cameras

Sherif Abdelwahab

Always-on edge cameras generate continuous video streams where redundant frames degrade cross-modal retrieval by crowding correct results out of top-k search. This paper presents a streaming retrieval architecture: an on-device epsilon-net filter retains only semantically novel frames, building a denoised embedding index; a cross-modal adapter and cloud re-ranker compensate for the compact encoder's weak alignment. A single-pass streaming filter outperforms offline alternatives (k-means, farthest-point, uniform, random) across eight vision-language models (8M-632M) on two egocentric datasets (AEA, EPIC-KITCHENS). Combined, the architecture reaches 45.6% Hit@5 on held-out data using an 8M on-device encoder at an estimated 2.7 mW.

comment: 6 pages, 3 figures, 5 tables; supplementary video included as ancillary file

☆ BigEarthNet.txt: A Large-Scale Multi-Sensor Image-Text Dataset and Benchmark for Earth Observation

Johann-Ludwig Herzog, Mathis Jürgen Adler, Leonard Hackel, Yan Shu, Angelos Zavras, Ioannis Papoutsis, Paolo Rota, Begüm Demir

Vision-langugage models (VLMs) have shown strong performance in computer vision (CV), yet their performance on remote sensing (RS) data remains limited due to the lack of large-scale, multi-sensor RS image-text datasets with diverse textual annotations. Existing datasets predominantly include aerial Red-Green-Blue imagery, with short or weakly grounded captions, and provide limited diversity in annotation types. To address this limitation, we introduce BigEarthNet.txt, a large-scale, multi-sensor image-text dataset designed to advance instruction-driven image-text learning in Earth observation across multiple tasks. BigEarthNet.txt contains 464044 co-registered Sentinel-1 synthetic aperture radar and Sentinel-2 multispectral images with 9.6M text annotations, including: i) geographically anchored captions describing land-use/land-cover (LULC) classes, their spatial relations, and environmental context; ii) visual question answering pairs relevant for different tasks; and iii) referring expression detection instructions for bounding box prediction. Through a comparative statistical analysis, we demonstrate that BigEarthNet.txt surpasses existing RS image-text datasets in textual richness and annotation type variety. We further establish a manually-verified benchmark split to evaluate VLMs in RS and CV. The results show the limitations of these models on tasks that involve complex LULC classes, whereas fine-tuning using BigEarthNet.txt results in consistent performance gains across all considered tasks.

comment: For details, see https://txt.bigearth.net

☆ Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

comment: Project Page: https://github.com/shawn0728/Unify-Agent

☆ Video-Oasis: Rethinking Evaluation of Video Understanding

Geuntaek Lim, Minho Shim, Sungjune Park, Jaeyun Lee, Inwoong Lee, Taeoh Kim, Dongyoon Wee, Yukyung Choi

The inherent complexity of video understanding makes it difficult to attribute whether performance gains stem from visual perception, linguistic reasoning, or knowledge priors. While many benchmarks have emerged to assess high-level reasoning, the essential criteria that constitute video understanding remain largely overlooked. Instead of introducing yet another benchmark, we take a step back to re-examine the current landscape of video understanding. In this work, we provide Video-Oasis, a sustainable diagnostic suite designed to systematically evaluate existing evaluations and distill spatio-temporal challenges for video understanding. Our analysis reveals two critical findings: (1) 54% of existing benchmark samples are solvable without visual input or temporal context, and (2) on the remaining samples, state-of-the-art models exhibit performance barely exceeding random guessing. To bridge this gap, we investigate which algorithmic design choices contribute to robust video understanding, providing practical guidelines for future research. We hope our work serves as a standard guideline for benchmark construction and the rigorous evaluation of architecture development. Code is available at https://github.com/sejong-rcv/Video-Oasis.

☆ FlowID : Enhancing Forensic Identification with Latent Flow-Matching Models

Jules Ripoll, David Bertoin, Alasdair Newson, Charles Dossal, Jose Pablo Baraybar

Every day, many people die under violent circumstances, whether from crimes, war, migration, or climate disasters. Medico-legal and law enforcement institutions document many portraits of the deceased for evidence, but cannot immediately carry out identification on them. While traditional image editing tools can process these photos for public release, the workflow is lengthy and produces suboptimal results. In this work, we leverage advances in image generation models, which can now produce photorealistic human portraits, to introduce FlowID, an identity-preserving facial reconstruction method. Our approach combines single-image fine-tuning, which adapts the generative model to out-of-distribution injured faces, with attention-based masking that localizes edits to damaged regions while preserving identity-critical features. Together, these components enable the removal of artifacts from violent death while retaining sufficient identity information to support identification. To evaluate our method, we introduce InjuredFaces, a novel benchmark for identity-preserving facial reconstruction under severe facial damage. Beyond serving as an evaluation tool for this work, InjuredFaces provides a standardized resource for the community to study and compare methods addressing facial reconstruction in extreme conditions. Experimental results show that FlowID outperforms state-of-the-art open-source methods while maintaining low memory requirements, making it suitable for local deployment without compromising data privacy.

☆ Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognition

Rongkang Dong, Cuixin Yang, Cong Zhang, Yushen Zuo, Kin-Man Lam

Facial Expression Recognition (FER) is essential for human-machine interaction, as it enables machines to interpret human emotions and internal states from facial affective behaviors. Although deep learning has significantly advanced FER performance, most existing deep-learning-based FER methods rely heavily on discriminative classifiers for fast predictions. These models tend to learn shortcuts and are vulnerable to even minor distribution shifts. To address this issue, we adopt a conditional generative diffusion model and introduce the Emotion Diffusion Classifier (EmoDC) for FER, which demonstrates enhanced adversarial robustness. However, retraining EmoDC using standard strategies fails to penalize incorrect categorical descriptions, leading to suboptimal recognition performance. To improve EmoDC, we propose margin-based discrepancy training, which encourages accurate predictions when conditioned on correct categorical descriptions and penalizes predictions conditioned on mismatched ones. This method enforces a minimum margin between noise-prediction errors for correct and incorrect categories, thereby enhancing the model's discriminative capability. Nevertheless, using a fixed margin fails to account for the varying difficulty of noise prediction across different images, limiting its effectiveness. To overcome this limitation, we propose Adaptive Margin Discrepancy Training (AMDiT), which dynamically adjusts the margin for each sample. Extensive experiments show that AMDiT significantly improves the accuracy of EmoDC over the Base model with standard denoising diffusion training on the RAF-DB basic subset, the RAF-DB compound subset, SFEW-2.0, and AffectNet, in 100-step evaluations. Additionally, EmoDC outperforms state-of-the-art discriminative classifiers in terms of robustness against noise and blur.

☆ Generating Key Postures of Bharatanatyam Adavus with Pose Estimation

Jagadish Kashinath Kamble, Jayanta Mukhopadhyay, Debaditya Roy, Partha Pratim Das

Preserving intangible cultural dances rooted in centuries of tradition and governed by strict structural and symbolic rules presents unique challenges in the digital era. Among these, Bharatanatyam, a classical Indian dance form, stands out for its emphasis on codified adavus and precise key postures. Accurately generating these postures is crucial not only for maintaining anatomical and stylistic integrity, but also for enabling effective documentation, analysis, and transmission to broader global audiences through digital means. We propose a pose-aware generative framework integrated with a pose estimation module, guided by keypoint-based loss and pose consistency constraints. These supervisory signals ensure anatomical accuracy and stylistic integrity in the synthesized outputs. We evaluate four configurations: standard conditional generative adversarial network (cGAN), cGAN with pose supervision, conditional diffusion, and conditional diffusion with pose supervision. Each model is conditioned on key posture class labels and optimized to maintain geometric structure. In both cGAN and conditional diffusion settings, the integrated pose guidance aligns generated poses with ground-truth keypoint structures, promoting cultural fidelity. Our results demonstrate that incorporating pose supervision significantly enhances the quality, realism, and authenticity of generated Bharatanatyam postures. This framework provides a scalable approach for the digital preservation, education, and dissemination of traditional dance forms, enabling high-fidelity generation without compromising cultural precision. Code is available at https://github.com/jagidsh/Generating-Key-Postures-of-Bharatanatyam-Adavus-with-Pose-Estimation.

comment: Published in ICVGIP, 2025

☆ Quantization with Unified Adaptive Distillation to enable multi-LoRA based one-for-all Generative Vision Models on edge

Sowmya Vajrala, Aakash Parmar, Prasanna R, Sravanth Kodavanti, Manjunath Arveti, Srinivas Soumitri Miriyala, Ashok Senapati

Generative Artificial Intelligence (GenAI) features such as image editing, object removal, and prompt-guided image transformation are increasingly integrated into mobile applications. However, deploying Large Vision Models (LVMs) for such tasks on resource-constrained devices remains challenging due to their high memory and compute requirements. While Low-Rank Adapters (LoRAs) enable parameter-efficient task adaptation, existing Mobile deployment pipelines typically compile separate model binaries for each LoRA + a copy of the foundation model, resulting in redundant storage and increased runtime overhead. In this work, we present a unified framework for enabling multi-task GenAI inference on edge devices using a single shared model. Our key idea is to treat LoRA weights as runtime inputs rather than embedding them into the compiled model graph, allowing dynamic task switching at runtime without recompilation. Then, to support efficient on-device execution, we introduce QUAD (Quantization with Unified Adaptive Distillation), a quantizationaware training strategy that aligns multiple LoRA adapters under a shared quantization profile. We implement the proposed system with a lightweight runtime stack compatible with mobile NPUs and evaluate it across multiple chipsets. Experimental results demonstrate up to 6x and 4x reduction in memory footprint and latency improvements, respectively, while maintaining high visual quality across multiple GenAI tasks.

comment: Accepted at the Mobile AI Workshop, CVPR 2026

☆ Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazing

Francesco Moretti, Giulia Bianchi, Andrea Gallo

Nighttime images captured under hazy conditions suffer from severe quality degradation, including low visibility, color distortion, and reduced contrast, caused by the combined effects of atmospheric scattering, absorption by suspended particles, and non-uniform illumination from artificial light sources. While existing nighttime dehazing methods have achieved partial success, they typically address only a subset of these issues, such as glow suppression or brightness enhancement, without jointly tackling the full spectrum of degradation factors. In this paper, we propose a two-stage nighttime image dehazing framework that integrates transmittance correction with structure-texture layered optimization. In the first stage, we introduce a novel transmittance correction method that establishes boundary-constrained initial transmittance maps and subsequently applies region-adaptive compensation and normalization based on whether image regions correspond to light source areas. A quadratic Gaussian filtering scheme operating in the YUV color space is employed to estimate the spatially varying atmospheric light map. The corrected transmittance map and atmospheric light map are then used in conjunction with an improved nighttime imaging model to produce the initial dehazed image. In the second stage, we propose a STAR-YUV decomposition model that separates the dehazed image into structure and texture layers within the YUV color space. Gamma correction and MSRCR-based color restoration are applied to the structure layer for illumination compensation and color bias correction, while Laplacian-of-Gaussian filtering is applied to the texture layer for detail enhancement. A novel two-phase fusion strategy, comprising nonlinear Retinex-based fusion of the enhanced layers followed by linear blending with the initial dehazing result, yields the final output.

☆ All-in-One Augmented Reality Guided Head and Neck Tumor Resection

Yue Yang, Matthieu Chabanas, Carrie Reale, Annie Benson, Jason Slagle, Matthew Weinger, Michael Topf, Jie Ying Wu

Positive margins are common in head and neck squamous cell carcinoma, yet intraoperative re-resection is often imprecise because margin locations are typically communicated verbally from pathology. We present an all-in-one augmented reality (AR) system that relocalizes positive margins from a resected specimen to the resection bed and visualizes them in situ using HoloLens 2 depth sensing and fully automated markerless surface registration. In a silicone phantom study with six medical trainees, markerless registration achieved target registration errors comparable to a marker-based baseline (median 1.8 mm vs. 1.7 mm; maximum < 4 mm). In a margin relocalization task, AR guidance reduced error from verbal guidance (median 14.2 mm) to a few millimeters (median 3.2 mm), with all AR localizations within 5 mm error. These results support the feasibility of markerless AR margin guidance for more precise intraoperative re-excision.

☆ VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference

Anmin Liu, Ruixuan Yang, Huiqiang Jiang, Bin Lin, Minmin Sun, Yong Li, Chen Zhang, Tao Xie

Long-context video understanding and generation pose a significant computational challenge for Transformer-based video models due to the quadratic complexity of self-attention. While existing sparse attention methods employ coarse-grained patterns to improve efficiency, they typically incur redundant computation and suboptimal performance. To address this issue, in this paper, we propose \textbf{VecAttention}, a novel framework of vector-wise sparse attention that achieves superior accuracy-efficiency trade-offs for video models. We observe that video attention maps exhibit a strong vertical-vector sparse pattern, and further demonstrate that this vertical-vector pattern offers consistently better accuracy-sparsity trade-offs compared with existing coarse-grained sparse patterns. Based on this observation, VecAttention dynamically selects and processes only informative vertical vectors through a lightweight important-vector selection that minimizes memory access overhead and an optimized kernel of vector sparse attention. Comprehensive evaluations on video understanding (VideoMME, LongVideoBench, and VCRBench) and generation (VBench) tasks show that VecAttention delivers a 2.65$\times$ speedup over full attention and a 1.83$\times$ speedup over state-of-the-art sparse attention methods, with comparable accuracy to full attention. Our code is available at https://github.com/anminliu/VecAttention.

comment: Accepted at CVPR 2026

☆ Square Superpixel Generation and Representation Learning via Granular Ball Computing

Shuyin Xia, Meng Yang, Dawei Dai, Fan Chen, Shilin Zhao, Junwei Han, Xinbo Gao, Guoyin Wang, Wen Lu

Superpixels provide a compact region-based representation that preserves object boundaries and local structures, and have therefore been widely used in a variety of vision tasks to reduce computational cost. However, most existing superpixel algorithms produce irregularly shaped regions, which are not well aligned with regular operators such as convolutions. Consequently, superpixels are often treated as an offline preprocessing step, limiting parallel implementation and hindering end-to-end optimization within deep learning pipelines. Motivated by the adaptive representation and coverage property of granular-ball computing, we develop a square superpixel generation approach. Specifically, we approximate superpixels using multi-scale square blocks to avoid the computational and implementation difficulties induced by irregular shapes, enabling efficient parallel processing and learnable feature extraction. For each block, a purity score is computed based on pixel-intensity similarity, and high-quality blocks are selected accordingly. The resulting square superpixels can be readily integrated as graph nodes in graph neural networks (GNNs) or as tokens in Vision Transformers (ViTs), facilitating multi-scale information aggregation and structured visual representation. Experimental results on downstream tasks demonstrate consistent performance improvements, validating the effectiveness of the proposed method.

☆ FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion

Ningzhi Gao, Siquan Huang, Leyu Shi, Ying Gao

Federated prototype learning (FPL), as a solution to heterogeneous federated learning (HFL), effectively alleviates the challenges of data and model heterogeneity.However, existing FPL methods fail to balance the fidelity and discriminability of the feature, and are limited by a single global prototype. In this paper, we propose FedDBP, a novel FPL method to address the above issues. On the client-side, we design a Dual-Branch feature projector that employs L2 alignment and contrastive learning simultaneously, thereby ensuring both the fidelity and discriminability of local features. On the server-side, we introduce a Personalized global prototype fusion approach that leverages Fisher information to identify the important channels of local prototypes. Extensive experiments demonstrate the superiority of FedDBP over ten existing advanced methods.

☆ Few-shot Writer Adaptation via Multimodal In-Context Learning

Tom Simon, Stephane Nicolas, Pierrick Tranouez, Clement Chatelain, Thierry Paquet

While state-of-the-art Handwritten Text Recognition (HTR) models perform well on standard benchmarks, they frequently struggle with writers exhibiting highly specific styles that are underrepresented in the training data. To handle unseen and atypical writers, writer adaptation techniques personalize HTR models to individual handwriting styles. Leading writer adaptation methods require either offline fine-tuning or parameter updates at inference time, both involving gradient computation and backpropagation, which increase computational costs and demand careful hyperparameter tuning. In this work, we propose a novel context-driven HTR framework3 inspired by multimodal in-context learning, enabling inference-time writer adaptation using only a few examples from the target writer without any parameter updates. We further demonstrate the impact of context length, design a compact 8M-parameter CNN-Transformer that enables few-shot in-context adaptation, and show that combining context-driven and standard OCR training strategies leads to complementary improvements. Experiments on IAM and RIMES validate our approach with Character Error Rates of 3.92% and 2.34%, respectively, surpassing all writer-independent HTR models without requiring any parameter updates at inference time.

☆ NeoNet: An End-to-End 3D MRI-Based Deep Learning Framework for Non-Invasive Prediction of Perineural Invasion via Generation-Driven Classification AAAI 2026

Youngung Han, Minkyung Cha, Kyeonghun Kim, Induk Um, Myeongbin Sho, Joo Young Bae, Jaewon Jung, Jung Hyeok Park, Seojun Lee, Nam-Joon Kim, Woo Kyoung Jeong, Won Jae Lee, Pa Hong, Ken Ying-Kai Liao, Hyuk-Jae Lee

Minimizing invasive diagnostic procedures to reduce the risk of patient injury and infection is a central goal in medical imaging. And yet, noninvasive diagnosis of perineural invasion (PNI), a critical prognostic factor involving infiltration of tumor cells along the surrounding nerve, still remains challenging, due to the lack of clear and consistent imaging criteria criteria for identifying PNI. To address this challenge, we present NeoNet, an integrated end-to-end 3D deep learning framework for PNI prediction in cholangiocarcinoma that does not rely on predefined image features. NeoNet integrates three modules: (1) NeoSeg, utilizing a Tumor-Localized ROI Crop (TLCR) algorithm; (2) NeoGen, a 3D Latent Diffusion Model (LDM) with ControlNet, conditioned on anatomical masks to generate synthetic image patches, specifically balancing the dataset to a 1:1 ratio; and (3) NeoCls, the final prediction module. For NeoCls, we developed the PNI-Attention Network (PattenNet), which uses the frozen LDM encoder and specialized 3D Dual Attention Blocks (DAB) designed to detect subtle intensity variations and spatial patterns indicative of PNI. In 5-fold cross-validation, NeoNet outperformed baseline 3D models and achieved the highest performance with a maximum AUC of 0.7903.

comment: 15 pages, 5 figures. Accepted for oral presentation at W3PHIAI Workshop, AAAI 2026

☆ EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images ICLR 2026

Yijie Zheng, Weijie Wu, Bingyue Wu, Long Zhao, Guoqing Li, Mikolaj Czerkawski, Konstantin Klemmer

While the Earth observation community has witnessed a surge in high-impact foundation models and global Earth embedding datasets, a significant barrier remains in translating these academic assets into freely accessible tools. This tutorial introduces EarthEmbeddingExplorer, an interactive web application designed to bridge this gap, transforming static research artifacts into dynamic, practical workflows for discovery. We will provide a comprehensive hands-on guide to the system, detailing its cloud-native software architecture, demonstrating cross-modal queries (natural language, visual, and geolocation), and showcasing how to derive scientific insights from retrieval results. By democratizing access to precomputed Earth embeddings, this tutorial empowers researchers to seamlessly transition from state-of-the-art models and data archives to real-world application and analysis. The web application is available at https://modelscope.ai/studios/Major-TOM/EarthEmbeddingExplorer.

comment: ICLR 2026 Workshop ML4RS Tutorial Track (oral)

☆ Polyhedral Unmixing: Bridging Semantic Segmentation with Hyperspectral Unmixing via Polyhedral-Cone Partitioning

Antoine Bottenmuller, Etienne Decencière, Petr Dokládal

Semantic segmentation and hyperspectral unmixing are two central problems in spectral image analysis. The former assigns each pixel a discrete label corresponding to its material class, whereas the latter estimates pure material spectra, called endmembers, and, for each pixel, a vector representing material abundances in the observed scene. Despite their complementarity, these two problems are usually addressed independently. This paper aims to bridge these two lines of work by formally showing that, under the linear mixing model, pixel classification by dominant materials induces polyhedral-cone regions in the spectral space. We leverage this fundamental property to propose a direct segmentation-to-unmixing pipeline that performs blind hyperspectral unmixing from any semantic segmentation by constructing a polyhedral-cone partition of the space that best fits the labeled pixels. Signed distances from pixels to the estimated regions are then computed, linearly transformed via a change of basis in the distance space, and projected onto the probability simplex, yielding an initial abundance estimate. This estimate is used to extract endmembers and recover final abundances via matrix pseudo-inversion. Because the segmentation method can be freely chosen, the user gains explicit control over the unmixing process, while the rest of the pipeline remains essentially deterministic and lightweight. Beyond improving interpretability, experiments on three real datasets demonstrate the effectiveness of the proposed approach when associated with appropriate clustering algorithms, and show consistent improvements over recent deep and non-deep state-of-the-art methods. The code is available at: https://github.com/antoine-bottenmuller/polyhedral-unmixing

☆ SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering

Wenli Li, Kai Zhao, Haoran Jiang, Enquan Yang, Yi Su, Dan Zeng

Vision-language models (VLMs) have been widely adopted for 3D question answering (3D QA). In typical pipelines, visual tokens extracted from multiple viewpoints are concatenated with language tokens and jointly processed by a large language model (LLM) for inference. However, aggregating multi-view observations inevitably introduces severe token redundancy, leading to an overly large visual token set that significantly hinders inference efficiency under constrained token budgets. Visual token pruning has emerged as a prevalent strategy to address this issue. Nevertheless, most existing pruners are primarily tailored to 2D inputs or rely on indirect geometric cues, which limits their ability to explicitly retain semantically critical objects and maintain sufficient spatial coverage for robust 3D reasoning. In this paper, we propose SeGPruner, a semantic-aware and geometry-guided token reduction framework for efficient 3D QA with multi-view images. Specifically, SeGPruner first preserves semantically salient tokens through an attention-based importance module (Saliency-aware Token Selector), ensuring that object-critical evidence is retained. It then complements these tokens with spatially diverse ones via a geometry-guided selector (Geometry-aware Token Diversifier), which jointly considers semantic relevance and 3D geometric distance. This cooperation between saliency preservation and geometry-guided diversification balances object-level evidence and global scene coverage under aggressive token reduction. Extensive experiments on ScanQA and OpenEQA demonstrate that SeGPruner substantially improves inference efficiency, reducing the visual token budget by 91% and inference latency by 86%, while maintaining competitive performance in 3D reasoning tasks.

☆ Seeing the Evidence, Missing the Answer: Tool-Guided Vision-Language Models on Visual Illusions

Xuesong Wang, Harry Wang

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a tool-guided inference framework for the DataCV 2026 Challenge (Tasks I and II) that addresses this failure mode without any model training. An off-the-shelf vision-language model is given access to a small set of generic image manipulation tools: line drawing, region cropping, side-by-side comparison, and channel isolation, together with an illusion-type-routing system prompt that prescribes which tools to invoke for each perceptual question category. Critically, every tool call produces a new, immutable image resource appended to a persistent registry, so the model can reference and compose any prior annotated view throughout its reasoning chain. Rather than hard-coding illusion-specific modules, this generic-tool-plus-routing design yields strong cross-structural generalization: performance remained consistent from the validation set to a test set containing structurally unfamiliar illusion variants (e.g., Mach Bands rotated from vertical to horizontal stacking). We further report three empirical observations that we believe warrant additional investigation: (i) a strong positive-detection bias likely rooted in imbalanced illusion training data, (ii) a striking dissociation between pixel-accurate spatial reasoning and logical inference over self-generated annotations, and (iii) pronounced sensitivity to image compression artifacts that compounds false positives.

comment: CVPR 2026 DataCV Workshop, code: https://github.com/Davidxswang/cvpr_2026_datacv_submission

☆ A2BFR: Attribute-Aware Blind Face Restoration

Chenxin Zhu, Yushun Fang, Lu Liu, Shibo Yin, Xiaohong Liu, Xiaoyun Zhang, Qiang Hu, Guangtao Zhai

Blind face restoration (BFR) aims to recover high-quality facial images from degraded inputs, yet its inherently ill-posed nature leads to ambiguous and uncontrollable solutions. Recent diffusion-based BFR methods improve perceptual quality but remain uncontrollable, whereas text-guided face editing enables attribute manipulation without reliable restoration. To address these issues, we propose A$^2$BFR, an attribute-aware blind face restoration framework that unifies high-fidelity reconstruction with prompt-controllable generation. Built upon a Diffusion Transformer backbone with unified image-text cross-modal attention, A$^2$BFR jointly conditions the denoising trajectory on both degraded inputs and textual prompts. To inject semantic priors, we introduce attribute-aware learning, which supervises denoising latents using facial attribute embeddings extracted by an attribute-aware encoder. To further enhance prompt controllability, we introduce semantic dual-training, which leverages the pairwise attribute variations in our newly curated AttrFace-90K dataset to enforce attribute discrimination while preserving fidelity. Extensive experiments demonstrate that A$^2$BFR achieves state-of-the-art performance in both restoration fidelity and instruction adherence, outperforming diffusion-based BFR baselines by -0.0467 LPIPS and +52.58% attribute accuracy, while enabling fine-grained, prompt-controllable restoration even under severe degradations.

☆ Multimodal Models Meet Presentation Attack Detection on ID Documents

Marina Villanueva, Juan M. Espin, Juan E. Tapia

The integration of multimodal models into Presentation Attack Detection (PAD) for ID Documents represents a significant advancement in biometric security. Traditional PAD systems rely solely on visual features, which often fail to detect sophisticated spoofing attacks. This study explores the combination of visual and textual modalities by utilizing pre-trained multimodal models, such as Paligemma, Llava, and Qwen, to enhance the detection of presentation attacks on ID Documents. This approach merges deep visual embeddings with contextual metadata (e.g., document type, issuer, and date). However, experimental results indicate that these models struggle to accurately detect PAD on ID Documents.

☆ RAAP: Retrieval-Augmented Affordance Prediction with Cross-Image Action Alignment

Qiyuan Zhuang, He-Yang Xu, Yijun Wang, Xin-Yang Zhao, Yang-Yang Li, Xiu-Shen Wei

Understanding object affordances is essential for enabling robots to perform purposeful and fine-grained interactions in diverse and unstructured environments. However, existing approaches either rely on retrieval, which is fragile due to sparsity and coverage gaps, or on large-scale models, which frequently mislocalize contact points and mispredict post-contact actions when applied to unseen categories, thereby hindering robust generalization. We introduce Retrieval-Augmented Affordance Prediction (RAAP), a framework that unifies affordance retrieval with alignment-based learning. By decoupling static contact localization and dynamic action direction, RAAP transfers contact points via dense correspondence and predicts action directions through a retrieval-augmented alignment model that consolidates multiple references with dual-weighted attention. Trained on compact subsets of DROID and HOI4D with as few as tens of samples per task, RAAP achieves consistent performance across unseen objects and categories, and enables zero-shot robotic manipulation in both simulation and the real world. Project website: https://github.com/SEU-VIPGroup/RAAP.

comment: Accepted to ICRA 2026

☆ Adversarial Prompt Injection Attack on Multimodal Large Language Models

Meiwen Ding, Song Xia, Chenqi Kong, Xudong Jiang

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly rely on textual prompts or perceptible visual prompts that are observable by human users. In this work, we study imperceptible visual prompt injection against powerful closed-source MLLMs, where adversarial instructions are embedded in the visual modality. Our method adaptively embeds the malicious prompt into the input image via a bounded text overlay to provide semantic guidance. Meanwhile, the imperceptible visual perturbation is iteratively optimized to align the feature representation of the attacked image with those of the malicious visual and textual targets at both coarse- and fine-grained levels. Specifically, the visual target is instantiated as a text-rendered image and progressively refined during optimization to more faithfully represent the desired semantics and improve transferability. Extensive experiments on two multimodal understanding tasks across multiple closed-source MLLMs demonstrate the superior performance of our approach compared to existing methods.

☆ Native-Domain Cross-Attention for Camera-LiDAR Extrinsic Calibration Under Large Initial Perturbations

Ni Ou, Zhuo Chen, Xinru Zhang, Junzheng Wang

Accurate camera-LiDAR fusion relies on precise extrinsic calibration, which fundamentally depends on establishing reliable cross-modal correspondences under potentially large misalignments. Existing learning-based methods typically project LiDAR points into depth maps for feature fusion, which distorts 3D geometry and degrades performance when the extrinsic initialization is far from the ground truth. To address this issue, we propose an extrinsic-aware cross-attention framework that directly aligns image patches and LiDAR point groups in their native domains. The proposed attention mechanism explicitly injects extrinsic parameter hypotheses into the correspondence modeling process, enabling geometry-consistent cross-modal interaction without relying on projected 2D depth maps. Extensive experiments on the KITTI and nuScenes benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in both accuracy and robustness. Under large extrinsic perturbations, our approach achieves accurate calibration in 88% of KITTI cases and 99% of nuScenes cases, substantially surpassing the second-best baseline. We have open sourced our code on https://github.com/gitouni/ProjFusion to benefit the community.

comment: 8 pages, 3 figures

☆ AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models

Yubo Cui, Xianchao Guan, Zijun Xiong, Zheng Zhang

Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-trained cross-modal alignment, weakening visual-textual correspondence and degrading zero-shot performance. In this paper, we propose an Alignment-Guided Fine-Tuning (AGFT) framework that enhances zero-shot adversarial robustness while preserving the cross-modal semantic structure. Unlike label-based methods that rely on hard labels and fail to maintain the relative relationships between image and text, AGFT leverages the probabilistic predictions of the original model for text-guided adversarial training, which aligns adversarial visual features with textual embeddings via soft alignment distributions, improving zero-shot adversarial robustness. To address structural discrepancies introduced by fine-tuning, we introduce a distribution consistency calibration mechanism that adjusts the robust model output to match a temperature-scaled version of the pre-trained model predictions. Extensive experiments across multiple zero-shot benchmarks demonstrate that AGFT outperforms state-of-the-art methods while significantly improving zero-shot adversarial robustness.

comment: Accepted by CVPR 2026; Code is available at \url{https://github.com/YuboCui/AGFT}

☆ Hallucination-aware intermediate representation edit in large vision-language models

Wei Suo, Hanzu Zhang, Lijun Zhang, Ji Ma, Peng Wang, Yanning Zhang

Large Vision-Language Models have demonstrated exceptional performance in multimodal reasoning and complex scene understanding. However, these models still face significant hallucination issues, where outputs contradict visual facts. Recent research on hallucination mitigation has focused on retraining methods and Contrastive Decoding (CD) methods. While both methods perform well, retraining methods require substantial training resources, and CD methods introduce dual inference overhead. These factors hinder their practical applicability. To address the above issue, we propose a framework for dynamically detecting hallucination representations and performing hallucination-eliminating edits on these representations. With minimal additional computational cost, we achieve state-of-the-art performance on existing benchmarks. Extensive experiments demonstrate the effectiveness of our approach, highlighting its efficient and robust hallucination elimination capability and its powerful controllability over hallucinations. Code is available at https://github.com/ASGO-MM/HIRE

☆ AA-Splat: Anti-Aliased Feed-forward Gaussian Splatting

Taewoo Suh, Sungpyo Kim, Jongmin Park, Munchurl Kim

Feed-forward 3D Gaussian Splatting (FF-3DGS) emerges as a fast and robust solution for sparse-view 3D reconstruction and novel view synthesis (NVS). However, existing FF-3DGS methods are built on incorrect screen-space dilation filters, causing severe rendering artifacts when rendering at out-of-distribution sampling rates. We firstly propose an FF-3DGS model, called AA-Splat, to enable robust anti-aliased rendering at any resolution. AA-Splat utilizes an opacity-balanced band-limiting (OBBL) design, which combines two components: a 3D band-limiting post-filter integrates multi-view maximal frequency bounds into the feed-forward reconstruction pipeline, effectively band-limiting the resulting 3D scene representations and eliminating degenerate Gaussians; an Opacity Balancing (OB) to seamlessly integrate all pixel-aligned Gaussian primitives into the rendering process, compensating for the increased overlap between expanded Gaussian primitives. AA-Splat demonstrates drastic improvements with average 5.4$\sim$7.5dB PSNR gains on NVS performance over a state-of-the-art (SOTA) baseline, DepthSplat, at all resolutions, between $4\times$ and $1/4\times$. Code will be made available.

comment: Please visit our project page at https://kaist-viclab.github.io/aasplat-site/

☆ Extend3D: Town-Scale 3D Generation

Seungwoo Yoon, Jinmo Kim, Jaesik Park

In this paper, we propose Extend3D, a training-free pipeline for 3D scene generation from a single image, built upon an object-centric 3D generative model. To overcome the limitations of fixed-size latent spaces in object-centric models for representing wide scenes, we extend the latent space in the $x$ and $y$ directions. Then, by dividing the extended latent space into overlapping patches, we apply the object-centric 3D generative model to each patch and couple them at each time step. Since patch-wise 3D generation with image conditioning requires strict spatial alignment between image and latent patches, we initialize the scene using a point cloud prior from a monocular depth estimator and iteratively refine occluded regions through SDEdit. We discovered that treating the incompleteness of 3D structure as noise during 3D refinement enables 3D completion via a concept, which we term under-noising. Furthermore, to address the sub-optimality of object-centric models for sub-scene generation, we optimize the extended latent during denoising, ensuring that the denoising trajectories remain consistent with the sub-scene dynamics. To this end, we introduce 3D-aware optimization objectives for improved geometric structure and texture fidelity. We demonstrate that our method yields better results than prior methods, as evidenced by human preference and quantitative experiments.

comment: CVPR 2026, Project Page: http://seungwoo-yoon.github.io/extend3d-page

☆ PromptForge-350k: A Large-Scale Dataset and Contrastive Framework for Prompt-Based AI Image Forgery Localization

Jianpeng Wang, Haoyu Wang, Baoying Chen, Jishen Zeng, Yiming Qin, Yiqi Yang, Zhongjie Ba

The rapid democratization of prompt-based AI image editing has recently exacerbated the risks associated with malicious content fabrication and misinformation. However, forgery localization methods targeting these emerging editing techniques remain significantly under-explored. To bridge this gap, we first introduce a fully automated mask annotating framework that leverages keypoint alignment and semantic space similarity to generate precise ground-truth masks for edited regions. Based on this framework, we construct PromptForge-350k, a large-scale forgery localization dataset covering four state-of-the-art prompt-based AI image editing models, thereby mitigating the data scarcity in this domain. Furthermore, we propose ICL-Net, an effective forgery localization network featuring a triple-stream backbone and intra-image contrastive learning. This design enables the model to capture highly robust and generalizable forensic features. Extensive experiments demonstrate that our method achieves an IoU of 62.5% on PromptForge-350k, outperforming SOTA methods by 5.1%. Additionally, it exhibits strong robustness against common degradations with an IoU drop of less than 1%, and shows promising generalization capabilities on unseen editing models, achieving an average IoU of 41.5%.

☆ Assessing Multimodal Chronic Wound Embeddings with Expert Triplet Agreement

Fabian Kabus, Julia Hindel, Jelena Bratulić, Meropi Karakioulaki, Ayush Gupta, Cristina Has, Thomas Brox, Abhinav Valada, Harald Binder

Recessive dystrophic epidermolysis bullosa (RDEB) is a rare genetic skin disorder for which clinicians greatly benefit from finding similar cases using images and clinical text. However, off-the-shelf foundation models do not reliably capture clinically meaningful features for this heterogeneous, long-tail disease, and structured measurement of agreement with experts is challenging. To address these gaps, we propose evaluating embedding spaces with expert ordinal comparisons (triplet judgments), which are fast to collect and encode implicit clinical similarity knowledge. We further introduce TriDerm, a multimodal framework that learns interpretable wound representations from small cohorts by integrating wound imagery, boundary masks, and expert reports. On the vision side, TriDerm adapts visual foundation models to RDEB using wound-level attention pooling and non-contrastive representation learning. For text, we prompt large language models with comparison queries and recover medically meaningful representations via soft ordinal embeddings (SOE). We show that visual and textual modalities capture complementary aspects of wound phenotype, and that fusing both modalities yields 73.5% agreement with experts, outperforming the best off-the-shelf single-modality foundation model by over 5.6 percentage points. We make the expert annotation tool, model code and representative dataset samples publicly available.

☆ StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision

Ziyang Chen, Yansong Qu, You Shen, Xuan Cheng, Liujuan Cao

Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research frontier. Contemporary stereo vision backbones typically rely on either monocular depth estimation (MDE) models or visual foundation models (VFMs). Crucially, these models are predominantly pretrained without explicit supervision of camera poses. Given that such geometric knowledge is indispensable for stereo vision, the absence of explicit spatial constraints constitutes a significant performance bottleneck for existing architectures. Recognizing that the Visual Geometry Grounded Transformer (VGGT) operates as a foundation model pretrained on extensive 3D priors, including camera poses, we investigate its potential as a robust backbone for stereo vision tasks. Nevertheless, empirical results indicate that its direct application to stereo vision yields suboptimal performance. We observe that VGGT suffers from a more significant degradation of geometric details during feature extraction. Such characteristics conflict with the requirements of binocular stereo vision, thereby constraining its efficacy for relative tasks. To bridge this gap, we propose StereoVGGT, a feature backbone specifically tailored for stereo vision. By leveraging the frozen VGGT and introducing a training-free feature adjustment pipeline, we mitigate geometric degradation and harness the latent camera calibration knowledge embedded within the model. StereoVGGT-based stereo matching network achieved the $1^{st}$ rank among all published methods on the KITTI benchmark, validating that StereoVGGT serves as a highly effective backbone for stereo vision.

☆ Uncertainty-Aware Trajectory Prediction: A Unified Framework Harnessing Positional and Semantic Uncertainties

Jintao Sun, Hu Zhang, Gangyi Ding, Zhedong Zheng

Trajectory prediction seeks to forecast the future motion of dynamic entities, such as vehicles and pedestrians, given a temporal horizon of historical movement data and environmental context. A central challenge in this domain is the inherent uncertainty in real-time maps, arising from two primary sources: (1) positional inaccuracies due to sensor limitations or environmental occlusions, and (2) semantic errors stemming from misinterpretations of scene context. To address these challenges, we propose a novel unified framework that jointly models positional and semantic uncertainties and explicitly integrates them into the trajectory prediction pipeline. Our approach employs a dual-head architecture to independently estimate semantic and positional predictions in a dual-pass manner, deriving prediction variances as uncertainty indicators in an end-to-end fashion. These uncertainties are subsequently fused with the semantic and positional predictions to enhance the robustness of trajectory forecasts. We evaluate our uncertainty-aware framework on the nuScenes real-world driving dataset, conducting extensive experiments across four map estimation methods and two trajectory prediction baselines. Results verify that our method (1) effectively quantifies map uncertainties through both positional and semantic dimensions, and (2) consistently improves the performance of existing trajectory prediction models across multiple metrics, including minimum Average Displacement Error (minADE), minimum Final Displacement Error (minFDE), and Miss Rate (MR). Code will available at https://github.com/JT-Sun/UATP.

comment: 13 pages, 7 figures, 4 tables

☆ CIPHER: Counterfeit Image Pattern High-level Examination via Representation

Kyeonghun Kim, Youngung Han, Seoyoung Ju, Yeonju Jean, YooHyun Kim, Minseo Choi, SuYeon Lim, Kyungtae Park, Seungwoo Baek, Sieun Hyeon, Nam-Joon Kim, Hyuk-Jae Lee

The rapid progress of generative adversarial networks (GANs) and diffusion models has enabled the creation of synthetic faces that are increasingly difficult to distinguish from real images. This progress, however, has also amplified the risks of misinformation, fraud, and identity abuse, underscoring the urgent need for detectors that remain robust across diverse generative models. In this work, we introduce Counterfeit Image Pattern High-level Examination via Representation(CIPHER), a deepfake detection framework that systematically reuses and fine-tunes discriminators originally trained for image generation. By extracting scale-adaptive features from ProGAN discriminators and temporal-consistency features from diffusion models, CIPHER captures generation-agnostic artifacts that conventional detectors often overlook. Through extensive experiments across nine state-of-the-art generative models, CIPHER demonstrates superior cross-model detection performance, achieving up to 74.33% F1-score and outperforming existing ViT-based detectors by over 30% in F1-score on average. Notably, our approach maintains robust performance on challenging datasets where baseline methods fail, with up to 88% F1-score on CIFAKE compared to near-zero performance from conventional detectors. These results validate the effectiveness of discriminator reuse and cross-model fine-tuning, establishing CIPHER as a promising approach toward building more generalizable and robust deepfake detection systems in an era of rapidly evolving generative technologies.

comment: 6 pages, 2 figures. Accepted at IEEE-Asia 2025

☆ FOSCU: Feasibility of Synthetic MRI Generation via Duo-Diffusion Models for Enhancement of 3D U-Nets in Hepatic Segmentation

Youngung Han, Kyeonghun Kim, Seoyoung Ju, Yeonju Jean, Minkyung Cha, Seohyoung Park, Hyeonseok Jung, Nam-Joon Kim, Woo Kyoung Jeong, Ken Ying-Kai Liao, Hyuk-Jae Lee

Medical image segmentation faces fundamental challenges including restricted access, costly annotation, and data shortage to clinical datasets through Picture Archiving and Communication Systems (PACS). These systemic barriers significantly impede the development of robust segmentation algorithms. To address these challenges, we propose FOSCU, which integrates Duo-Diffusion, a 3D latent diffusion model with ControlNet that simultaneously generates high-resolution, anatomically realistic synthetic MRI volumes and corresponding segmentation labels, and an enhanced 3D U-Net training pipeline. Duo-Diffusion employs segmentation-conditioned diffusion to ensure spatial consistency and precise anatomical detail in the generated data. Experimental evaluation on 720 abdominal MRI scans shows that models trained with combined real and synthetic data yield a mean Dice score gain of 0.67% over those using only real data, and achieve a 36.4% reduction in Fréchet Inception Distance (FID), reflecting enhanced image fidelity.

comment: 10 pages, 5 figures. Accepted at IEEE APCCAS 2025

♻ ☆ Efficient Universal Perception Encoder

Chenchen Zhu, Saksham Suri, Cijo Jose, Maxime Oquab, Marc Szafraniec, Wei Wen, Yunyang Xiong, Patrick Labatut, Piotr Bojanowski, Raghuraman Krishnamoorthi, Vikas Chandra

Running AI models on smart edge devices can unlock versatile user experiences, but presents challenges due to limited compute and the need to handle multiple tasks simultaneously. This requires a vision encoder with small size but powerful and versatile representations. We present our method, Efficient Universal Perception Encoder (EUPE), which offers both inference efficiency and universally good representations for diverse downstream tasks. We achieve this by distilling from multiple domain-expert foundation vision encoders. Unlike previous agglomerative methods that directly scale down from multiple teachers to an efficient encoder, we demonstrate the importance of first scaling up to a large proxy teacher and then scaling down from this single teacher. Experiments show that EUPE achieves on-par or better performance than individual domain experts of the same size on diverse task domains and also outperforms previous agglomerative encoders. We release the full family of EUPE models and the code to foster future research.

comment: Code: https://github.com/facebookresearch/EUPE; Model: https://huggingface.co/collections/facebook/eupe

♻ ☆ Gaze Authentication: Factors Influencing Authentication Performance

Dillon Lohr, Michael J Proulx, Mehedi Hasan Raju, Oleg V Komogortsev

This paper examines the key factors that influence the performance of state-of-the-art gaze-based authentication. Experiments were conducted on a large-scale, in-house dataset comprising 8,849 subjects collected with Meta Quest Pro equivalent hardware running a video oculography-driven gaze estimation pipeline at 72~Hz. State of the neural network architecture was employed to study the influence of the following factors on authentication performance: eye tracking signal quality, various aspects of eye tracking calibration, and simple filtering on estimated raw gaze. This report provides performance results and their analysis.

comment: 21 pages, 6 figures, 10 tables

♻ ☆ GenOL: Generating Diverse Examples for Name-only Online Learning

Minhyuk Seo, Seongwon Cho, Minjae Lee, Diganta Misra, Hyeonbeom Choi, Seon Joo Kim, Jonghyun Choi

Online learning methods often rely on supervised data. However, under data distribution shifts, such as in continual learning (CL), where continuously arriving online data streams incorporate new concepts (e.g., classes), real-time manual annotation is impractical due to its costs and latency, which hinder real-time adaptation. To alleviate this, 'name-only' setup has been proposed, requiring only the name of concepts, not the supervised samples. A recent approach tackles this setup by supplementing data with web-scraped images, but such data often suffers from issues of data imbalance, noise, and copyright. To overcome the limitations of both human supervision and webly supervision, we propose GenOL using generative models for name-only training. But naive application of generative models results in limited diversity of generated data. Here, we enhance (i) intra-diversity, the diversity of images generated by a single model, by proposing a diverse prompt generation method that generates diverse text prompts for text-to-image models, and (ii) inter-diversity, the diversity of images generated by multiple generative models, by introducing an ensemble strategy that selects minimally overlapping samples. We empirically validate that the proposed \frameworkname outperforms prior arts, even a model trained with fully supervised data by large margins, in various tasks, including image recognition and multi-modal visual reasoning.

comment: TMLR 2025

♻ ☆ MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation

Ruiyao Liu, Hui Shen, Ping Zhang, Yunta Hsieh, Yifan Zhang, Jing Xu, Sicheng Chen, Junchen Li, Jiawei Lu, Jianing Ma, Jiaqi Mo, Qi Han, Zhen Zhang, Zhongwei Wan, Jing Xiong, Xin Wang, Ziyuan Liu, Hangrui Cao, Ngai Wong

Modern generative models have demonstrated the ability to solve challenging mathematical problems. In many real-world settings, however, mathematical solutions must be expressed visually through diagrams, plots, geometric constructions, and structured symbolic layouts, where correctness depends on precise visual composition. This naturally raises the question of whether generative models can still do so when the answer must be rendered visually rather than written in text? To study this problem, we introduce MathGen, a rigorous benchmark of 900 problems spanning seven core domains, each paired with an executable verifier under a Script-as-a-Judge protocol for deterministic and objective evaluation. Experiments on representative open-source and proprietary text-to-image models show that mathematical fidelity remains a major bottleneck: even the best closed-source model reaches only 42.0% overall accuracy, while open-source models achieve just ~ 1-11%, often near 0% on structured tasks. Overall, current T2I models remain far from competent at even elementary mathematical visual generation.

♻ ☆ ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs

An Yu, Ting Yu Tsai, Zhenfei Zhang, Weiheng Lu, Felix X. -F. Ye, Ming-Ching Chang

Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present ReDiPrune, a training-free token pruning method applied before the vision-language projector, where visual features remain rich and discriminative. Unlike post-projection pruning methods that operate on compressed representations, ReDiPrune selects informative tokens directly from vision encoder outputs, preserving fine-grained spatial and semantic cues. Each token is scored by a lightweight rule that jointly consider text-conditioned relevance and max-min diversity, ensuring the selected tokens are both query-relevant and non-redundant. ReDiPrune is fully plug-and-play, requiring no retraining or architectural modifications, and can be seamlessly inserted between the encoder and projector. Across four video and five image benchmarks, it consistently improves the accuracy-efficiency trade-off. For example, on EgoSchema with LLaVA-NeXT-Video-7B, retaining only 15% of visual tokens yields a +2.0% absolute accuracy gain while reducing computation by more than $6\times$ in TFLOPs. Code is available at https://github.com/UA-CVML/ReDiPrune.

♻ ☆ DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

Lunbin Zeng, Jingfeng Yao, Bencheng Liao, Hongyuan Tao, Wenyu Liu, Xinggang Wang

Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, diffusion vision language models (dVLMs) still lag significantly behind mainstream autoregressive vision language models. This is due to the scarcity and weaker performance of base diffusion language models (dLLMs) compared with their autoregressive counterparts. This raises a natural question: Can we build high-performing dVLMs directly from existing powerful AR models, without relying on dLLMs? We propose DiffusionVL, a family of dVLMs obtained by translating pretrained AR models into the diffusion paradigm via an efficient diffusion finetuning procedure that changes the training objective and decoding process while keeping the backbone architecture intact. Through an efficient diffusion finetuning strategy, we successfully adapt AR pretrained models into the diffusion paradigm. This approach yields two key observations: (1) The paradigm shift from AR-based multimodal models to diffusion is remarkably effective. (2) Direct conversion of an AR language model to a dVLM is also feasible, achieving performance comparable to that of the same AR model finetuned with standard autoregressive visual instruction tuning. To enable practical open-ended generation, we further integrate block decoding, which supports arbitrary-length outputs and KV-cache reuse for faster inference. Our experiments demonstrate that despite training with less than 5% of the data required by prior methods, DiffusionVL achieves a comprehensive performance improvement, with a 34.4% gain on the MMMU-Pro (vision) benchmark and 37.5% gain on the MME (Cog.) benchmark, alongside a 2x inference speedup. The model and code are released at https://github.com/hustvl/DiffusionVL.

comment: 12 pages, 4 figures, conference or other essential info

♻ ☆ LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction

Shuwei Huang, Shizhuo Liu, Zijun Wei

Diffusion-based image super-resolution (SR), which aims to reconstruct high-resolution (HR) images from corresponding low-resolution (LR) observations, faces a fundamental trade-off between inference efficiency and reconstruction quality. The state-of-the-art residual-shifting diffusion framework achieves efficient 4-step inference, yet suffers from severe performance degradation in compact sampling trajectories. This is mainly attributed to two core limitations: the inherent suboptimality of unconstrained random Gaussian noise in intermediate steps, which leads to error accumulation and insufficient LR prior guidance, and the initialization bias caused by naive bicubic upsampling. In this paper, we propose LPNSR, a prior-enhanced efficient diffusion framework to address these issues. We first mathematically derive the closed-form analytical solution of the optimal intermediate noise for the residual-shifting diffusion paradigm, and accordingly design an LR-guided multi-input-aware noise predictor to replace random Gaussian noise, embedding LR structural priors into the reverse process while fully preserving the framework's core efficient residual-shifting mechanism. We further mitigate initial bias with a high-quality pre-upsampling network to optimize the diffusion starting point. With a compact 4-step trajectory, LPNSR can be optimized in an end-to-end manner. Extensive experiments demonstrate that LPNSR achieves state-of-the-art perceptual performance on both synthetic and real-world datasets, without relying on any large-scale text-to-image priors. The source code of our method can be found at https://github.com/Faze-Hsw/LPNSR.

♻ ☆ Unsupervised Modular Adaptive Region Growing and RegionMix Classification for Wind Turbine Segmentation

Raül Pérez-Gonzalo, Riccardo Magro, Andreas Espersen, Antonio Agudo

Reliable operation of wind turbines requires frequent inspections, as even minor surface damages can degrade aerodynamic performance, reduce energy output, and accelerate blade wear. Central to automating these inspections is the accurate segmentation of turbine blades from visual data. This task is traditionally addressed through dense, pixel-wise deep learning models. However, such methods demand extensive annotated datasets, posing scalability challenges. In this work, we introduce an annotation-efficient segmentation approach that reframes the pixel-level task into a binary region classification problem. Image regions are generated using a fully unsupervised, interpretable Modular Adaptive Region Growing technique, guided by image-specific Adaptive Thresholding and enhanced by a Region Merging process that consolidates fragmented areas into coherent segments. To improve generalization and classification robustness, we introduce RegionMix, an augmentation strategy that synthesizes new training samples by combining distinct regions. Our framework demonstrates state-of-the-art segmentation accuracy and strong cross-site generalization by consistently segmenting turbine blades across distinct windfarms.

comment: Accepted to WACV 2026

♻ ☆ SceneDiff: A Benchmark and Method for Multiview Object Change Detection

Yuqun Wu, Chih-hao Lin, Henry Che, Aditi Tiwari, Chuhang Zou, Shenlong Wang, Derek Hoiem

We investigate the problem of identifying objects that have been added, removed, or moved between a pair of captures (images or videos) of the same scene at different times. Accurately identifying verifiable changes is extremely challenging -- some objects may appear to be missing because they are occluded or out of frame, while others may appear different due to large viewpoint changes. To study this problem, we introduce the SceneDiff Benchmark, the first multiview change detection dataset for scenes captured along different camera trajectories, comprising 350 diverse video pairs with dense object instance-level annotations. We also introduce the SceneDiff algorithm, a training-free approach that solves for image poses, segments images into objects, and compares them using semantic and geometric features. By building on pretrained models, SceneDiff generalizes across domains without retraining and naturally improves as the underlying models advance. Experiments on multiview and two-view benchmarks demonstrate that our method outperforms existing approaches by large margins (53.0\% and 30.6\% relative AP improvements). Project page: https://yuqunw.github.io/SceneDiff

♻ ☆ SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models

Haowen Liu, Shaoxiong Yao, Haonan Chen, Jiawei Gao, Jiayuan Mao, Jia-Bin Huang, Yilun Du

Vision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities. However, they lack a grounded understanding of physical dynamics. This limitation arises from training VLMs on static internet-scale visual-language data that contain no causal interactions or action-conditioned changes. Consequently, it remains challenging to leverage VLMs for fine-grained robotic manipulation tasks that require physical understanding, reasoning, and corresponding action planning. To overcome this, we present SIMPACT, a test-time, SIMulation-enabled ACTion Planning framework that equips VLMs with physical reasoning through simulation-in-the-loop world modeling, without requiring any additional training. From a single RGB-D observation, SIMPACT efficiently constructs physics simulations, enabling the VLM to propose informed actions, observe simulated rollouts, and iteratively refine its reasoning. By integrating language reasoning with physics prediction, our simulation-enabled VLM can understand contact dynamics and action outcomes in a physically grounded way. Our method demonstrates state-of-the-art performance on five challenging, real-world rigid-body and deformable manipulation tasks that require fine-grained physical reasoning, outperforming existing general-purpose robotic manipulation models. Our results demonstrate that embedding physics understanding via efficient simulation into VLM reasoning at test time offers a promising path towards generalizable embodied intelligence. Project webpage can be found at https://simpact-bot.github.io

comment: Accepted to CVPR 2026; camera-ready version

♻ ☆ ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval

Tianyu Yang, Chenwei He, Xiangzhao Hao, Tianyue Wang, Jiarui Guo, Haiyun Guo, Leigang Qu, Jinqiao Wang, Tat-Seng Chua

Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models (VLMs) struggle with cross-modality compositional reasoning required for this task. While adapting generative Multimodal Large Language Models (MLLMs) for retrieval offers a promising direction, we identify that this strategy overlooks a fundamental issue: compressing a generative MLLM into a single-embedding discriminative retriever triggers a paradigm conflict, which leads to Capability Degradation - the deterioration of native fine-grained reasoning after retrieval adaptation. To address this challenge, we propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline: First, we diagnose cognitive blind spots of the retriever via self-guided informative instance mining. Next, we generate corrective instructions and triplets by prompting the foundation MLLM and conduct quality control with VQA-based consistency filtering. Finally, we refine the retriever through continual training on these triplets with a grouped contrastive scheme, thereby internalizing fine-grained visual-semantic distinctions and realigning the discriminative embedding space of retriever with intrinsic compositional reasoning within the MLLM. Extensive experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance. Code is available at https://github.com/RemRico/Recall.

comment: Accepted to CVPR 2026

♻ ☆ TransFIRA: Transfer Learning for Face Image Recognizability Assessment

Allen Tu, Kartik Narayan, Joshua Gleason, Jennifer Xu, Matthew Meyn, Tom Goldstein, Vishal M. Patel

Face recognition in unconstrained environments such as surveillance, video, and web imagery must contend with extreme variation in pose, blur, illumination, and occlusion, where conventional visual quality metrics fail to predict whether inputs are truly recognizable to the deployed encoder. Existing FIQA methods typically rely on visual heuristics, curated annotations, or computationally intensive generative pipelines, leaving their predictions detached from the encoder's decision geometry. We introduce TransFIRA (Transfer Learning for Face Image Recognizability Assessment), a lightweight and annotation-free framework that grounds recognizability directly in embedding space. TransFIRA delivers three advances: (i) a definition of recognizability via class-center similarity (CCS) and class-center angular separation (CCAS), yielding the first natural, decision-boundary-aligned criterion for filtering and weighting; (ii) a recognizability-informed aggregation strategy that achieves state-of-the-art verification accuracy on BRIAR and IJB-C while nearly doubling correlation with true recognizability, all without external labels, heuristics, or backbone-specific training; and (iii) new extensions beyond faces, including encoder-grounded explainability that reveals how degradations and subject-specific factors affect recognizability, and the first method for body recognizability assessment. Experiments confirm state-of-the-art results on faces, strong performance on body recognition, and robustness under cross-dataset shifts and out-of-distribution evaluation. Together, these contributions establish TransFIRA as a unified, geometry-driven framework for recognizability assessment that is encoder-specific, accurate, interpretable, and extensible across modalities, significantly advancing FIQA in accuracy, explainability, and scope.

comment: Project Page: https://transfira.github.io/

♻ ☆ LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting

Xuan Deng, Xiandong Meng, Hengyu Man, Qiang Zhu, Tiange Zhang, Debin Zhao, Xiaopeng Fan

Although 3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, its prohibitive storage overhead severely hinders practical deployment. Recent anchor-based 3DGS compression schemes reduce gaussina redundancy through ome advanced context models. However, overlook explicit geometric dependencies, leading to structural degradation and suboptimal rate-distortion performance. In this paper, we propose LG-HCC, a geometry-aware 3DGS compression framework that incorporates inter-anchor geometric correlations into anchor pruning and entropy coding for compact representation. Specifically, we introduce an Neighborhood-Aware Anchor Pruning (NAAP) strategy, which evaluates anchor importance via weighted neighborhood feature aggregation and merges redundant anchors into salient neighbors, yielding a compact yet geometry-consistent anchor set. Building upon this optimized structure, we further develop a hierarchical entropy coding scheme, in which coarse-to-fine priors are exploited through a lightweight Geometry-Guided Convolution (GG-Conv) operator to enable spatially adaptive context modeling and rate-distortion optimization. Extensive experiments demonstrate that LG-HCC effectively resolves the structure preservation bottleneck, maintaining superior geometric integrity and rendering fidelity over state-of-the-art anchor-based compression approaches.

comment: 10

♻ ☆ CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition

Muhammad Osama Zeeshan, Masoumeh Sharafi, Benoît Savary, Alessandro Lameiras Koerich, Marco Pedersoli, Eric Granger

Personalization in emotion recognition (ER) is essential for an accurate interpretation of subtle and subject-specific expressive patterns. Recent advances in vision-language models (VLMs) such as CLIP demonstrate strong potential for leveraging joint image-text representations in ER. However, CLIP-based methods either depend on CLIP's contrastive pretraining or on LLMs to generate descriptive text prompts, which are noisy, computationally expensive, and fail to capture fine-grained expressions, leading to degraded performance. In this work, we leverage Action Units (AUs) as structured textual prompts within CLIP to model fine-grained facial expressions. AUs encode the subtle muscle activations underlying expressions, providing localized and interpretable semantic cues for more robust ER. We introduce CLIP-AU, a lightweight AU-guided temporal learning method that integrates interpretable AU semantics into CLIP. It learns generic, subject-agnostic representations by aligning AU prompts with facial dynamics, enabling fine-grained ER without CLIP fine-tuning or LLM-generated text supervision. Although CLIP-AU models fine-grained AU semantics, it does not adapt to subject-specific variability in subtle expressions. To address this limitation, we propose CLIP-AUTT, a video-based test-time personalization method that dynamically adapts AU prompts to videos from unseen subjects. By combining entropy-guided temporal window selection with prompt tuning, CLIP-AUTT enables subject-specific adaptation while preserving temporal consistency. Our extensive experiments on three challenging video-based subtle ER datasets, BioVid, StressID, and BAH, indicate that CLIP-AU and CLIP-AUTT outperform state-of-the-art CLIP-based FER and TTA methods, achieving robust and personalized subtle ER. Our code is publicly available at: https://github.com/osamazeeshan/CLIP-AUTT.

♻ ☆ LatentFM: A Latent Flow Matching Approach for Generative Medical Image Segmentation

Huynh Trinh Ngoc, Hoang Anh Nguyen Kim, Toan Nguyen Hai, Long Tran Quoc

Generative models have achieved remarkable progress with the emergence of flow matching (FM). It has demonstrated strong generative capabilities and attracted significant attention as a simulation-free flow-based framework capable of learning exact data densities. Motivated by these advances, we propose LatentFM, a flow-based model operating in the latent space for medical image segmentation. To model the data distribution, we first design two variational autoencoders (VAEs) to encode both medical images and their corresponding masks into a lower-dimensional latent space. We then estimate a conditional velocity field that guides the flow based on the input image. By sampling multiple latent representations, our method synthesizes diverse segmentation outputs whose pixel-wise variance reliably captures the underlying data distribution, enabling both highly accurate and uncertainty-aware predictions. Furthermore, we generate confidence maps that quantify the model certainty, providing clinicians with richer information for deeper analysis. We conduct experiments on two datasets, ISIC-2018 and CVC-Clinic, and compare our method with several prior baselines, including both deterministic and generative approach models. Through comprehensive evaluations, both qualitative and quantitative results show that our approach achieves superior segmentation accuracy while remaining highly efficient in the latent space.

♻ ☆ InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models

Hongyuan Tao, Bencheng Liao, Shaoyu Chen, Haoran Yin, Qian Zhang, Wenyu Liu, Xinggang Wang

Vision-Language Models (VLMs) are increasingly tasked with ultra-long multimodal understanding. While linear architectures offer constant computation and memory footprints, they often struggle with high-frequency visual perception compared to standard Transformers. To bridge this gap, we introduce \textbf{InfiniteVL}. We first develop a hybrid base model called \textbf{InfiniteVL-Base} that interleaves a small fraction of Full Attention layers with Gated DeltaNet. Empowered by a tailored distillation and fine-tuning strategy, InfiniteVL-Base matches the fundamental multimodal performance of equivalent Transformers while achieving a \textbf{1.7$\times$} decoding speedup. However, the quadratic complexity of the retained Full Attention inevitably becomes an efficiency bottleneck when scaling to ultra long context. To break this barrier, we propose a novel Long-Sequence Architectural Fine-Tuning strategy that seamlessly transforms the dense attention into vision-specific sparse mechanisms. This yields two specialized variants: \textbf{InfiniteVL-Offline} for offline retrieval and \textbf{InfiniteVL-Online} for online streaming. By eliminating the computation explosion of global attention without sacrificing high-frequency visual recall, InfiniteVL-Offline achieves Transformer-level length generalization with a \textbf{5x} prefill acceleration at 256K context. Concurrently, InfiniteVL-Online delivers robust streaming perception with a constant memory footprint and a real-time throughput of \textbf{25} FPS. Code and models are available at https://github.com/hustvl/InfiniteVL.

comment: 20 pages, 8 figures, conference or other essential info

♻ ☆ ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning

Huanxuan Liao, Zhongtao Jiang, Yupu Hao, Yuqiao Tan, Shizhu He, Ben Wang, Jun Zhao, Kun Xu, Kang Liu

Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatial resolution and long temporal context prohibitive. We argue that the bottleneck lies not in how post-encoding representations are compressed but in the volume of pixels the encoder receives, and address it with ResAdapt, an Input-side adaptation framework that learns how much visual budget each frame should receive before encoding. ResAdapt couples a lightweight Allocator with an unchanged MLLM backbone, so the backbone retains its native visual-token interface while receiving an operator-transformed input. We formulate allocation as a contextual bandit and train the Allocator with Cost-Aware Policy Optimization (CAPO), which converts sparse rollout feedback into a stable accuracy-cost learning signal. Across budget-controlled video QA, temporal grounding, and image reasoning tasks, ResAdapt improves low-budget operating points and often lies on or near the efficiency-accuracy frontier, with the clearest gains on reasoning-intensive benchmarks under aggressive compression. Notably, ResAdapt supports up to 16x more frames at the same visual budget while delivering over 15% performance gain. Code is available at https://github.com/Xnhyacinth/ResAdapt.

comment: work in progress

♻ ☆ DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching

Jiayi Chen, Wenxuan Song, Shuai Chen, Jingbo Wang, Zhijun Li, Haoang Li

Vision--Language--Action (VLA) models that encode actions using a discrete tokenization scheme are increasingly adopted for robotic manipulation, but existing decoding paradigms remain fundamentally limited. Whether actions are decoded sequentially by autoregressive VLAs or in parallel by discrete diffusion VLAs, once a token is generated, it is typically fixed and cannot be revised in subsequent iterations, so early token errors cannot be effectively corrected later. We propose DFM-VLA, a discrete flow matching VLA for iterative refinement of action tokens. DFM-VLA~models a token-level probability velocity field that dynamically updates the full action sequence across refinement iterations. We investigate two ways to construct the velocity field: an auxiliary velocity-head formulation and an action-embedding-guided formulation. Our framework further adopts a two-stage decoding strategy with an iterative refinement stage followed by deterministic validation for stable convergence. Extensive experiments on CALVIN, LIBERO, and real-world manipulation tasks show that DFM-VLA consistently outperforms strong autoregressive, discrete diffusion, and continuous diffusion baselines in manipulation performance while retaining high inference efficiency. In particular, DFM-VLA achieves an average success length of 4.44 on CALVIN and an average success rate of 95.7\% on LIBERO, highlighting the value of action refinement via discrete flow matching for robotic manipulation. Our project is available https://chris1220313648.github.io/DFM-VLA/

♻ ☆ Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models ICLR2026

Sen Ye, Mengde Xu, Shuyang Gu, Di He, Liwei Wang, Han Hu

Current research in multimodal models faces a key challenge where enhancing generative capabilities often comes at the expense of understanding, and vice versa. We analyzed this trade-off and identify the primary cause might be the potential conflict between generation and understanding, which creates a competitive dynamic within the model. To address this, we propose the Reason-Reflect-Refine (R3) framework. This innovative algorithm re-frames the single-step generation task into a multi-step process of "generate-understand-regenerate". By explicitly leveraging the model's understanding capability during generation, we successfully mitigate the optimization dilemma, achieved stronger generation results and improved understanding ability which are related to the generation process. This offers valuable insights for designing next-generation unified multimodal models. Code is available at https://github.com/sen-ye/R3.

comment: Accepted to ICLR2026

♻ ☆ Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting

Tao Han, Zhibin Wen, Zhenghao Chen, Dazhao Du, Song Guo, Lei Bai

The development of Time-Series Forecasting (TSF) models is often constrained by the lack of comprehensive datasets, especially in Global Station Weather Forecasting (GSWF), where existing datasets are small, temporally short, and spatially sparse. To address this, we introduce WEATHER-5K, a large-scale observational weather dataset that better reflects real-world conditions, supporting improved model training and evaluation. While recent TSF methods perform well on benchmarks, they lag behind operational Numerical Weather Prediction systems in capturing complex weather dynamics and extreme events. We propose PhysicsFormer, a physics-informed forecasting model combining a dynamic core with a Transformer residual to predict future weather states. Physical consistency is enforced via pressure-wind alignment and energy-aware smoothness losses, ensuring plausible dynamics while capturing complex temporal patterns. We benchmark PhysicsFormer and other TSF models against operational systems across several weather variables, extreme event prediction, and model complexity, providing a comprehensive assessment of the gap between academic TSF models and operational forecasting. The dataset and benchmark implementation are available at: https://github.com/taohan10200/WEATHER-5K.

comment: 34 pages, 20 figures

♻ ☆ $R_\text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation

Linqian Fan, Peiqin Sun, Tiancheng Wen, Shun Lu, Chengru Song

Diffusion models achieve state-of-the-art generative performance but are fundamentally bottlenecked by their slow, iterative sampling process. While diffusion distillation techniques enable high-fidelity, few-step generation, traditional objectives often restrict the student's performance by anchoring it solely to the teacher. Recent approaches have attempted to break this ceiling by integrating Reinforcement Learning (RL), typically through a simple summation of distillation and RL objectives. In this work, we propose a novel paradigm by re-conceptualizing distribution matching as a reward, denoted as $R_\text{dm}$. This unified perspective bridges the algorithmic gap between Diffusion Matching Distillation (DMD) and RL, providing several primary benefits. (1) Enhanced Optimization Stability: We introduce Group Normalized Distribution Matching (GNDM), which adapts standard RL group normalization to stabilize $R_\text{dm}$ estimation. By leveraging group-mean statistics, GNDM establishes a more robust and effective optimization direction. (2) Seamless Reward Integration: Our reward-centric formulation inherently supports adaptive weighting mechanisms, allowing for the fluid combination of DMD with external reward models. (3) Improved Sampling Efficiency: By aligning with RL principles, the framework readily incorporates Importance Sampling (IS), leading to a significant boost in sampling efficiency. Extensive experiments demonstrate that GNDM outperforms vanilla DMD, reducing the FID by 1.87. Furthermore, our multi-reward variant, GNDMR, surpasses existing baselines by striking an optimal balance between aesthetic quality and fidelity, achieving a peak HPS of 30.37 and a low FID-SD of 12.21. Ultimately, $R_\text{dm}$ provides a flexible, stable, and efficient framework for real-time, high-fidelity synthesis. Codes are coming soon.

♻ ☆ Noise-adapted Neural Operator for Robust Non-Line-of-Sight Imaging

Lianfang Wang, Kuilin Qin, Xueying Liu, Huibin Chang, Yong Wang, Yuping Duan

This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Computational imaging, especially non-line-of-sight (NLOS) imaging, the extraction of information from obscured or hidden scenes is achieved through the utilization of indirect light signals resulting from multiple reflections or scattering. The inherently weak nature of these signals, coupled with their susceptibility to noise, necessitates the integration of physical processes to ensure accurate reconstruction. This paper presents a parameterized inverse problem framework tailored for large-scale linear problems in 3D imaging reconstruction. Initially, a noise estimation module is employed to adaptively assess the noise levels present in transient data. Subsequently, a parameterized neural operator is developed to approximate the inverse mapping, facilitating end-to-end rapid image reconstruction. Our 3D image reconstruction framework, grounded in operator learning, is constructed through deep algorithm unfolding, which not only provides commendable model interpretability but also enables dynamic adaptation to varying noise levels in the acquired data, thereby ensuring consistently robust and accurate reconstruction outcomes. Furthermore, we introduce a novel method for the fusion of global and local spatiotemporal data features. By integrating structural and detailed information, this method significantly enhances both accuracy and robustness. Comprehensive numerical experiments conducted on both simulated and real datasets substantiate the efficacy of the proposed method. It demonstrates remarkable performance with fast scanning data and sparse illumination point data, offering a viable solution for NLOS imaging in complex scenarios.

♻ ☆ DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams

Ginés Carreto Picón, Peng Yuan Zhou, Qi Zhang, Alexandros Iosifidis

Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high performance, low-latency inference on devices with limited resources. In particular, stream data inference is typically performed over a sliding temporal window, leading to highly redundant computations. While the recent Continual Transformers started addressing this issue, they can be effectively used only in shallow models, which limits their scope and generalization power. In this paper, we propose the Deep Continual Transformer (DeepCoT), a redundancy-free encoder attention mechanism that can be applied over existing deep encoder architectures with minimal changes. In our experiments over audio, video, and text streams, we show that DeepCoTs retain comparative performance to their non-continual baselines while offering a linear computational cost for all Transformer layers, which reduces up to two orders of magnitude in the running time compared to previous efficient models.

comment: 15 pages, 5 figures

♻ ☆ From Plausibility to Verifiability: Risk-Controlled Generative OCR for Vision-Language Models

Weile Gong, Yiping Zuo, Zijian Lu, Xin He, Weibei Fan, Lianyong Qi, Shi Jin

Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors semantic plausibility, whereas OCR requires outputs that are visually grounded and geometrically verifiable. This mismatch produces severe errors, especially over-generation and unsupported substitutions, creating deployment risk even when benchmark accuracy remains high. We therefore formulate frozen VLM OCR as a selective accept/abstain problem and propose a model-agnostic Geometric Risk Controller. The controller probes multiple structured views of the same input, applies lightweight structural screening, and accepts a transcription only when cross-view consensus and stability satisfy predefined criteria, yielding a small family of operating points. Experiments on frozen VLM backbones and standard OCR benchmarks show consistent reductions in extreme-error risk and catastrophic over-generation at predictable coverage costs. Reliable deployment of generative OCR with frozen VLMs benefits from explicit system-level risk control rather than unconstrained generation.

comment: 10 pages, 5 figures, 5 tables

♻ ☆ The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Weichen Fan, Haiwen Diao, Quan Wang, Dahua Lin, Ziwei Liu

comment: Code link: https://github.com/WeichenFan/UAE

♻ ☆ EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval

Yuhan Chen, Pengwen Dai, Chuan Wang, Dayan Wu, Xiaochun Cao

comment: Accepted at CVPR 2026

♻ ☆ SleepVLM: Explainable and Rule-Grounded Sleep Staging via a Vision-Language Model

Guifeng Deng, Pan Wang, Jiquan Wang, Shuying Rao, Junyi Xie, Wanjun Guo, Tao Li, Haiteng Jiang

While automated sleep staging has achieved expert-level accuracy, its clinical adoption is hindered by a lack of auditable reasoning. We introduce SleepVLM, a rule-grounded vision-language model (VLM) designed to stage sleep from multi-channel polysomnography (PSG) waveform images while generating clinician-readable rationales based on American Academy of Sleep Medicine (AASM) scoring criteria. Utilizing waveform-perceptual pre-training and rule-grounded supervised fine-tuning, SleepVLM achieved Cohen's kappa scores of 0.767 on an held out test set (MASS-SS1) and 0.743 on an external cohort (ZUAMHCS), matching state-of-the-art performance. Expert evaluations further validated the quality of the model's reasoning, with mean scores exceeding 4.0/5.0 for factual accuracy, evidence comprehensiveness, and logical coherence. By coupling competitive performance with transparent, rule-based explanations, SleepVLM may improve the trustworthiness and auditability of automated sleep staging in clinical workflows. To facilitate further research in interpretable sleep medicine, we release MASS-EX, a novel expert-annotated dataset.

comment: Under review

♻ ☆ Improving Liver Disease Diagnosis with SNNDeep: A Custom Spiking Neural Network Using Diverse Learning Algorithms

Zofia Rudnicka, Janusz Szczepanski, Agnieszka Pregowska

Purpose: Spiking neural networks (SNNs) have recently gained attention as energy-efficient, biologically plausible alternatives to conventional deep learning models. Their application in high-stakes biomedical imaging remains almost entirely unexplored. Methods: This study introduces SNNDeep, the first tailored SNN specifically optimized for binary classification of liver health status from computed tomography (CT) features. To ensure clinical relevance and broad generalizability, the model was developed and evaluated using the Task03\Liver dataset from the Medical Segmentation Decathlon (MSD), a standardized benchmark widely used for assessing performance across diverse medical imaging tasks. We benchmark three fundamentally different learning algorithms, namely Surrogate Gradient Learning, the Tempotron rule, and Bio-Inspired Active Learning across three architectural variants: a fully customized low-level model built from scratch, and two implementations using leading SNN frameworks, i.e., snnTorch and SpikingJelly. Hyperparameter optimization was performed using Optuna. Results: Our results demonstrate that the custom-built SNNDeep consistently outperforms framework-based implementations, achieving a maximum validation accuracy of 98.35%, superior adaptability across learning rules, and significantly reduced training overhead. Conclusion:This study provides the first empirical evidence that low-level, highly tunable SNNs can surpass standard frameworks in medical imaging, especially in data-limited, temporally constrained diagnostic settings, thereby opening a new pathway for neuro-inspired AI in precision medicine.

♻ ☆ Universal Skeleton Understanding via Differentiable Rendering and MLLMs

Ziyi Wang, Peiming Li, Xinshun Wang, Yang Tang, Kai-Kuang Ma, Mengyuan Liu

Multimodal large language models (MLLMs) exhibit strong visual-language reasoning, yet remain confined to their native modalities and cannot directly process structured, non-visual data such as human skeletons. Existing methods either compress skeleton dynamics into lossy feature vectors for text alignment, or quantize motion into discrete tokens that generalize poorly across heterogeneous skeleton formats. We present SkeletonLLM, which achieves universal skeleton understanding by translating arbitrary skeleton sequences into the MLLM's native visual modality. At its core is DrAction, a differentiable, format-agnostic renderer that converts skeletal kinematics into compact image sequences. Because the pipeline is end-to-end differentiable, MLLM gradients can directly guide the rendering to produce task-informative visual tokens. To further enhance reasoning capabilities, we introduce a cooperative training strategy: Causal Reasoning Distillation transfers structured, step-by-step reasoning from a teacher model, while Discriminative Finetuning sharpens decision boundaries between confusable actions. SkeletonLLM demonstrates strong generalization on diverse tasks including recognition, captioning, reasoning, and cross-format transfer -- suggesting a viable path for applying MLLMs to non-native modalities. Code will be released upon acceptance.

comment: 32 pages, 15 figures

♻ ☆ SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World

Jungho Kim, Jiyong Oh, Seunghoon Yu, Hongjae Shin, Donghyuk Kwak, Jun Won Choi

The end-to-end (E2E) paradigm, which maps sensor inputs directly to driving decisions, has recently attracted significant attention due to its unified modeling capability and scalability. However, ensuring safety in this unified framework remains one of the most critical challenges. In this work, we propose SafeDrive, an E2E planning framework designed to perform explicit and interpretable safety reasoning through a trajectory-conditioned Sparse World Model. SafeDrive comprises two complementary networks: the Sparse World Network (SWNet) and the Fine-grained Reasoning Network (FRNet). SWNet constructs trajectory-conditioned sparse worlds that simulate the future behaviors of critical dynamic agents and road entities, providing interaction-centric representations for downstream reasoning. FRNet then evaluates agent-specific collision risks and temporal adherence to drivable regions, enabling precise identification of safety-critical events across future timesteps. SafeDrive achieves state-of-the-art performance on both open-loop and closed-loop benchmarks. On NAVSIM, it records a PDMS of 91.6 and an EPDMS of 87.5, with only 61 collisions out of 12,146 scenarios (0.5%). On Bench2Drive, SafeDrive attains a 66.8% driving score.

comment: Accepted to CVPR 2026, 19 pages, 9 figures

♻ ☆ A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models

Mujtaba Hussain Mirza, Antonio D'Orazio, Odelia Melamed, Iacopo Masi

Despite the rapid progress in multimodal models and Large Visual-Language Models (LVLM), they remain highly susceptible to adversarial perturbations, raising serious concerns about their reliability in real-world use. While adversarial training has become the leading paradigm for building models that are robust to adversarial attacks, Test-Time Transformations (TTT) have emerged as a promising strategy to boost robustness at inference. In light of this, we propose Energy-Guided Test-Time Transformation (ET3), a lightweight, training-free defense that enhances the robustness by minimizing the energy of the input samples. Our method is grounded in a theory that proves our transformation succeeds in classification under reasonable assumptions. We present extensive experiments demonstrating that ET3 provides a strong defense for classifiers, zero-shot classification with CLIP, and also for boosting the robustness of LVLMs in tasks such as Image Captioning and Visual Question Answering. Code is available at github.com/OmnAI-Lab/Energy-Guided-Test-Time-Defense .

comment: Accepted at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026, Main Conference

♻ ☆ Detection of Adversarial Attacks in Robotic Perception

Ziad Sharawy, Mohammad Nakshbandi, Sorin Mihai Grigorescu

Deep Neural Networks (DNNs) achieve strong performance in semantic segmentation for robotic perception but remain vulnerable to adversarial attacks, threatening safety-critical applications. While robustness has been studied for image classification, semantic segmentation in robotic contexts requires specialized architectures and detection strategies.

comment: 9 pages, 6 figures. Accepted and presented at STE 2025, Transilvania University of Brasov, Romania

♻ ☆ VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval ACL 2026

Diogo Glória-Silva, David Semedo, João Maglhães

We introduce VIGiA, a novel multimodal dialogue model designed to understand and reason over complex, multi-step instructional video action plans. Unlike prior work which focuses mainly on text-only guidance, or treats vision and language in isolation, VIGiA supports grounded, plan-aware dialogue that requires reasoning over visual inputs, instructional plans, and interleaved user interactions. To this end, VIGiA incorporates two key capabilities: (1) multimodal plan reasoning, enabling the model to align uni- and multimodal queries with the current task plan and respond accurately; and (2) plan-based retrieval, allowing it to retrieve relevant plan steps in either textual or visual representations. Experiments were done on a novel dataset with rich Instructional Video Dialogues aligned with Cooking and DIY plans. Our evaluation shows that VIGiA outperforms existing state-of-the-art models on all tasks in a conversational plan guidance setting, reaching over 90\% accuracy on plan-aware VQA.

comment: Published at EACL 2026 Findings

♻ ☆ Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators

Alaa Zniber, Arne Symons, Ouassim Karrakchou, Marian Verhelst, Mounir Ghogho

Deployment of dynamic neural networks on edge accelerators requires careful consideration of hardware constraints beyond conventional complexity metrics such as Multiply-Accumulate operations. In Early-Exiting Neural Networks (EENN), exit placement, quantization level, and hardware workload mapping interact in non-trivial ways, influencing memory traffic, accelerator utilization, and ultimately energy-latency trade-offs. These interactions remain insufficiently understood in existing Neural Architecture Search (NAS) approaches, which typically rely on proxy metrics or hardware-in-the-loop evaluation. This work presents a hardware-algorithm co-design framework for EENN that explicitly models the interplay between quantization, exit configuration, and multi-core accelerator mapping. Using analytical design space exploration, we characterize how small architectural variations can induce disproportionate changes in hardware efficiency due to tensor dimension alignment and dataflow effects. Building on this analysis, we formulate EENN deployment as a constrained multi-objective optimization problem balancing accuracy, energy-latency product, exit overhead, and dynamic inference behavior. Experimental results on CIFAR-10 demonstrate that the proposed framework identifies architectures achieving over 50\% reduction in energy-latency product compared to static baselines under 8-bit quantization. The results highlight the importance of deployment-aware co-design for dynamic inference on heterogeneous edge platforms.

♻ ☆ GERD: Geometric event response data generation

Jens Egholm Pedersen, Dimitris Korakovounis, Jörg Conradt

Event-based vision sensors offer high time resolution, high dynamic range, and low power consumption, yet event-based vision models lag behind conventional frame-based vision methods. We argue that this gap is partly due to the lack of principled study of the transformation groups that govern event-based visual streams. Motivated by the role that geometric and group-theoretic methods have played in advancing computer vision, we present GERD: a simulator for generating event-based recordings of objects under precisely controlled affine, Galilean, and temporal scaling transformations. By providing ground-truth transformations at each timestep, GERD enables hypothesis-driven and controlled studies of geometric properties that are otherwise impossible to isolate in real-world datasets. The simulator supports three noise models and sub-pixel motion as a complement to real sensor datasets. We demonstrate its use in training and evaluating models with geometric guarantees and release GERD as an open tool available at github.com/ncskth/gerd

♻ ☆ SVBench: Evaluation of Video Generation Models on Social Reasoning

Wenshuo Peng, Gongxuan Wang, Tianmeng Yang, Chuanhao Li, Xiaojie Xu, Hui He, Kaipeng Zhang

Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coherent behavior. Unlike humans, who readily infer intentions, beliefs, emotions, and social norms from brief visual cues, current models often generate literal scenes without capturing the underlying causal and psychological dynamics. To systematically assess this limitation, we introduce the first benchmark for social reasoning in video generation. Grounded in developmental and social psychology, the benchmark covers thirty classic social cognition paradigms spanning seven core dimensions: mental-state inference, goal-directed action, joint attention, social coordination, prosocial behavior, social norms, and multi-agent strategy. To operationalize these paradigms, we build a fully training-free agent-based pipeline that distills the reasoning structure of each paradigm, synthesizes diverse video-ready scenarios, enforces conceptual neutrality and difficulty control through cue-based critique, and evaluates generated videos with a high-capacity VLM judge along five interpretable dimensions of social reasoning. Using this framework, we conduct the first large-scale evaluation of seven state-of-the-art video generation systems. Results show a clear gap between surface-level plausibility and deeper social reasoning, suggesting that current models remain limited in their ability to generate socially grounded behavior. https://github.com/Gloria2tt/SVBench-Evaluation

comment: 10pages

♻ ☆ StreetTree: A Large-Scale Global Benchmark for Fine-Grained Tree Species Classification

Jiapeng Li, Yingjing Huang, Fan Zhang, Yu liu

The fine grained classification of street trees is a crucial task for urban planning, streetscape management, and the assessment of urban ecosystem services. However, progress in this field has been hindered by the lack of large scale, geographically diverse, and publicly available benchmark datasets specifically designed for street trees. To address this critical gap, we introduce StreetTree, the world's first large scale benchmark dataset dedicated to fine grained street tree classification. The dataset contains over 12 million images covering more than 8,300 common street tree species, collected from urban streetscapes across 133 countries spanning five continents, and supplemented with expert verified observational data. StreetTree poses challenges for pretrained vision models under complex urban environments including high inter species visual similarity, long tailed natural distributions, significant intra class variations caused by seasonal changes, and diverse imaging conditions such as lighting, occlusions from buildings, and varying camera angles. In addition, we provide a hierarchical taxonomy (order, family, genus, and species) to support research in hierarchical classification and representation learning. Through extensive experiments with various vision models, we establish solid baselines and reveal the limitations of existing methods in handling such real world complexities. We believe that StreetTree will serve as a key resource for driving new advancements at the intersection of computer vision and urban science.

♻ ☆ CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design ICLR 2026

Hui Zhang, Dexiang Hong, Maoke Yang, Yutao Cheng, Zhao Zhang, Weidong Chen, Jie Shao, Xinglong Wu, Zuxuan Wu, Yu-Gang Jiang

Graphic design plays a vital role in visual communication across advertising, marketing, and multimedia entertainment. Prior work has explored automated graphic design generation using diffusion models, aiming to streamline creative workflows and democratize design capabilities. However, complex graphic design scenarios require accurately adhering to design intent specified by multiple heterogeneous user-provided elements (\eg images, layouts, and texts), which pose multi-condition control challenges for existing methods. Specifically, previous single-condition control models demonstrate effectiveness only within their specialized domains but fail to generalize to other conditions, while existing multi-condition methods often lack fine-grained control over each sub-condition and compromise overall compositional harmony. To address these limitations, we introduce CreatiDesign, a systematic solution for automated graphic design covering both model architecture and dataset construction. First, we design a unified multi-condition driven architecture that enables flexible and precise integration of heterogeneous design elements with minimal architectural modifications to the base diffusion model. Furthermore, to ensure that each condition precisely controls its designated image region and to avoid interference between conditions, we propose a multimodal attention mask mechanism. Additionally, we develop a fully automated pipeline for constructing graphic design datasets, and introduce a new dataset with 400K samples featuring multi-condition annotations, along with a comprehensive benchmark. Experimental results show that CreatiDesign outperforms existing models by a clear margin in faithfully adhering to user intent.

comment: Accepted by ICLR 2026

♻ ☆ Generative AI Enables Structural Brain Network Construction from fMRI via Symmetric Diffusion Learning

Qiankun Zuo, Bangjun Lei, Wanyu Qiu, Changhong Jing, Jin Hong, Shuqiang Wang

Mapping from functional connectivity (FC) to structural connectivity (SC) can facilitate multimodal brain network fusion and discover potential biomarkers for clinical implications. However, it is challenging to directly bridge the reliable non-linear mapping relations between SC and functional magnetic resonance imaging (fMRI). In this paper, a novel symmetric diffusive generative adversarial network-based fMRI-to-SC (DiffGAN-F2S) model is proposed to predict SC from brain fMRI in a unified framework. To be specific, the proposed DiffGAN-F2S leverages denoising diffusion probabilistic models (DDPMs) and adversarial learning to efficiently generate symmetric and high-fidelity SC through a few steps from fMRI. By designing the dual-channel multi-head spatial attention (DMSA) and graph convolutional modules, the symmetric graph generator first captures global relations among direct and indirect connected brain regions, then models the local brain region interactions. It can uncover the complex mapping relations between fMRI and symmetric structural connectivity. Furthermore, the spatially connected consistency loss is devised to constrain the generator to preserve global-local topological information for accurate symmetric SC prediction. Testing on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the proposed model can effectively generate empirical SC-preserved connectivity from four-dimensional imaging data and shows superior performance in SC prediction compared with other related models. Furthermore, the proposed model can identify the vast majority of important brain regions and connections derived from the empirical method, providing an alternative way to fuse multimodal brain networks and analyze clinical brain disease.

comment: 12 pages

♻ ☆ "It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models

Kapil Garg, Xinru Tang, Jimin Heo, Dwayne R. Morgan, Darren Gergle, Erik B. Sudderth, Anne Marie Piper

Vision-Language Models (VLMs) are increasingly used by blind and low-vision (BLV) people to identify and understand products in their everyday lives, such as food, personal care items, and household goods. Despite their prevalence, we lack an empirical understanding of how common image quality issues--such as blur, misframing, and rotation--affect the accuracy of VLM-generated captions and whether the resulting captions meet BLV people's information needs. Based on a survey of 86 BLV participants, we develop an annotated dataset of 1,859 product images from BLV people to systematically evaluate how image quality issues affect VLM-generated captions. While the best VLM achieves 98% accuracy on images with no quality issues, accuracy drops to 75% overall when quality issues are present, worsening considerably as issues compound. We discuss the need for model evaluations that center on disabled people's experiences throughout the process and offer concrete recommendations for HCI and ML researchers to make VLMs more reliable for BLV people.

comment: Published at CHI 2026; Honorable Mention for Best Paper (Top 5%). Dataset available at: https://github.com/Accessibility-Research-Collective-UCI/image-quality-vlm-chi26

♻ ☆ TUGS: Physics-based Compact Representation of Underwater Scenes by Tensorized Gaussian

Shijie Lian, Ziyi Zhang, Hua Li, Laurence Tianruo Yang, Mengyu Ren, Debin Liu, Wenhui Wu

Underwater 3D scene reconstruction is crucial for multimedia applications in adverse environments, such as underwater robotic perception and navigation. However, the complexity of interactions between light propagation, water medium, and object surfaces poses significant difficulties for existing methods in accurately simulating their interplay. Additionally, expensive training and rendering costs limit their practical application. Therefore, we propose Tensorized Underwater Gaussian Splatting (TUGS), a compact underwater 3D representation based on physical modeling of complex underwater light fields. TUGS includes a physics-based underwater Adaptive Medium Estimation (AME) module, enabling accurate simulation of both light attenuation and backscatter effects in underwater environments, and introduces Tensorized Densification Strategies (TDS) to efficiently refine the tensorized representation during optimization. TUGS is able to render high-quality underwater images with faster rendering speeds and less memory usage. Extensive experiments on real-world underwater datasets have demonstrated that TUGS can efficiently achieve superior reconstruction quality using a limited number of parameters. The code is available at https://liamlian0727.github.io/TUGS

♻ ☆ Early Exiting Predictive Coding Neural Networks for Edge AI

Alaa Zniber, Mounir Ghogho, Ouassim Karrakchou, Mehdi Zakroum

The Internet of Things is transforming various fields, with sensors increasingly embedded in wearables, smart buildings, and connected equipment. While deep learning enables valuable insights from IoT data, conventional models are too computationally demanding for resource-limited edge devices. Moreover, privacy concerns and real-time processing needs make local computation a necessity over cloud-based solutions. Inspired by the brain's energy efficiency, we propose a shallow bidirectional predictive coding network with early exiting, dynamically halting computations once a performance threshold is met. This reduces the memory footprint and computational overhead while maintaining high accuracy. We validate our approach using the CIFAR-10 dataset. Our model achieves performance comparable to deep networks with significantly fewer parameters and lower computational complexity, demonstrating the potential of biologically inspired architectures for efficient edge AI.

♻ ☆ SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering

Jiahao Niu, Rongjia Zheng, Wenju Xu, Wei-Shi Zheng, Qing Zhang

We present SGS-Intrinsic, an indoor inverse rendering framework that works well for sparse-view images. Unlike existing 3D Gaussian Splatting (3DGS) based methods that focus on object-centric reconstruction and fail to work under sparse view settings, our method allows to achieve high-quality geometry reconstruction and accurate disentanglement of material and illumination. The core idea is to construct a dense and geometry-consistent Gaussian semantic field guided by semantic and geometric priors, providing a reliable foundation for subsequent inverse rendering. Building upon this, we perform material-illumination disentanglement by combining a hybrid illumination model and material prior to effectively capture illumination-material interactions. To mitigate the impact of cast shadows and enhance the robustness of material recovery, we introduce illumination-invariant material constraint together with a deshadowing model. Extensive experiments on benchmark datasets show that our method consistently improves both reconstruction fidelity and inverse rendering quality over existing 3DGS-based inverse rendering approaches. Our code is available at https://github.com/GrumpySloths/SGS_Intrinsic.github.io.

comment: CVPR2026

♻ ☆ Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery

Wei He, Xianghan Meng, Zhiyuan Huang, Xianbiao Qi, Rong Xiao, Chun-Guang Li

Generalized Category Discovery (GCD) aims to identify both known and unknown categories, with only partial labels given for the known categories, posing a challenging open-set recognition problem. State-of-the-art approaches for GCD task are usually built on multi-modality representation learning, which is heavily dependent upon inter-modality alignment. However, few of them cast a proper intra-modality alignment to generate a desired underlying structure of representation distributions. In this paper, we propose a novel and effective multi-modal representation learning framework for GCD via Semi-Supervised Rate Reduction, called SSR$^2$-GCD, to learn cross-modality representations with desired structural properties based on emphasizing to properly align intra-modality relationships. Moreover, to boost knowledge transfer, we integrate prompt candidates by leveraging the inter-modal alignment offered by Vision Language Models. We conduct extensive experiments on generic and fine-grained benchmark datasets demonstrating superior performance of our approach.

comment: 15 pages, accepted by CVPR 2026

♻ ☆ Streaming 4D Visual Geometry Transformer

Dong Zhuo, Wenzhao Zheng, Jiahe Guo, Yuqi Wu, Jie Zhou, Jiwen Lu

Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar philosophy with autoregressive large language models. We explore a simple and efficient design and employ a causal transformer architecture to process the input sequence in an online manner. We use temporal causal attention and cache the historical keys and values as implicit memory to enable efficient streaming long-term 3D reconstruction. This design can handle low-latency 3D reconstruction by incrementally integrating historical information while maintaining high-quality spatial consistency. For efficient training, we propose to distill knowledge from the dense bidirectional visual geometry grounded transformer (VGGT) to our causal model. For inference, our model supports the migration of optimized efficient attention operators (e.g., FlashAttention) from large language models. Extensive experiments on various 3D geometry perception benchmarks demonstrate that our model enhances inference speed in online scenarios while maintaining competitive performance, thereby facilitating scalable and interactive 3D vision systems. Code is available at: https://github.com/wzzheng/StreamVGGT.

comment: Code is available at: https://github.com/wzzheng/StreamVGGT

♻ ☆ Modeling Spatiotemporal Neural Frames for High Resolution Brain Dynamic

Wanying Qu, Jianxiong Gao, Wei Wang, Yanwei Fu

Capturing dynamic spatiotemporal neural activity is essential for understanding large-scale brain mechanisms. Functional magnetic resonance imaging (fMRI) provides high-resolution cortical representations that form a strong basis for characterizing fine-grained brain activity patterns. The high acquisition cost of fMRI limits large-scale applications, therefore making high-quality fMRI reconstruction a crucial task. Electroencephalography (EEG) offers millisecond-level temporal cues that complement fMRI. Leveraging this complementarity, we present an EEG-conditioned framework for reconstructing dynamic fMRI as continuous neural sequences with high spatial fidelity and strong temporal coherence at the cortical-vertex level. To address sampling irregularities common in real fMRI acquisitions, we incorporate a null-space intermediate-frame reconstruction, enabling measurement-consistent completion of arbitrary intermediate frames and improving sequence continuity and practical applicability. Experiments on the CineBrain dataset demonstrate superior voxel-wise reconstruction quality and robust temporal consistency across whole-brain and functionally specific regions. The reconstructed fMRI also preserves essential functional information, supporting downstream visual decoding tasks. This work provides a new pathway for estimating high-resolution fMRI dynamics from EEG and advances multimodal neuroimaging toward more dynamic brain activity modeling.

comment: CVPR 2026

♻ ☆ Towards Policy-Adaptive Image Guardrail: Benchmark and Method

Caiyong Piao, Zhiyuan Yan, Haoming Xu, Yunzhen Zhao, Kaiqing Lin, Feiyang Xu, Shuigeng Zhou

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and over time. However, traditional classifiers, confined to fixed categories, require frequent retraining when new policies are introduced. Vision-language models (VLMs) offer a more adaptable and generalizable foundation for dynamic safety guardrails. Despite this potential, existing VLM-based safeguarding methods are typically trained and evaluated under only a fixed safety policy. We find that these models are heavily overfitted to the seen policy, fail to generalize to unseen policies, and even lose the basic instruction-following ability and general knowledge. To address this issue, in this paper we make two key contributions. First, we benchmark the cross-policy generalization performance of existing VLMs with SafeEditBench, a new evaluation suite. SafeEditBench leverages image-editing models to convert unsafe images into safe counterparts, producing policy-aligned datasets where each safe-unsafe image pair remains visually similar except for localized regions violating specific safety rules. Human annotators then provide accurate safe/unsafe labels under five distinct policies, enabling fine-grained assessment of policy-aware generalization. Second, we introduce SafeGuard-VL, a reinforcement learning-based method with verifiable rewards (RLVR) for robust unsafe-image guardrails. Instead of relying solely on supervised fine-tuning (SFT) under fixed policies, SafeGuard-VL explicitly optimizes the model with policy-grounded rewards, promoting verifiable adaptation across evolving policies. Extensive experiments verify the effectiveness of our method for unsafe image guardrails across various policies.

♻ ☆ Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction

Bo Du, Xiaochen Ma, Xuekang Zhu, Zhe Yang, Chaogun Niu, Mingqi Fang, Zhenming Wang, Jingjing Liu, Jian Liu, Ji-Zhe Zhou

Fake Image Detection (FID), aiming at unified detection across four image forensic subdomains, is critical in real-world forensic scenarios. Compared with ensemble approaches, monolithic FID models are theoretically more promising, but to date, consistently yield inferior performance in practice. In this work, by discovering the ``heterogeneous phenomenon'', which is the intrinsic distinctness of artifacts across subdomains, we diagnose the cause of this underperformance for the first time: the collapse of the artifact feature space driven by such phenomenon. The core challenge for developing a practical monolithic FID model thus boils down to the ``unified-yet-discriminative" reconstruction of the artifact feature space. To address this paradoxical challenge, we hypothesize that high-level semantics can serve as a structural prior for the reconstruction, and further propose Semantic-Induced Constrained Adaptation (SICA), the first monolithic FID paradigm. Extensive experiments on our OpenMMSec dataset demonstrate that SICA outperforms 15 state-of-the-art methods and reconstructs the target unified-yet-discriminative artifact feature space in a near-orthogonal manner, thus firmly validating our hypothesis. The code and dataset are available at:https: //github.com/scu-zjz/SICA_OpenMMSec.

♻ ☆ Super-Resolved Canopy Height Mapping from Sentinel-2 Time Series Using LiDAR HD Reference Data across Metropolitan France

Ekaterina Kalinicheva, Florian Helen, Stéphane Mermoz, Florian Mouret, Milena Planells

Fine-scale forest monitoring is essential for understanding canopy structure and its dynamics, which are key indicators of carbon stocks, biodiversity, and forest health. Deep learning is particularly effective for this task, as it integrates spectral, temporal, and spatial signals that jointly reflect the canopy structure. To address this need, we introduce THREASURE-Net, a novel end-to-end framework for Tree Height Regression And Super-Resolution. The model is trained on Sentinel-2 time series using reference height metrics derived from LiDAR HD data at multiple spatial resolutions over Metropolitan France to produce annual height maps. We evaluate three model variants, producing tree-height predictions at 2.5 m, 5 m, and 10 m resolution. THREASURE-Net does not rely on any pretrained model nor on reference very high resolution optical imagery to train its super-resolution module; instead, it learns solely from LiDAR-derived height information. Our approach outperforms existing state-of-the-art methods based on Sentinel data and is competitive with methods based on very high resolution imagery. It can be deployed to generate high-precision annual canopy-height maps, achieving mean absolute errors of 2.63 m, 2.70 m, and 2.88 m at 2.5 m, 5 m, and 10 m resolution, respectively. These results highlight the potential of THREASURE-Net for scalable and cost-effective structural monitoring of temperate forests using only freely available satellite data. The source code for THREASURE-Net is available at: https://github.com/Global-Earth-Observation/threasure-net.

♻ ☆ Unified Multimodal Models as Auto-Encoders

Zhiyuan Yan, Kaiqing Lin, Zongjian Li, Junyan Ye, Hui Han, Haochen Wang, Zhendong Wang, Bin Lin, Hao Li, Xinyan Xiao, Jingdong Wang, Haifeng Wang, Li Yuan

Image-to-text (I2T) understanding and text-to-image (T2I) generation are two fundamental, important yet traditionally isolated multimodal tasks. Despite their intrinsic connection, existing approaches typically optimize them independently, missing the opportunity for mutual enhancement. In this paper, we argue that the both tasks can be connected under a shared Auto-Encoder perspective, where text serves as the intermediate latent representation bridging the two directions - encoding images into textual semantics (I2T) and decoding text back into images (T2I). Our key insight is that if the encoder truly "understands" the image, it should capture all essential structure, and if the decoder truly "understands" the text, it should recover that structure faithfully. Building upon this principle, we propose Unified-GRPO, a post-training method based on reinforcement learning that jointly optimizes both modules through reconstructive rewards, maximizing the semantic consistency between the input and the generated images. Under this reconstruction objective, the encoder is encouraged to extract as much accurate and comprehensive semantic information from the input image to maximize reconstruction quality, while the decoder is simultaneously optimized to generate conditioned on the encoder's prior, enabling a self-evolving improvement. Empirically, we find that using text as the intermediate representation and training under a reconstructive RL paradigm effectively benefits both I2T and T2I. The I2T module gains stronger fine-grained visual perception, such as small-object recognition, grounding, etc, while its dense embeddings and language priors, in turn, provide richer semantic signals that improve T2I fidelity and complex instruction following. These results demonstrate that the reconstructive RL establishes a mutually reinforcing cross-modal synergy within the auto-encoding framework.

♻ ☆ BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports

Jing-Yuan Chang

Badminton, known for having the fastest ball speeds among all sports, presents significant challenges to the field of computer vision, including player identification, court line detection, shuttlecock trajectory tracking, and player stroke-type classification. In this paper, we introduce a novel video clipping strategy to extract frames of each player's racket swing in a badminton broadcast match. These clipped frames are then processed by three existing models: one for Human Pose Estimation to obtain human skeletal joints, another for shuttlecock trajectory tracking, and the other for court line detection to determine player positions on the court. Leveraging these data as inputs, we propose Badminton Stroke-type Transformer (BST) to classify player stroke-types in singles. To the best of our knowledge, experimental results demonstrate that our method outperforms the previous state-of-the-art on the largest publicly available badminton video dataset (ShuttleSet), another badminton dataset (BadmintonDB), and a tennis dataset (TenniSet). These results suggest that effectively leveraging ball trajectory is a promising direction for action recognition in racket sports.

comment: Accepted by CVPRW 2026 - 12th CVsports

♻ ☆ TruckDrive: Long-Range Autonomous Highway Driving Dataset

Filippo Ghilotti, Edoardo Palladin, Samuel Brucker, Adam Sigal, Mario Bijelic, Felix Heide

Safe highway autonomy for heavy trucks remains an open and unsolved challenge: due to long braking distances, scene understanding of hundreds of meters is required for anticipatory planning and to allow safe braking margins. However, existing driving datasets primarily cover urban scenes, with perception effectively limited to short ranges of only up to 100 meters. To address this gap, we introduce TruckDrive, a highway-scale multimodal driving dataset, captured with a sensor suite purpose-built for long range sensing: seven long-range FMCW LiDARs measuring range and radial velocity, three high-resolution short-range LiDARs, eleven 8MP surround cameras with varying focal lengths and ten 4D FMCW radars. The dataset offers 475 thousands samples with 165 thousands densely annotated frames for driving perception benchmarking up to 1,000 meters for 2D detection and 400 meters for 3D detection, depth estimation, tracking, planning and end to end driving over 20 seconds sequences at highway speeds. We find that state-of-the-art autonomous driving models do not generalize to ranges beyond 150 meters, with drops between 31% and 99% in 3D perception tasks, exposing a systematic long-range gap that current architectures and training signals cannot close.

♻ ☆ Human-level 3D shape perception emerges from multi-view learning

Tyler Bonnen, Jitendra Malik, Angjoo Kanazawa

Humans can infer the three-dimensional structure of objects from two-dimensional visual inputs. Modeling this ability has been a longstanding goal for the science and engineering of visual intelligence, yet decades of computational methods have fallen short of human performance. Here we develop a modeling framework that predicts human 3D shape inferences for arbitrary objects, directly from experimental stimuli. We achieve this with a novel class of neural networks trained using a visual-spatial objective over naturalistic sensory data; given a set of images taken from different locations within a natural scene, these models learn to predict spatial information related to these images, such as camera location and visual depth, without relying on any object-related inductive biases. Notably, these visual-spatial signals are analogous to sensory cues readily available to humans. We design a zero-shot evaluation approach to determine the performance of these 'multi-view' models on a well established 3D perception task, then compare model and human behavior. Our modeling framework is the first to match human accuracy on 3D shape inferences, even without task-specific training or fine-tuning. Remarkably, independent readouts of model responses predict fine-grained measures of human behavior, including error patterns and reaction times, revealing a natural correspondence between model dynamics and human perception. Taken together, our findings indicate that human-level 3D perception can emerge from a simple, scalable learning objective over naturalistic visual-spatial data. Code, images, and human data needed to reproduce all analyses can be found at https://tzler.github.io/human_multiview/

comment: Project page: https://tzler.github.io/human_multiview Code: https://github.com/tzler/human_multiview Huggingface dataset: https://huggingface.co/datasets/tzler/MOCHI

♻ ☆ ANVIL: Accelerator-Native Video Interpolation via Codec Motion Vector Priors

Shibo Liu

Real-time 30-to-60 fps video frame interpolation on mobile neural processing units (NPUs) requires each synthesized frame within 33.3 ms. We show that mainstream flow-based video frame interpolation faces three structural deployment barriers on mobile NPUs: spatial sampling operators exceed the frame budget or lack hardware support, iterative flow refinement collapses under 8-bit integer post-training quantization, and memory-bound operators dominate the inference graph. ANVIL addresses these barriers by reusing motion vectors from the H.264/AVC decoder to prealign input frames, removing learned optical flow, spatial sampling, and iterative accumulation from the accelerator graph. The remaining residual is refined by a convolution-dominated network composed almost entirely of compute-bound operators. On a Snapdragon 8 Gen 3 device, ANVIL achieves 12.8 ms 1080p inference at 8-bit integer precision; an open-source Android player sustains 28.4 ms median end-to-end latency over 30-minute continuous playback. Per-operator causal analysis identifies quantized accumulation on recurrent flow states as a key mechanism behind integer quantization failure in iterative methods. The current design targets H.264/AVC playback with decoder-exposed motion vectors.

comment: 12 pages, 4 figures, 10 tables. Submitted to IEEE TCSVT. v2: revised ablation studies, compressed text, expanded abstract abbreviations. Code: https://github.com/NihilDigit/anvil

♻ ☆ ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering

Alberto Compagnoni, Marco Morini, Sara Sarto, Federico Cocchi, Davide Caffagni, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in jointly understanding text, images, and videos, often evaluated via Visual Question Answering (VQA). However, even state-of-the-art MLLMs struggle with domain-specific or knowledge-intensive queries, where relevant information is underrepresented in pre-training data. Knowledge-based VQA (KB-VQA) addresses this by retrieving external documents to condition answer generation, but current retrieval-augmented approaches suffer from low precision, noisy passages, and limited reasoning. To address this, we propose ReAG, a novel Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages, ensuring high-quality additional context. The model follows a multi-stage training strategy leveraging reinforcement learning to enhance reasoning over retrieved content, while supervised fine-tuning serves only as a cold start. Extensive experiments on Encyclopedic-VQA and InfoSeek demonstrate that ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.

comment: CVPR 2026 - Project page: https://aimagelab.github.io/ReAG/

♻ ☆ Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting

Fan Chen, Shuyin Xia, Yi Wang

Single-source domain generalization for crowd counting is highly challenging because a single labeled source domain may contain heterogeneous latent domains, while unseen target domains often exhibit severe distribution shifts. A central issue is stable latent domain discovery: directly performing flat clustering on evolving sample-level latent features is easily disturbed by feature noise, outliers, and representation drift, leading to unreliable pseudo-domain assignments and weakened domain-structured learning. To address this problem, we propose a granular ball guided stable latent domain discovery framework for domain-general crowd counting. The proposed method first groups samples into compact local granular balls and then clusters granular ball centers as representatives to infer pseudo-domains, thereby converting direct sample-level clustering into a hierarchical representative-based clustering process. This design produces more stable and semantically consistent pseudo-domain assignments. On top of the discovered latent domains, we develop a two-branch learning framework that improves transferable semantic representations via semantic codebook re-encoding and captures domain-specific appearance variations through a style branch, thereby alleviating semantic--style entanglement under domain shifts. Extensive experiments on ShanghaiTech A/B, UCF\_QNRF, and NWPU-Crowd under a strict no-adaptation protocol verify the effectiveness of the proposed method and show strong generalization ability, especially in transfer settings with large domain gaps.

♻ ☆ Image Segmentation via Divisive Normalization: dealing with environmental diversity

Pablo Hernández-Cámara, Jorge Vila-Tomás, Paula Dauden-Oliver, Nuria Alabau-Bosque, Valero Laparra, Jesús Malo

Autonomous driving is a challenging scenario for image segmentation due to the presence of uncontrolled environmental conditions and the eventually catastrophic consequences of failures. Previous work suggested that a biologically motivated computation, the so-called Divisive Normalization, could be useful to deal with image variability, but its effects have not been systematically studied over different data sources and environmental factors. Here we put segmentation U-nets augmented with Divisive Normalization to work far from training conditions to find where this adaptation is more critical. We categorize the scenes according to their radiance level and dynamic range (day/night), and according to their achromatic/chromatic contrasts. We also consider video game (synthetic) images to broaden the range of environments. We check the performance in the extreme percentiles of such categorization. Then, we push the limits further by artificially modifying the images in perceptually/environmentally relevant dimensions: luminance, contrasts and spectral radiance. Results show that neural networks with Divisive Normalization get better results in all the scenarios and their performance remains more stable with regard to the considered environmental factors and nature of the source. Finally, we explain the improvements in segmentation performance in two ways: (1) by quantifying the invariance of the responses that incorporate Divisive Normalization, and (2) by illustrating the adaptive nonlinearity of the different layers that depends on the local activity.

♻ ☆ ALADIN:Attribute-Language Distillation Network for Person Re-Identification

Wang Zhou, Boran Duan, Haojun Ai, Ruiqi Lan, Ziyue Zhou

Recent vision-language models such as CLIP provide strong cross-modal alignment, but current CLIP-guided ReID pipelines rely on global features and fixed prompts. This limits their ability to capture fine-grained attribute cues and adapt to diverse appearances. We propose ALADIN, an attribute-language distillation network that distills knowledge from a frozen CLIP teacher to a lightweight ReID student. ALADIN introduces fine-grained attribute-local alignment to establish adaptive text-visual correspondence and robust representation learning. A Scene-Aware Prompt Generator produces image-specific soft prompts to facilitate adaptive alignment. Attribute-local distillation enforces consistency between textual attributes and local visual features, significantly enhancing robustness under occlusions. Furthermore, we employ cross-modal contrastive and relation distillation to preserve the inherent structural relationships among attributes. To provide precise supervision, we leverage Multimodal LLMs to generate structured attribute descriptions, which are then converted into localized attention maps via CLIP. At inference, only the student is used. Experiments on Market-1501, DukeMTMC-reID, and MSMT17 show improvements over CNN-, Transformer-, and CLIP-based methods, with better generalization and interpretability.

comment: 14pages, 3figures, 7charts

♻ ☆ Image-Specific Adaptation of Transformer Encoders for Compute-Efficient Segmentation

Manyi Yao, Abhishek Aich, Yumin Suh, Amit Roy-Chowdhury, Christian Shelton, Manmohan Chandraker

Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be taxing on deployed devices. One way to overcome this challenge is by adapting the computation level to the specific needs of the input image rather than the current one-size-fits-all approach. To this end, we introduce ECO-M2F or EffiCient TransfOrmer Encoders for Mask2Former-style models. Noting that the encoder module of M2F-style models incur high resource-intensive computations, ECO-M2F provides a strategy to self-select the number of hidden layers in the encoder, conditioned on the input image. To enable this self-selection ability for providing a balance between performance and computational efficiency, we present a three step recipe. The first step is to train the parent architecture to enable early exiting from the encoder. The second step is to create an derived dataset of the ideal number of encoder layers required for each training example. The third step is to use the aforementioned derived dataset to train a gating network that predicts the number of encoder layers to be used, conditioned on the input image. Additionally, to change the computational-accuracy tradeoff, only steps two and three need to be repeated which significantly reduces retraining time. Experiments on the public datasets show that the proposed approach reduces expected encoder computational cost while maintaining performance, adapts to various user compute resources, is flexible in architecture configurations, and can be extended beyond the segmentation task to object detection.

comment: Accepted at WACV 2026 WVAQ

♻ ☆ ArtLLM: Generating Articulated Assets via 3D LLM

Penghao Wang, Siyuan Xie, Hongyu Yan, Xianghui Yang, Jingwei Huang, Chunchao Guo, Jiayuan Gu

Creating interactive digital environments for gaming, robotics, and simulation relies on articulated 3D objects whose functionality emerges from their part geometry and kinematic structure. However, existing approaches remain fundamentally limited: optimization-based reconstruction methods require slow, per-object joint fitting and typically handle only simple, single-joint objects, while retrieval-based methods assemble parts from a fixed library, leading to repetitive geometry and poor generalization. To address these challenges, we introduce ArtLLM, a novel framework for generating high-quality articulated assets directly from complete 3D meshes. At its core is a 3D multimodal large language model trained on a large-scale articulation dataset curated from both existing articulation datasets and procedurally generated objects. Unlike prior work, ArtLLM autoregressively predicts a variable number of parts and joints, inferring their kinematic structure in a unified manner from the object's point cloud. This articulation-aware layout then conditions a 3D generative model to synthesize high-fidelity part geometries. Experiments on the PartNet-Mobility dataset show that ArtLLM significantly outperforms state-of-the-art methods in both part layout accuracy and joint prediction, while generalizing robustly to real-world objects. Finally, we demonstrate its utility in constructing digital twins, highlighting its potential for scalable robot learning.

comment: CVPR 2026. Project page: https://authoritywang.github.io/artllm/

♻ ☆ PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding NeurIPS 2025

Penghao Wang, Yiyang He, Xin Lv, Yukai Zhou, Lan Xu, Jingyi Yu, Jiayuan Gu

Understanding objects at the level of their constituent parts is fundamental to advancing computer vision, graphics, and robotics. While datasets like PartNet have driven progress in 3D part understanding, their reliance on untextured geometries and expert-dependent annotation limits scalability and usability. We introduce PartNeXt, a next-generation dataset addressing these gaps with over 23,000 high-quality, textured 3D models annotated with fine-grained, hierarchical part labels across 50 categories. We benchmark PartNeXt on two tasks: (1) class-agnostic part segmentation, where state-of-the-art methods (e.g., PartField, SAMPart3D) struggle with fine-grained and leaf-level parts, and (2) 3D part-centric question answering, a new benchmark for 3D-LLMs that reveals significant gaps in open-vocabulary part grounding. Additionally, training Point-SAM on PartNeXt yields substantial gains over PartNet, underscoring the dataset's superior quality and diversity. By combining scalable annotation, texture-aware labels, and multi-task evaluation, PartNeXt opens new avenues for research in structured 3D understanding.

comment: NeurIPS 2025 DB Track. Project page: https://authoritywang.github.io/partnext

♻ ☆ Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction

Ruihong Yin, Xuepeng Shi, Oleksandr Bailo, Marco Manfredi, Theo Gevers

Recent perception-generalist approaches based on language models have achieved state-of-the-art results across diverse tasks, including 3D scene layout estimation and 3D object detection, via unified architecture and interface. However, these approaches rely on autoregressive next-token prediction, which is inherently slow. In this work, we introduce Fast SceneScript, a novel structured language model for accurate and efficient 3D scene understanding. Our method employs multi-token prediction (MTP) to reduce the number of autoregressive iterations and significantly accelerate inference. While MTP improves speed, unreliable token predictions can significantly reduce accuracy. To filter out unreliable tokens, we adapt self-speculative decoding (SSD) for structured language models and introduce confidence-guided decoding (CGD) with an improved scoring mechanism for token reliability. Furthermore, we design a parameter-efficient mechanism that reduces the parameter overhead of MTP. Extensive experiments on synthetic and real-world benchmarks demonstrate that Fast SceneScript can generate up to 9 tokens per decoder inference step without compromising accuracy, while adding only $\sim7.5\%$ additional parameters.

comment: Accepted to CVPR 2026

♻ ☆ Fine-grained Image Quality Assessment for Perceptual Image Restoration AAAI2026

Xiangfei Sheng, Xiaofeng Pan, Zhichao Yang, Pengfei Chen, Leida Li

Recent years have witnessed remarkable achievements in perceptual image restoration (IR), creating an urgent demand for accurate image quality assessment (IQA), which is essential for both performance comparison and algorithm optimization. Unfortunately, the existing IQA metrics exhibit inherent weakness for IR task, particularly when distinguishing fine-grained quality differences among restored images. To address this dilemma, we contribute the first-of-its-kind fine-grained image quality assessment dataset for image restoration, termed FGRestore, comprising 18,408 restored images across six common IR tasks. Beyond conventional scalar quality scores, FGRestore was also annotated with 30,886 fine-grained pairwise preferences. Based on FGRestore, a comprehensive benchmark was conducted on the existing IQA metrics, which reveal significant inconsistencies between score-based IQA evaluations and the fine-grained restoration quality. Motivated by these findings, we further propose FGResQ, a new IQA model specifically designed for image restoration, which features both coarse-grained score regression and fine-grained quality ranking. Extensive experiments and comparisons demonstrate that FGResQ significantly outperforms state-of-the-art IQA metrics. Codes and model weights have been released in https://sxfly99.github.io/FGResQ-Home.

comment: Accepted by AAAI2026

♻ ☆ JoyStreamer: Unlocking Highly Expressive Avatars via Harmonized Text-Audio Conditioning

Ruikui Wang, Jinheng Feng, Lang Tian, Huaishao Luo, Chaochao Li, Liangbo Zhou, Huan Zhang, Youzheng Wu, Xiaodong He

Existing video avatar models have demonstrated impressive capabilities in scenarios such as talking, public speaking, and singing. However, the majority of these methods exhibit limited alignment with respect to text instructions, particularly when the prompts involve complex elements including large full-body movement, dynamic camera trajectory, background transitions, or human-object interactions. To break out this limitation, we present JoyAvatar, a framework capable of generating long duration avatar videos, featuring two key technical innovations. Firstly, we introduce a twin-teacher enhanced training algorithm that enables the model to transfer inherent text-controllability from the foundation model while simultaneously learning audio-visual synchronization. Secondly, during training, we dynamically modulate the strength of multi-modal conditions (e.g., audio and text) based on the distinct denoising timestep, aiming to mitigate conflicts between the heterogeneous conditioning signals. These two key designs serve to substantially expand the avatar model's capacity to generate natural, temporally coherent full-body motions and dynamic camera movements as well as preserve the basic avatar capabilities, such as accurate lip-sync and identity consistency. GSB evaluation results demonstrate that our JoyStreamer model outperforms the state-of-the-art models such as Omnihuman-1.5 and KlingAvatar 2.0. Moreover, our approach enables complex applications including multi-person dialogues and non-human subjects role-playing. Some video samples are provided on https://joystreamer.github.io/.

♻ ☆ GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

Rui Xie, Zhi Gao, Chenrui Shi, Zirui Shang, Lu Chen, Qing Li

Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to domain-specific software operation data during training, these agents exhibit significant domain bias - they lack familiarity with the specific operation workflows (planning) and UI element layouts (grounding) of particular applications, limiting their real-world task performance. In this paper, we present GUIDE (GUI Unbiasing via Instructional-Video Driven Expertise), a training-free, plug-and-play framework that resolves GUI agent domain bias by autonomously acquiring domain-specific expertise from web tutorial videos through a retrieval-augmented automated annotation pipeline. GUIDE introduces two key innovations. First, a subtitle-driven Video-RAG pipeline unlocks video semantics through subtitle analysis, performing progressive three-stage retrieval - domain classification, topic extraction, and relevance matching - to identify task-relevant tutorial videos. Second, a fully automated annotation pipeline built on an inverse dynamics paradigm feeds consecutive keyframes enhanced with UI element detection into VLMs, inferring the required planning and grounding knowledge that are injected into the agent's corresponding modules to address both manifestations of domain bias. Extensive experiments on OSWorld demonstrate GUIDE's generality as a plug-and-play component for both multi-agent systems and single-model agents. It consistently yields over 5% improvements and reduces execution steps - without modifying any model parameters or architecture - validating GUIDE as an architecture-agnostic enhancement to bridge GUI agent domain bias.

comment: 28 pages, 8 figures, 7 tables

♻ ☆ Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds

Bin Yang, Mohamed Abdelsamad, Miao Zhang, Alexandru Paul Condurache

Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across augmented views or by masked scene modeling. However, the resulting representations transfer poorly to instance localization, and often require full finetuning for strong performance. Instance awareness is a fundamental component of 3D perception, thus bridging this gap is crucial for progressing toward true 3D foundation models that support all downstream tasks on 3D data. In this work, we introduce PointINS, an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning. PointINS employs an orthogonal offset branch to jointly learn high-level semantic understanding and geometric reasoning, yielding instance awareness. We identify two consistent properties essential for robust instance localization and formulate them as complementary regularization strategies, Offset Distribution Regularization (ODR), which aligns predicted offsets with empirically observed geometric priors, and Spatial Clustering Regularization (SCR), which enforces local coherence by regularizing offsets with pseudo-instance masks. Through extensive experiments across five datasets, PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation, paving the way for scalable 3D foundation models.

comment: The paper was accepted by CVPR2026

♻ ☆ Text-guided Fine-Grained Video Anomaly Understanding

Jihao Gu, Kun Li, He Wang, Kaan Akşit

Subtle abnormal events in videos often manifest as weak spatio-temporal cues that are easily overlooked by conventional anomaly detection systems. Existing video anomaly detection approaches typically provide coarse binary anomaly decisions without interpretable evidence, while large vision-language models (LVLMs) can produce textual judgments but lack precise localization of subtle visual signals. To address this gap, we propose Text-guided Fine-Grained Video Anomaly Understanding T-VAU, a framework that grounds subtle anomaly evidence into multimodal reasoning. Specifically, we introduce an Anomaly Heatmap Decoder (AHD) that performs visual-textual feature alignment to extract pixel-level spatio-temporal anomaly heatmaps from intermediate visual representations. We further design a Region-aware Anomaly Encoder (RAE) that converts these heatmaps into structured prompt embeddings, enabling the LVLM to perform anomaly detection, localization, and semantic explanation in a unified reasoning pipeline. To support fine-grained supervision, we construct a target-level fine-grained video-text anomaly dataset derived from ShanghaiTech and UBnormal with detailed annotations of object appearance, localization, and motion trajectories. Extensive experiments demonstrate that T-VAU significantly improves anomaly localization and textual reasoning performance on both benchmarks, achieving strong results in BLEU-4 metrics and Yes/No decision accuracy while providing interpretable pixel-level spatio-temporal evidence for anomaly understanding. The code will be available at https://github.com/momiji-bit/T-VAU.

comment: Accepted by CVPR 2026 SVC Workshop

♻ ☆ JoyStreamer-Flash: Real-time and Infinite Audio-Driven Avatar Generation with Autoregressive Diffusion

Chaochao Li, Ruikui Wang, Liangbo Zhou, Jinheng Feng, Huaishao Luo, Huan Zhang, Youzheng Wu, Xiaodong He

Existing DiT-based audio-driven avatar generation methods have achieved considerable progress, yet their broader application is constrained by limitations such as high computational overhead and the inability to synthesize long-duration videos. Autoregressive methods address this problem by applying block-wise autoregressive diffusion methods. However, these methods suffer from the problem of error accumulation and quality degradation. To address this, we propose JoyStreamer-Flash, an audio-driven autoregressive model capable of real-time inference and infinite-length video generation with the following contributions: (1) Progressive Step Bootstrapping (PSB), which allocates more denoising steps to initial frames to stabilize generation and reduce error accumulation; (2) Motion Condition Injection (MCI), enhancing temporal coherence by injecting noise-corrupted previous frames as motion condition; and (3) Unbounded RoPE via Cache-Resetting (URCR), enabling infinite-length generation through dynamic positional encoding. Our 1.3B-parameter causal model achieves 16 FPS on a single GPU and achieves competitive results in visual quality, temporal consistency, and lip synchronization.

♻ ☆ A Novel Camera-to-Robot Calibration Method for Vision-Based Floor Measurements

Jan Andre Rudolph, Dennis Haitz, Markus Ulrich

A novel hand-eye calibration method for ground-observing mobile robots is proposed. While cameras on mobile robots are common, they are rarely used for ground-observing measurement tasks. Laser trackers are increasingly used in robotics for precise localization. A referencing plate is designed to combine the two measurement modalities of laser-tracker 3D metrology and camera-based 2D imaging. It incorporates reflector nests for pose acquisition using a laser tracker and a camera calibration target that is observed by the robot-mounted camera. The procedure comprises estimating the plate pose, the plate-camera pose, and the robot pose, followed by computing the robot-camera transformation. Experiments indicate sub-millimeter repeatability.

comment: 8 pages; accepted for publication in the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

♻ ☆ JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding

Koki Maeda, Naoaki Okazaki

Japanese scene text poses challenges that multilingual benchmarks often fail to capture, including mixed scripts, frequent vertical writing, and a character inventory far larger than the Latin alphabet. Although Japanese is included in several multilingual benchmarks, these resources do not adequately capture the language-specific complexities. Meanwhile, existing Japanese visual text datasets have primarily focused on scanned documents, leaving in-the-wild scene text underexplored. To fill this gap, we introduce JaWildText, a diagnostic benchmark for evaluating vision-language models (VLMs) on Japanese scene text understanding. JaWildText contains 3,241 instances from 2,961 images newly captured in Japan, with 1.12 million annotated characters spanning 3,643 unique character types. It comprises three complementary tasks that vary in visual organization, output format, and writing style: (i) Dense Scene Text Visual Question Answering (STVQA), which requires reasoning over multiple pieces of visual text evidence; (ii) Receipt Key Information Extraction (KIE), which tests layout-aware structured extraction from mobile-captured receipts; and (iii) Handwriting OCR, which evaluates page-level transcription across various media and writing directions. We evaluate 14 open-weight VLMs and find that the best model achieves an average score of 0.64 across the three tasks. Error analyses show recognition remains the dominant bottleneck, especially for kanji. JaWildText enables fine-grained, script-aware diagnosis of Japanese scene text capabilities, and will be released with evaluation code.

comment: 18 pages

♻ ☆ Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning

Chinthani Sugandhika, Chen Li, Deepu Rajan, Basura Fernando

Large Video-Language Models (Video-LMs) have achieved impressive progress in multimodal understanding, yet their reasoning remains weakly grounded in space and time. We present Know-Show, a new benchmark designed to evaluate spatio-temporal grounded reasoning, the ability of a model to reason about actions and their semantics while simultaneously grounding its inferences in visual and temporal evidence. Know-Show unifies reasoning and localization within a single evaluation framework consisting of five complementary scenarios across spatial (person, object, person-object, and hand-object) and temporal dimensions. Built from Charades, Action Genome, and Ego4D with 2.5K high-quality human-authored questions, the benchmark exposes significant gaps between current Video-LMs and human reasoning. To bridge this gap, we propose GRAM, a training-free plug-in that augments Video-LMs with fine-grained grounded reasoning through attention-based video token selection and explicit timestamp encoding. Extensive experiments across open and closed Video-LMs (e.g., Qwen, VideoR1, Gemini, and GPT-4o) reveal that existing models struggle to "show what they know" and vice versa. Know-Show establishes a unified standard for assessing grounded reasoning in video-language understanding and provides insights toward developing interpretable and reliable multimodal reasoning systems. We have released the dataset at https://github.com/LUNAProject22/Know-Show, and the code will be released in the same repository.

♻ ☆ Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning

Haozhen Gong, Xiaozhong Ji, Yuansen Liu, Wenbin Wu, Xiaoxiao Yan, Jingjing Liu, Kai Wu, Jiazhen Pan, Bailiang Jian, Jiangning Zhang, Xiaobin Hu, Hongwei Bran Li

MLLMs MLLMs are beginning to appear in clinical workflows, but their ability to perform complex medical reasoning remains unclear. We present Med-CMR, a fine-grained Medical Complex Multimodal Reasoning benchmark. Med-CMR distinguishes from existing counterparts by three core features: 1) Systematic capability decomposition, splitting medical multimodal reasoning into fine-grained visual understanding and multi-step reasoning to enable targeted evaluation; 2) Challenging task design, with visual understanding across three key dimensions (small-object detection, fine-detail discrimination, spatial understanding) and reasoning covering four clinically relevant scenarios (temporal prediction, causal reasoning, long-tail generalization, multi-source integration); 3) Broad, high-quality data coverage, comprising 20,653 Visual Question Answering (VQA) pairs spanning 11 organ systems and 12 imaging modalities, validated via a rigorous two-stage (human expert + model-assisted) review to ensure clinical authenticity. We evaluate 18 state-of-the-art MLLMs with Med-CMR, revealing GPT-5 as the top-performing commercial model: 57.81 accuracy on multiple-choice questions (MCQs) and a 48.70 open-ended score, outperforming Gemini 2.5 Pro (49.87 MCQ accuracy, 45.98 open-ended score) and leading open-source model Qwen3-VL-235B-A22B (49.34 MCQ accuracy, 42.62 open-ended score). However, specialized medical MLLMs do not reliably outperform strong general models, and long-tail generalization emerges as the dominant failure mode. Med-CMR thus provides a stress test for visual-reasoning integration and rare-case robustness in medical MLLMs, and a rigorous yardstick for future clinical systems.

♻ ☆ ProFashion: Prototype-guided Fashion Video Generation with Multiple Reference Images

Xianghao Kong, Qiaosong Qi, Yuanbin Wang, Biaolong Chen, Aixi Zhang, Anyi Rao

Fashion video generation aims to synthesize temporally consistent videos from reference images of a designated character. Despite significant progress, existing diffusion-based methods only support a single reference image as input, severely limiting their capability to generate view-consistent fashion videos, especially when there are different patterns on the clothes from different perspectives. Moreover, the widely adopted motion module does not sufficiently model human body movement, leading to sub-optimal spatiotemporal consistency. To address these issues, we propose ProFashion, a fashion video generation framework leveraging multiple reference images to achieve improved view consistency and temporal coherency. To effectively leverage features from multiple reference images while maintaining a reasonable computational cost, we devise a Pose-aware Prototype Aggregator, which selects and aggregates global and fine-grained reference features according to pose information to form frame-wise prototypes, which serve as guidance in the denoising process. To further enhance motion consistency, we introduce a Flow-enhanced Prototype Instantiator, which exploits the human keypoint motion flow to guide an extra spatiotemporal attention process in the denoiser. To demonstrate the effectiveness of ProFashion, we extensively evaluate our method on the MRFashion-7K dataset we collected from the Internet. ProFashion also outperforms previous methods on the UBC Fashion dataset.

comment: CVPRW 2026

2026-03-30

Sound 17

☆ SonoWorld: From One Image to a 3D Audio-Visual Scene

Derong Jin, Xiyi Chen, Ming C. Lin, Ruohan Gao

Tremendous progress in visual scene generation now turns a single image into an explorable 3D world, yet immersion remains incomplete without sound. We introduce Image2AVScene, the task of generating a 3D audio-visual scene from a single image, and present SonoWorld, the first framework to tackle this challenge. From one image, our pipeline outpaints a 360° panorama, lifts it into a navigable 3D scene, places language-guided sound anchors, and renders ambisonics for point, areal, and ambient sources, yielding spatial audio aligned with scene geometry and semantics. Quantitative evaluations on a newly curated real-world dataset and a controlled user study confirm the effectiveness of our approach. Beyond free-viewpoint audio-visual rendering, we also demonstrate applications to one-shot acoustic learning and audio-visual spatial source separation. Project website: https://humathe.github.io/sonoworld/

comment: Accepted by CVPR 2026, project page: https://humathe.github.io/sonoworld/

☆ ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

Anuj Diwan, Eunsol Choi, David Harwath

We introduce ParaSpeechCLAP, a dual-encoder contrastive model that maps speech and text style captions into a common embedding space, supporting a wide range of intrinsic (speaker-level) and situational (utterance-level) descriptors (such as pitch, texture and emotion) far beyond the narrow set handled by existing models. We train specialized ParaSpeechCLAP-Intrinsic and ParaSpeechCLAP-Situational models alongside a unified ParaSpeechCLAP-Combined model, finding that specialization yields stronger performance on individual style dimensions while the unified model excels on compositional evaluation. We further show that ParaSpeechCLAP-Intrinsic benefits from an additional classification loss and class-balanced training. We demonstrate our models' performance on style caption retrieval, speech attribute classification and as an inference-time reward model that improves style-prompted TTS without additional training. ParaSpeechCLAP outperforms baselines on most metrics across all three applications. Our models and code are released at https://github.com/ajd12342/paraspeechclap .

comment: Under review

☆ Constructing Composite Features for Interpretable Music-Tagging ICASSP 2026

Chenhao Xue, Weitao Hu, Joyraj Chakraborty, Zhijin Guo, Kang Li, Tianyu Shi, Martin Reed, Nikolaos Thomos

Combining multiple audio features can improve the performance of music tagging, but common deep learning-based feature fusion methods often lack interpretability. To address this problem, we propose a Genetic Programming (GP) pipeline that automatically evolves composite features by mathematically combining base music features, thereby capturing synergistic interactions while preserving interpretability. This approach provides representational benefits similar to deep feature fusion without sacrificing interpretability. Experiments on the MTG-Jamendo and GTZAN datasets demonstrate consistent improvements compared to state-of-the-art systems across base feature sets at different abstraction levels. It should be noted that most of the performance gains are noticed within the first few hundred GP evaluations, indicating that effective feature combinations can be identified under modest search budgets. The top evolved expressions include linear, nonlinear, and conditional forms, with various low-complexity solutions at top performance aligned with parsimony pressure to prefer simpler expressions. Analyzing these composite features further reveals which interactions and transformations tend to be beneficial for tagging, offering insights that remain opaque in black-box deep models.

comment: 5 pages, 8 figures, accepted at ICASSP 2026

☆ A Probabilistic Generative Model for Spectral Speech Enhancement

Marco Hidalgo-Araya, Raphaël Trésor, Bart Van Erp, Wouter W. L. Nuijten, Thijs Van De Laar, Bert De Vries

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or listening contexts. This paper introduces a unified modular framework that formulates signal processing, learning, and personalization as Bayesian inference with explicit uncertainty tracking. The proposed framework replaces ad hoc algorithm design with a single probabilistic generative model that continuously adapts to changing acoustic conditions and user preferences. It extends spectral subtraction with principled mechanisms for in-situ personalization and adaptation to acoustic context. The system is implemented as an interconnected probabilistic state-space model, and inference is performed via variational message passing in the \texttt{RxInfer.jl} probabilistic programming environment, enabling real-time Bayesian processing under hearing-aid constraints. Proof-of-concept experiments on the \emph{VoiceBank+DEMAND} corpus show competitive speech quality and noise reduction with 85 effective parameters. The framework provides an interpretable, data-efficient foundation for uncertainty-aware, adaptive hearing-aid processing and points toward devices that learn continuously through probabilistic inference.

comment: Submitted to the IEEE Open Journal of Signal Processing

☆ Membership Inference Attacks against Large Audio Language Models

Jia-Kai Dong, Yu-Xiang Lin, Hung-Yi Lee

We present the first systematic Membership Inference Attack (MIA) evaluation of Large Audio Language Models (LALMs). As audio encodes non-semantic information, it induces severe train and test distribution shifts and can lead to spurious MIA performance. Using a multi-modal blind baseline based on textual, spectral, and prosodic features, we demonstrate that common speech datasets exhibit near-perfect train/test separability (AUC approximately 1.0) even without model inference, and the standard MIA scores strongly correlate with these blind acoustic artifacts (correlation greater than 0.7). Using this blind baseline, we identify that distribution-matched datasets enable reliable MIA evaluation without distribution shift confounds. We benchmark multiple MIA methods and conduct modality disentanglement experiments on these datasets. The results reveal that LALM memorization is cross-modal, arising only from binding a speaker's vocal identity with its text. These findings establish a principled standard for auditing LALMs beyond spurious correlations.

comment: submitted to Interspeech 2026

☆ On the Usefulness of Diffusion-Based Room Impulse Response Interpolation to Microphone Array Processing

Sagi Della Torre, Mirco Pezzoli, Fabio Antonacci, Sharon Gannot

Room Impulse Responses estimation is a fundamental problem in spatial audio processing and speech enhancement. In this paper, we build upon our previously introduced diffusion-based inpainting framework for Room Impulse Response interpolation and demonstrate its applicability to enhancing the performance of practical multi-microphone array processing tasks. Furthermore, we validate the robustness of this method in interpolating real-world Room Impulse Responses.

☆ MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions

Kexin Huang, Liwei Fan, Botian Jiang, Yaozhou Jiang, Qian Tu, Jie Zhu, Yuqian Zhang, Yiwei Zhao, Chenchen Yang, Zhaoye Fei, Shimin Li, Xiaogui Yang, Qinyuan Cheng, Xipeng Qiu

Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptions, allowing users to create voices tailored to specific roles, personalities, and emotions. Such controllable voice creation benefits a wide range of downstream applications-including storytelling, game dubbing, role-play agents, and conversational assistants, making it a significant task for modern Text-to-Speech models. However, existing models are largely trained on carefully recorded studio data, which produces speech that is clean and well-articulated, yet lacks the lived-in qualities of real human voices. To address these limitations, we present MOSS-VoiceGenerator, an open-source instruction-driven voice generation model that creates new timbres directly from natural language prompts. Motivated by the hypothesis that exposure to real-world acoustic variation produces more perceptually natural voices, we train on large-scale expressive speech data sourced from cinematic content. Subjective preference studies demonstrate its superiority in overall performance, instruction-following, and naturalness compared to other voice design models.

☆ Audio Language Model for Deepfake Detection Grounded in Acoustic Chain-of-Thought

Runkun Chen, Yixiong Fang, Pengyu Chang, Yuante Li, Massa Baali, Bhiksha Ramakrishnan

☆ On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR

Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar

Automatic speech recognition (ASR) has advanced rapidly in recent years, driven by large-scale pretrained models and end-to-end architectures such as SLAM-ASR. A key component of SLAM-ASR systems is the Whisper speech encoder, which provides robust acoustic representations. While model pruning has been explored for the full Whisper encoder-decoder architecture, its impact within the SLAM-ASR setting remains under-investigated. In this work, we analyze the effects of layer pruning in the Whisper encoder when used as the acoustic backbone of SLAM-ASR. We further examine the extent to which LoRA-based fine-tuning can recover performance degradation caused by pruning. Experiments conducted across three Whisper variants (Small, Medium, Large-v2), three languages representing distinct resource levels (Danish, Dutch, English), and over 200 training runs demonstrate that pruning two encoder layers causes only 2-4% WER degradation, and that combining this pruning with LoRA adaptation consistently outperforms the unpruned baseline while reducing total parameters by 7-14%. Moreover, our error analysis reveals that LoRA primarily compensates through the language model's linguistic priors, reducing total word errors by 11-21% for Dutch and English, with substitutions and deletions showing the largest reductions. However, for low-resource Danish, the reduction is smaller (4-7%), and LoRA introduces increased insertion errors, indicating that compensation effectiveness depends on the LLM's pre-existing language proficiency and available training data.

comment: Accepted at SPEAKABLE Workshop, LREC 2026

☆ An Empirical Recipe for Universal Phone Recognition

Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi, Eunjung Yeo, William Chen, Shinji Watanabe, David R. Mortensen

Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive. Highly performant English-focused models do not generalize across languages, while multilingual models underutilize pretrained representations. It also remains unclear how data scale, architecture, and training objective contribute to multilingual PR. We present PhoneticXEUS -- trained on large-scale multilingual data and achieving state-of-the-art performance on both multilingual (17.7% PFER) and accented English speech (10.6% PFER). Through controlled ablations with evaluations across 100+ languages under a unified scheme, we empirically establish our training recipe and quantify the impact of SSL representations, data scale, and loss objectives. In addition, we analyze error patterns across language families, accented speech, and articulatory features. All data and code are released openly.

comment: Submitted to Interspeech 2026. Code: https://github.com/changelinglab/PhoneticXeus

♻ ☆ Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Rao Koluguri, Piotr Żelasko, Somshubra Majumdar, Adel Moumen, Sanchit Gandhi

We present the Open ASR Leaderboard, a reproducible benchmarking platform with community contributions from academia and industry. It compares 86 open-source and proprietary systems across 12 datasets, with English short- and long-form and multilingual short-form tracks. We standardize word error rate (WER) and inverse real-time factor (RTFx) evaluation for consistent accuracy-efficiency comparisons across model architectures and toolkits (e.g., ESPNet, NeMo, SpeechBrain, Transformers). We observe that Conformer-based encoders paired with transformer-based decoders achieve the best average WER, while connectionist temporal classification (CTC) and token-and-duration transducer (TDT) decoders offer superior RTFx, making them better suited for long-form and batched processing. All code and dataset loaders are open-sourced to support transparent, extensible evaluation. We present our evaluation methodology to facilitate community-driven benchmarking in ASR and other tasks.

comment: Leaderboard: https://huggingface.co/spaces/hf-audio/open_asr_leaderboard ; Code: https://github.com/huggingface/open_asr_leaderboard

♻ ☆ UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking

Xuangeng Chu, Ruicong Liu, Yifei Huang, Yun Liu, Yichen Peng, Bo Zheng

Generating lifelike conversational avatars requires modeling not just isolated speakers, but the dynamic, reciprocal interaction of speaking and listening. However, modeling the listener is exceptionally challenging: direct audio-driven training fails, producing stiff, static listening motions. This failure stems from a fundamental imbalance: the speaker's motion is strongly driven by speech audio, while the listener's motion primarily follows an internal motion prior and is only loosely guided by external speech. This challenge has led most methods to focus on speak-only generation. The only prior attempt at joint generation relies on extra speaker's motion to produce the listener. This design is not end-to-end, thereby hindering the real-time applicability. To address this limitation, we present UniLS, the first end-to-end framework for generating unified speak-listen expressions, driven by only dual-track audio. Our method introduces a novel two-stage training paradigm. Stage 1 first learns the internal motion prior by training an audio-free autoregressive generator, capturing the spontaneous dynamics of natural facial motion. Stage 2 then introduces the dual-track audio, fine-tuning the generator to modulate the learned motion prior based on external speech cues. Extensive evaluations show UniLS achieves state-of-the-art speaking accuracy. More importantly, it delivers up to 44.1\% improvement in listening metrics, generating significantly more diverse and natural listening expressions. This effectively mitigates the stiffness problem and provides a practical, high-fidelity audio-driven solution for interactive digital humans. Code and demos are available at https://xg-chu.site/project_unils/.

comment: CVPR 2026, code is available at https://github.com/xg-chu/UniLS, more demos are available at https://xg-chu.site/project_unils/

♻ ☆ POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation

Xuanchen Li, Chenrui Cui, Tianrui Wang, Meng Ge, Zikang Huang, Jin Li, Yizhou Peng, Yuheng Lu, Nyima Tashi, Longbiao Wang, Jianwu Dang

♻ ☆ PAVAS: Physics-Aware Video-to-Audio Synthesis

Oh Hyun-Bin, Yuhta Takida, Toshimitsu Uesaka, Tae-Hyun Oh, Yuki Mitsufuji

Recent advances in Video-to-Audio (V2A) generation have achieved impressive perceptual quality and temporal synchronization, yet most models remain appearance-driven, capturing visual-acoustic correlations without considering the physical factors that shape real-world sounds. We present Physics-Aware Video-to-Audio Synthesis (PAVAS), a method that incorporates physical reasoning into a latent diffusion-based V2A generation through the Physics-Driven Audio Adapter (Phy-Adapter). The adapter receives object-level physical parameters estimated by the Physical Parameter Estimator (PPE), which uses a Vision-Language Model (VLM) to infer the moving-object mass and a segmentation-based dynamic 3D reconstruction module to recover its motion trajectory for velocity computation. These physical cues enable the model to synthesize sounds that reflect underlying physical factors. To assess physical realism, we curate VGG-Impact, a benchmark focusing on object-object interactions, and introduce Audio-Physics Correlation Coefficient (APCC), an evaluation metric that measures consistency between physical and auditory attributes. Comprehensive experiments show that PAVAS produces physically plausible and perceptually coherent audio, outperforming existing V2A models in both quantitative and qualitative evaluations. Visit https://physics-aware-video-to-audio-synthesis.github.io for demo videos.

♻ ☆ Listen to Rhythm, Choose Movements: Autoregressive Multimodal Dance Generation via Diffusion and Mamba with Decoupled Dance Dataset

Oran Duan, Yinghua Shen, Yingzhu Lv, Luyang Jie, Yaxin Liu, Qiong Wu

Advances in generative models and sequence learning have greatly promoted research in dance motion generation, yet current methods still suffer from coarse semantic control and poor coherence in long sequences. In this work, we present Listen to Rhythm, Choose Movements (LRCM), a multimodal-guided diffusion framework supporting both diverse input modalities and autoregressive dance motion generation. We explore a feature decoupling paradigm for dance datasets and generalize it to the Motorica Dance dataset, separating motion capture data, audio rhythm, and professionally annotated global and local text descriptions. Our diffusion architecture integrates an audio-latent Conformer and a text-latent Cross-Conformer, and incorporates a Motion Temporal Mamba Module (MTMM) to enable smooth, long-duration autoregressive synthesis. Experimental results indicate that LRCM delivers strong performance in both functional capability and quantitative metrics, demonstrating notable potential in multimodal input scenarios and extended sequence generation. We will release the full codebase, dataset, and pretrained models publicly upon acceptance.

comment: 12 pages, 13 figures

♻ ☆ Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models

Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park

As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction. However, the development of such models is constrained by the scarcity of high-quality, multi-speaker conversational data, as existing large-scale resources are predominantly single-speaker or limited in volume. Addressing the complex dynamics of natural dialogue, such as overlapping and back-channeling remains a challenge, with standard processing pipelines suffering from diarization errors and ASR hallucinations. To bridge this gap, we present a robust and scalable open-source data processing pipeline designed for full-duplex model.

comment: 34 pages, 7 figures, 11 tables

♻ ☆ Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR

Rishikesh Kumar Sharma, Safal Narshing Shrestha, Jenny Poudel, Rupak Tiwari, Arju Shrestha, Rupak Raj Ghimire, Bal Krishna Bal

Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources. In this work, we introduce Nwāchā Munā, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha, and establish the first benchmark using script-preserving acoustic modeling. We investigate whether proximal cross-lingual transfer from a geographically and linguistically adjacent language (Nepali) can rival large-scale multilingual pretraining in an ultra-low-resource Automatic Speech Recognition (ASR) setting. Fine-tuning a Nepali Conformer model reduces the Character Error Rate (CER) from a 52.54% zero-shot baseline to 17.59% with data augmentation, effectively matching the performance of the multilingual Whisper-Small model despite utilizing significantly fewer parameters. Our findings demonstrate that proximal transfer from Nepali language serves as a computationally efficient alternative to massive multilingual models. We openly release the dataset and benchmarks to digitally enable the Newari community and foster further research in Nepal Bhasha.

comment: Accepted in CHiPSAL@LREC 2026

Audio and Speech Processing 10

☆ ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

Anuj Diwan, Eunsol Choi, David Harwath

comment: Under review

☆ Acoustic-to-articulatory Inversion of the Complete Vocal Tract from RT-MRI with Various Audio Embeddings and Dataset Sizes

Sofiane Azzouz, Pierre-André Vuissoz, Yves Laprie

Articulatory-to-acoustic inversion strongly depends on the type of data used. While most previous studies rely on EMA, which is limited by the number of sensors and restricted to accessible articulators, we propose an approach aiming at a complete inversion of the vocal tract, from the glottis to the lips. To this end, we used approximately 3.5 hours of RT-MRI data from a single speaker. The innovation of our approach lies in the use of articulator contours automatically extracted from MRI images, rather than relying on the raw images themselves. By focusing on these contours, the model prioritizes the essential geometric dynamics of the vocal tract while discarding redundant pixel-level information. These contours, alongside denoised audio, were then processed using a Bi-LSTM architecture. Two experiments were conducted: (1) the analysis of the impact of the audio embedding, for which three types of embeddings were evaluated as input to the model (MFCCs, LCCs, and HuBERT), and (2) the study of the influence of the dataset size, which we varied from 10 minutes to 3.5 hours. Evaluation was performed on the test data using RMSE, median error, as well as Tract Variables, to which we added an additional measurement: the larynx height. The average RMSE obtained is 1.48\,mm, compared with the pixel size (1.62\,mm). These results confirm the feasibility of a complete vocal-tract inversion using RT-MRI data.

☆ Can Hierarchical Cross-Modal Fusion Predict Human Perception of AI Dubbed Content? ICASSP 2026

Ashwini Dasare, Nirmesh Shah, Ashishkumar Gudmalwar, Pankaj Wasnik

Evaluating AI generated dubbed content is inherently multi-dimensional, shaped by synchronization, intelligibility, speaker consistency, emotional alignment, and semantic context. Human Mean Opinion Scores (MOS) remain the gold standard but are costly and impractical at scale. We present a hierarchical multimodal architecture for perceptually meaningful dubbing evaluation, integrating complementary cues from audio, video, and text. The model captures fine-grained features such as speaker identity, prosody, and content from audio, facial expressions and scene-level cues from video and semantic context from text, which are progressively fused through intra and inter-modal layers. Lightweight LoRA adapters enable parameter-efficient fine-tuning across modalities. To overcome limited subjective labels, we derive proxy MOS by aggregating objective metrics with weights optimized via active learning. The proposed architecture was trained on 12k Hindi-English bidirectional dubbed clips, followed by fine-tuning with human MOS. Our approach achieves strong perceptual alignment (PCC > 0.75), providing a scalable solution for automatic evaluation of AI-dubbed content.

comment: Accepted at ICASSP 2026

☆ VAANI: Capturing the language landscape for an inclusive digital India

Sujith Pulikodan, Abhayjeet Singh, Agneedh Basu, Lokesh Rady, Nihar Desai, Pavan Kumar J, Prajjwal Srivastav, Pranav D Bhat, Raghu Dharmaraju, Ritika Gupta, Sathvik Udupa, Saurabh Kumar, Sumit Sharma, Vaibhav Vishwakarma, Visruth Sanka, Dinesh Tewari, Harsh Dhand, Amrita Kamat, Sukhwinder Singh, Shikhar Vashishth, Partha Talukdar, Raj Acharya, Prasanta Kumar Ghosh

☆ BiFormer3D: Grid-Free Time-Domain Reconstruction of Head-Related Impulse Responses with a Spatially Encoded Transformer

Shaoheng Xu, Chunyi Sun, Jihui Zhang, Amy Bastine, Prasanga N. Samarasinghe, Thushara D. Abhayapala, Hongdong Li

Individualized head-related impulse responses (HRIRs) enable binaural rendering, but dense per-listener measurements are costly. We address HRIR spatial up-sampling from sparse per-listener measurements: given a few measured HRIRs for a listener, predict HRIRs at unmeasured target directions. Prior learning methods often work in the frequency domain, rely on minimum-phase assumptions or separate timing models, and use a fixed direction grid, which can degrade temporal fidelity and spatial continuity. We propose BiFormer3D, a time-domain, grid-free binaural Transformer for reconstructing HRIRs at arbitrary directions from sparse inputs. It uses sinusoidal spatial features, a Conv1D refinement module, and auxiliary interaural time difference (ITD) and interaural level difference (ILD) heads. On SONICOM, it improves normalized mean squared error (NMSE), cosine distance, and ITD/ILD errors over prior methods; ablations validate modules and show minimum-phase pre-processing is unnecessary.

comment: The paper was submitted for review to Interspeech 2026

☆ An Empirical Recipe for Universal Phone Recognition

Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi, Eunjung Yeo, William Chen, Shinji Watanabe, David R. Mortensen

comment: Submitted to Interspeech 2026. Code: https://github.com/changelinglab/PhoneticXeus

♻ ☆ Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Rao Koluguri, Piotr Żelasko, Somshubra Majumdar, Adel Moumen, Sanchit Gandhi

comment: Leaderboard: https://huggingface.co/spaces/hf-audio/open_asr_leaderboard ; Code: https://github.com/huggingface/open_asr_leaderboard

♻ ☆ Joint Optimization of Speaker and Spoof Detectors for Spoofing-Robust Automatic Speaker Verification

Oğuzhan Kurnaz, Jagabandhu Mishra, Tomi H. Kinnunen, Cemal Hanilçi

Spoofing-robust speaker verification (SASV) combines the tasks of speaker and spoof detection to authenticate speakers under adversarial settings. Many SASV systems rely on fusion of speaker and spoof cues at embedding, score or decision levels, based on independently trained subsystems. In this study, we respect similar modularity of the two subsystems, by integrating their outputs using trainable back-end classifiers. In particular, we explore various approaches for directly optimizing the back-end for the recently-proposed SASV performance metric (a-DCF) as a training objective. Our experiments on the ASVspoof 5 dataset demonstrate two important findings: (i) nonlinear score fusion consistently improves a-DCF over linear fusion, and (ii) the combination of weighted cosine scoring for speaker detection with SSL-AASIST for spoof detection achieves state-of-the-art performance, reducing min a-DCF to 0.196 and SPF-EER to 7.6%. These contributions highlight the importance of modular design, calibrated integration, and task-aligned optimization for advancing robust and interpretable SASV systems.

comment: submitted to IEEE/ACM Transactions on Audio, Speech and Language Processing

♻ ☆ X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

Di Cao, Dongjie Fu, Hai Yu, Siqi Zheng, Xu Tan, Tao Jin

While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts. The standard Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) training methods fail to close this gap. To address this, we propose X-OPD, a novel Cross-Modal On-Policy Distillation framework designed to systematically align the capabilities of Speech LLMs to their text-based counterparts. X-OPD enables the Speech LLM to explore its own distribution via on-policy rollouts, where a text-based teacher model evaluates these trajectories and provides token-level feedback, effectively distilling teacher's capabilities into student's multi-modal representations. Extensive experiments across multiple benchmarks demonstrate that X-OPD significantly narrows the gap in complex tasks while preserving the model's inherent capabilities.

comment: Submitted to Interspeech 2026

♻ ☆ Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models

Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park

comment: 34 pages, 7 figures, 11 tables

Computer Vision and Pattern Recognition 150

☆ Gen-Searcher: Reinforcing Agentic Search for Image Generation

Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jiang, Hongyu Li, Dian Zheng, Chenyang Wang, Xiangyu Yue

Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline and curate two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diverse search-intensive prompts and corresponding ground-truth synthesis images. We further introduce KnowGen, a comprehensive benchmark that explicitly requires search-grounded external knowledge for image generation and evaluates models from multiple dimensions. Based on these resources, we train Gen-Searcher with SFT followed by agentic reinforcement learning with dual reward feedback, which combines text-based and image-based rewards to provide more stable and informative learning signals for GRPO training. Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE. We hope this work can serve as an open foundation for search agents in image generation, and we fully open-source our data, models, and code.

comment: Project page: https://gen-searcher.vercel.app Code: https://github.com/tulerfeng/Gen-Searcher

☆ HandX: Scaling Bimanual Motion and Interaction Generation

Zimu Zhang, Yucheng Zhang, Xiyan Xu, Ziyin Wang, Sirui Xu, Kai Zhou, Bing Zhou, Chuan Guo, Jian Wang, Yu-Xiong Wang, Liang-Yan Gui

Synthesizing human motion has advanced rapidly, yet realistic hand motion and bimanual interaction remain underexplored. Whole-body models often miss the fine-grained cues that drive dexterous behavior, finger articulation, contact timing, and inter-hand coordination, and existing resources lack high-fidelity bimanual sequences that capture nuanced finger dynamics and collaboration. To fill this gap, we present HandX, a unified foundation spanning data, annotation, and evaluation. We consolidate and filter existing datasets for quality, and collect a new motion-capture dataset targeting underrepresented bimanual interactions with detailed finger dynamics. For scalable annotation, we introduce a decoupled strategy that extracts representative motion features, e.g., contact events and finger flexion, and then leverages reasoning from large language models to produce fine-grained, semantically rich descriptions aligned with these features. Building on the resulting data and annotations, we benchmark diffusion and autoregressive models with versatile conditioning modes. Experiments demonstrate high-quality dexterous motion generation, supported by our newly proposed hand-focused metrics. We further observe clear scaling trends: larger models trained on larger, higher-quality datasets produce more semantically coherent bimanual motion. Our dataset is released to support future research.

comment: CVPR 2026. Project Page: https://handx-project.github.io. Code: https://github.com/handx-project/HandX

☆ PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models

Lorenza Prospero, Orest Kupyn, Ostap Viniavskyi, João F. Henriques, Christian Rupprecht

Acquiring labeled datasets for 3D human mesh estimation is challenging due to depth ambiguities and the inherent difficulty of annotating 3D geometry from monocular images. Existing datasets are either real, with manually annotated 3D geometry and limited scale, or synthetic, rendered from 3D engines that provide precise labels but suffer from limited photorealism, low diversity, and high production costs. In this work, we explore a third path: generated data. We introduce PoseDreamer, a novel pipeline that leverages diffusion models to generate large-scale synthetic datasets with 3D mesh annotations. Our approach combines controllable image generation with Direct Preference Optimization for control alignment, curriculum-based hard sample mining, and multi-stage quality filtering. Together, these components naturally maintain correspondence between 3D labels and generated images, while prioritizing challenging samples to maximize dataset utility. Using PoseDreamer, we generate more than 500,000 high-quality synthetic samples, achieving a 76% improvement in image-quality metrics compared to rendering-based datasets. Models trained on PoseDreamer achieve performance comparable to or superior to those trained on real-world and traditional synthetic datasets. In addition, combining PoseDreamer with synthetic datasets results in better performance than combining real-world and synthetic datasets, demonstrating the complementary nature of our dataset. We will release the full dataset and generation code.

☆ On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or

Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt. This typicality bias presents a challenge for creative applications that require a wide range of generative outcomes. We identify a fundamental trade-off in current approaches to diversity: modifying model inputs requires costly optimization to incorporate feedback from the generative path. In contrast, acting on spatially-committed intermediate latents tends to disrupt the forming visual structure, leading to artifacts. In this work, we propose to apply repulsion in the Contextual Space as a novel framework for achieving rich diversity in Diffusion Transformers. By intervening in the multimodal attention channels, we apply on-the-fly repulsion during the transformer's forward pass, injecting the intervention between blocks where text conditioning is enriched with emergent image structure. This allows for redirecting the guidance trajectory after it is structurally informed but before the composition is fixed. Our results demonstrate that repulsion in the Contextual Space produces significantly richer diversity without sacrificing visual fidelity or semantic adherence. Furthermore, our method is uniquely efficient, imposing a small computational overhead while remaining effective even in modern "Turbo" and distilled models where traditional trajectory-based interventions typically fail.

comment: Conditionally accepted to SIGGRAPH 2026. Project page: https://contextual-repulsion.github.io/

☆ SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild

Patrick Rim, Kevin Harris, Braden Copple, Shangchen Han, Xu Xie, Ivan Shugurov, Sizhe An, He Wen, Alex Wong, Tomas Hodan, Kun He

Accurate 3D understanding of human hands and objects during manipulation remains a significant challenge for egocentric computer vision. Existing hand-object interaction datasets are predominantly captured in controlled studio settings, which limits both environmental diversity and the ability of models trained on such data to generalize to real-world scenarios. To address this challenge, we introduce a novel marker-less multi-camera system that allows for nearly unconstrained mobility in genuinely in-the-wild conditions, while still having the ability to generate precise 3D annotations of hands and objects. The capture system consists of a lightweight, back-mounted, multi-camera rig that is synchronized and calibrated with a user-worn VR headset. For 3D ground-truth annotation of hands and objects, we develop an ego-exo tracking pipeline and rigorously evaluate its quality. Finally, we present SHOW3D, the first large-scale dataset with 3D annotations that show hands interacting with objects in diverse real-world environments, including outdoor settings. Our approach significantly reduces the fundamental trade-off between environmental realism and accuracy of 3D annotations, which we validate with experiments on several downstream tasks. show3d-dataset.github.io

comment: CVPR 2026

☆ FlowIt: Global Matching for Optical Flow with Confidence-Guided Refinement

Sadra Safadoust, Fabio Tosi, Matteo Poggi, Fatma Güney

We present FlowIt, a novel architecture for optical flow estimation designed to robustly handle large pixel displacements. At its core, FlowIt leverages a hierarchical transformer architecture that captures extensive global context, enabling the model to effectively model long-range correspondences. To overcome the limitations of localized matching, we formulate the flow initialization as an optimal transport problem. This formulation yields a highly robust initial flow field, alongside explicitly derived occlusion and confidence maps. These cues are then seamlessly integrated into a guided refinement stage, where the network actively propagates reliable motion estimates from high-confidence regions into ambiguous, low-confidence areas. Extensive experiments across the Sintel, KITTI, Spring, and LayeredFlow datasets validate the efficacy of our approach. FlowIt achieves state-of-the-art results on the competitive Sintel and KITTI benchmarks, while simultaneously establishing new state-of-the-art cross-dataset zero-shot generalization performance on Sintel, Spring, and LayeredFlow.

☆ SonoWorld: From One Image to a 3D Audio-Visual Scene

Derong Jin, Xiyi Chen, Ming C. Lin, Ruohan Gao

comment: Accepted by CVPR 2026, project page: https://humathe.github.io/sonoworld/

☆ Pandora: Articulated 3D Scene Graphs from Egocentric Vision

Alan Yu, Yun Chang, Christopher Xie, Luca Carlone

Robotic mapping systems typically approach building metric-semantic scene representations from the robot's own sensors and cameras. However, these "first person" maps inherit the robot's own limitations due to its embodiment or skillset, which may leave many aspects of the environment unexplored. For example, the robot might not be able to open drawers or access wall cabinets. In this sense, the map representation is not as complete, and requires a more capable robot to fill in the gaps. We narrow these blind spots in current methods by leveraging egocentric data captured as a human naturally explores a scene wearing Project Aria glasses, giving a way to directly transfer knowledge about articulation from the human to any deployable robot. We demonstrate that, by using simple heuristics, we can leverage egocentric data to recover models of articulate object parts, with quality comparable to those of state-of-the-art methods based on other input modalities. We also show how to integrate these models into 3D scene graph representations, leading to a better understanding of object dynamics and object-container relationships. We finally demonstrate that these articulated 3D scene graphs enhance a robot's ability to perform mobile manipulation tasks, showcasing an application where a Boston Dynamics Spot is tasked with retrieving concealed target items, given only the 3D scene graph as input.

comment: 14 pages, 5 figures. Presented at the 2025 British Machine Vision Conference (BMVC) in Sheffield, UK

☆ SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

Philip Schroeder, Thomas Weng, Karl Schmeckpeper, Eric Rosen, Stephen Hart, Ondrej Biza

Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervise robot learning. However, when used as evaluators in reinforcement learning (RL), today's strongest models often fail under partial observability and distribution shift, enabling policies to exploit perceptual errors rather than solve the task. To address this limitation, we introduce SOLE-R1 (Self-Observing LEarner), a video-language reasoning model explicitly designed to serve as the sole reward signal for online RL. Given only raw video observations and a natural-language goal, SOLE-R1 performs per-timestep spatiotemporal chain-of-thought (CoT) reasoning and produces dense estimates of task progress that can be used directly as rewards. To train SOLE-R1, we develop a large-scale video trajectory and reasoning synthesis pipeline that generates temporally grounded CoT traces aligned with continuous progress supervision. This data is combined with foundational spatial and multi-frame temporal reasoning, and used to train the model with a hybrid framework that couples supervised fine-tuning with RL from verifiable rewards. Across four different simulation environments and a real-robot setting, SOLE-R1 enables zero-shot online RL from random initialization: robots learn previously unseen manipulation tasks without ground-truth rewards, success indicators, demonstrations, or task-specific tuning. SOLE-R1 succeeds on 24 unseen tasks and substantially outperforms strong vision-language rewarders, including GPT-5 and Gemini-3-Pro, while exhibiting markedly greater robustness to reward hacking.

☆ Stepwise Credit Assignment for GRPO on Flow-Matching Models

Yash Savani, Branislav Kveton, Yuchen Liu, Yilin Wang, Jing Shi, Subhojyoti Mukherjee, Nikos Vlassis, Krishna Kumar Singh

Flow-GRPO successfully applies reinforcement learning to flow models, but uses uniform credit assignment across all steps. This ignores the temporal structure of diffusion generation: early steps determine composition and content (low-frequency structure), while late steps resolve details and textures (high-frequency details). Moreover, assigning uniform credit based solely on the final image can inadvertently reward suboptimal intermediate steps, especially when errors are corrected later in the diffusion trajectory. We propose Stepwise-Flow-GRPO, which assigns credit based on each step's reward improvement. By leveraging Tweedie's formula to obtain intermediate reward estimates and introducing gain-based advantages, our method achieves superior sample efficiency and faster convergence. We also introduce a DDIM-inspired SDE that improves reward quality while preserving stochasticity for policy gradients.

comment: Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026 Project page: https://stepwiseflowgrpo.com

☆ DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing

Kailai Feng, Yuxiang Wei, Bo Chen, Yang Pan, Hu Ye, Songwei Liu, Chenqian Yan, Yuan Gao

Diffusion models have made significant progress in both text-to-image (T2I) generation and text-guided image editing. However, these models are typically built with billions of parameters, leading to high latency and increased deployment challenges. While on-device diffusion models improve efficiency, they largely focus on T2I generation and lack support for image editing. In this paper, we propose DreamLite, a compact unified on-device diffusion model (0.39B) that supports both T2I generation and text-guided image editing within a single network. DreamLite is built on a pruned mobile U-Net backbone and unifies conditioning through in-context spatial concatenation in the latent space. It concatenates images horizontally as input, using a (target | blank) configuration for generation tasks and (target | source) for editing tasks. To stabilize the training of this compact model, we introduce a task-progressive joint pretraining strategy that sequentially targets T2I, editing, and joint tasks. After high-quality SFT and reinforcement learning, DreamLite achieves GenEval (0.72) for image generation and ImgEdit (4.11) for image editing, outperforming existing on-device models and remaining competitive with several server-side models. By employing step distillation, we further reduce denoising processing to just 4 steps, enabling our DreamLite could generate or edit a 1024 x 1024 image in less than 1s on a Xiaomi 14 smartphone. To the best of our knowledge, DreamLite is the first unified on-device diffusion model that supports both image generation and image editing.

comment: https://carlofkl.github.io/dreamlite/

☆ AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding

Haozhe Qi, Kevin Qu, Mahdi Rad, Rui Wang, Alexander Mathis, Marc Pollefeys

Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches mitigate this by scoring and selecting frames/tokens within short clips, but they lack a principled mechanism to (i) compare relevance across distant video clips and (ii) stop processing once sufficient evidence has been gathered. We propose AdaptToken, a training-free framework that turns an MLLM's self-uncertainty into a global control signal for long-video token selection. AdaptToken splits a video into groups, extracts cross-modal attention to rank tokens within each group, and uses the model's response entropy to estimate each group's prompt relevance. This entropy signal enables a global token budget allocation across groups and further supports early stopping (AdaptToken-Lite), skipping the remaining groups when the model becomes sufficiently certain. Across four long-video benchmarks (VideoMME, LongVideoBench, LVBench, and MLVU) and multiple base MLLMs (7B-72B), AdaptToken consistently improves accuracy (e.g., +6.7 on average over Qwen2.5-VL 7B) and continues to benefit from extremely long inputs (up to 10K frames), while AdaptToken-Lite reduces inference time by about half with comparable performance. Project page: https://haozheqi.github.io/adapt-token

comment: Project page: https://haozheqi.github.io/adapt-token

☆ Why Aggregate Accuracy is Inadequate for Evaluating Fairness in Law Enforcement Facial Recognition Systems

Khalid Adnan Alsayed

Facial recognition systems are increasingly deployed in law enforcement and security contexts, where algorithmic decisions can carry significant societal consequences. Despite high reported accuracy, growing evidence demonstrates that such systems often exhibit uneven performance across demographic groups, leading to disproportionate error rates and potential harm. This paper argues that aggregate accuracy is an insufficient metric for evaluating the fairness and reliability of facial recognition systems in high-stakes environments. Through analysis of subgroup-level error distribution, including false positive rate (FPR) and false negative rate (FNR), the paper demonstrates how aggregate performance metrics can obscure critical disparities across demographic groups. Empirical observations show that systems with similar overall accuracy can exhibit substantially different fairness profiles, with subgroup error rates varying significantly despite a single aggregate metric. The paper further examines the operational risks associated with accuracy-centric evaluation practices in law enforcement applications, where misclassification may result in wrongful suspicion or missed identification. It highlights the importance of fairness-aware evaluation approaches and model-agnostic auditing strategies that enable post-deployment assessment of real-world systems. The findings emphasise the need to move beyond accuracy as a primary metric and adopt more comprehensive evaluation frameworks for responsible AI deployment.

comment: 9 pages, 2 tables, 1 figure. Position paper with empirical subgroup analysis highlighting limitations of aggregate accuracy in fairness evaluation

☆ Sim-to-Real Fruit Detection Using Synthetic Data: Quantitative Evaluation and Embedded Deployment with Isaac Sim

Martina Hutter-Mironovova

This study investigates the effectiveness of synthetic data for sim-to-real transfer in object detection under constrained data conditions and embedded deployment requirements. Synthetic datasets were generated in NVIDIA Isaac Sim and combined with limited real-world fruit images to train YOLO-based detection models under real-only, synthetic-only, and hybrid regimes. Performance was evaluated on two test datasets: an in-domain dataset with conditions matching the training data and a domain shift dataset containing real fruit and different background conditions. Results show that models trained exclusively on real data achieve the highest accuracy, while synthetic-only models exhibit reduced performance due to a domain gap. Hybrid training strategies significantly improve performance compared to synthetic-only approaches and achieve results close to real-only training while reducing the need for manual annotation. Under domain shift conditions, all models show performance degradation, with hybrid models providing improved robustness. The trained models were successfully deployed on a Jetson Orin NX using TensorRT optimization, achieving real-time inference performance. The findings highlight that synthetic data is most effective when used in combination with real data and that deployment constraints must be considered alongside detection accuracy.

comment: 18 pages, 6 figures

☆ Industrial3D: A Terrestrial LiDAR Point Cloud Dataset and CrossParadigm Benchmark for Industrial Infrastructure

Chao Yin, Hongzhe Yue, Qing Han, Difeng Hu, Zhenyu Liang, Fangzhou Lin, Bing Sun, Boyu Wang, Mingkai Li, Wei Yao, Jack C. P. Cheng

Automated semantic understanding of dense point clouds is a prerequisite for Scan-to-BIM pipelines, digital twin construction, and as-built verification--core tasks in the digital transformation of the construction industry. Yet for industrial mechanical, electrical, and plumbing (MEP) facilities, this challenge remains largely unsolved: TLS acquisitions of water treatment plants, chiller halls, and pumping stations exhibit extreme geometric ambiguity, severe occlusion, and extreme class imbalance that architectural benchmarks (e.g., S3DIS or ScanNet) cannot adequately represent. We present Industrial3D, a terrestrial LiDAR dataset comprising 612 million expertly labelled points at 6 mm resolution from 13 water treatment facilities. At 6.6x the scale of the closest comparable MEP dataset, Industrial3D provides the largest and most demanding testbed for industrial 3D scene understanding to date. We further establish the first industrial cross-paradigm benchmark, evaluating nine representative methods across fully supervised, weakly supervised, unsupervised, and foundation model settings under a unified benchmark protocol. The best supervised method achieves 55.74% mIoU, whereas zero-shot Point-SAM reaches only 15.79%--a 39.95 percentage-point gap that quantifies the unresolved domain-transfer challenge for industrial TLS data. Systematic analysis reveals that this gap originates from a dual crisis: statistical rarity (215:1 imbalance, 3.5x more severe than S3DIS) and geometric ambiguity (tail-class points share cylindrical primitives with head-class pipes) that frequency-based re-weighting alone cannot resolve. Industrial3D, along with benchmark code and pre-trained models, will be publicly available at https://github.com/pointcloudyc/Industrial3D.

comment: 49 pages, 8 figure, 14 tables

☆ Divide and Restore: A Modular Task-Decoupled Framework for Universal Image Restoration

Joanna Wiekiera, Martyna Zur

Restoring images affected by various types of degradation, such as noise, blur, or improper exposure, remains a significant challenge in computer vision. While recent trends favor complex monolithic all-in-one architectures, these models often suffer from negative task interference and require extensive joint training cycles on high-end computing clusters. In this paper, we propose a modular, task-decoupled image restoration framework based on an explicit diagnostic routing mechanism. The architecture consists of a lightweight Convolutional Neural Network (CNN) classifier that evaluates the input image and dynamically directs it to a specialized restoration node. A key advantage of this framework is its model-agnostic extensibility: while we demonstrate it using three independent U-Net experts, the system allows for the integration of any restoration method tailored to specific tasks. By isolating reconstruction paths, the framework prevents feature conflicts and significantly reduces training overhead. Unlike monolithic models, adding new degradation types in our framework only requires training a single expert and updating the router, rather than a full system retraining. Experimental results demonstrate that this computationally accessible approach offers a scalable and efficient solution for multi-degradation restoration on standard local hardware. The code will be published upon paper acceptance.

☆ TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark

Hannes Mareen, Dimitrios Karageorgiou, Paschalis Giakoumoglou, Peter Lambert, Symeon Papadopoulos, Glenn Van Wallendael

Generative AI has made text-guided inpainting a powerful image editing tool, but at the same time a growing challenge for media forensics. Existing benchmarks, including our text-guided inpainting forgery (TGIF) dataset, show that image forgery localization (IFL) methods can localize manipulations in spliced images but struggle not in fully regenerated (FR) images, while synthetic image detection (SID) methods can detect fully regenerated images but cannot perform localization. With new generative inpainting models emerging and the open problem of localization in FR images remaining, updated datasets and benchmarks are needed. We introduce TGIF2, an extended version of TGIF, that captures recent advances in text-guided inpainting and enables a deeper analysis of forensic robustness. TGIF2 augments the original dataset with edits generated by FLUX.1 models, as well as with random non-semantic masks. Using the TGIF2 dataset, we conduct a forensic evaluation spanning IFL and SID, including fine-tuning IFL methods on FR images and generative super-resolution attacks. Our experiments show that both IFL and SID methods degrade on FLUX.1 manipulations, highlighting limited generalization. Additionally, while fine-tuning improves localization on FR images, evaluation with random non-semantic masks reveals object bias. Furthermore, generative super-resolution significantly weakens forensic traces, demonstrating that common image enhancement operations can undermine current forensic pipelines. In summary, TGIF2 provides an updated dataset and benchmark, which enables new insights into the challenges posed by modern inpainting and AI-based image enhancements. TGIF2 is available at https://github.com/IDLabMedia/tgif-dataset.

comment: 33 pages, accepted at Journal on Information Security

☆ ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning

Huanxuan Liao, Zhongtao Jiang, Yupu Hao, Yuqiao Tan, Shizhu He, Jun Zhao, Kun Xu, Kang Liu

comment: work in progress

☆ Unsafe2Safe: Controllable Image Anonymization for Downstream Utility

Mih Dinh, SouYoung Jin

Large-scale image datasets frequently contain identifiable or sensitive content, raising privacy risks when training models that may memorize and leak such information. We present Unsafe2Safe, a fully automated pipeline that detects privacy-prone images and rewrites only their sensitive regions using multimodally guided diffusion editing. Unsafe2Safe operates in two stages. Stage 1 uses a vision-language model to (i) inspect images for privacy risks, (ii) generate paired private and public captions that respectively include and omit sensitive attributes, and (iii) prompt a large language model to produce structured, identity-neutral edit instructions conditioned on the public caption. Stage 2 employs instruction-driven diffusion editors to apply these dual textual prompts, producing privacy-safe images that preserve global structure and task-relevant semantics while neutralizing private content. To measure anonymization quality, we introduce a unified evaluation suite covering Quality, Cheating, Privacy, and Utility dimensions. Across MS-COCO, Caltech101, and MIT Indoor67, Unsafe2Safe reduces face similarity, text similarity, and demographic predictability by large margins, while maintaining downstream model accuracy comparable to training on raw data. Fine-tuning diffusion editors on our automatically generated triplets (private caption, public caption, edit instruction) further improves both privacy protection and semantic fidelity. Unsafe2Safe provides a scalable, principled solution for constructing large, privacy-safe datasets without sacrificing visual consistency or downstream utility.

comment: Accepted at CVPR 2026 and CVPR 2026 Workshop on Machine Unlearning for Computer Vision

☆ ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains ICLR 2026

Pavel Suma, Giorgos Kordopatis-Zilos, Yannis Kalantidis, Giorgos Tolias

Large-scale instance-level training data is scarce, so models are typically trained on domain-specific datasets. Yet in real-world retrieval, they must handle diverse domains, making generalization to unseen data critical. We introduce ELViS, an image-to-image similarity model that generalizes effectively to unseen domains. Unlike conventional approaches, our model operates in similarity space rather than representation space, promoting cross-domain transfer. It leverages local descriptor correspondences, refines their similarities through an optimal transport step with data-dependent gains that suppress uninformative descriptors, and aggregates strong correspondences via a voting process into an image-level similarity. This design injects strong inductive biases, yielding a simple, efficient, and interpretable model. To assess generalization, we compile a benchmark of eight datasets spanning landmarks, artworks, products, and multi-domain collections, and evaluate ELViS as a re-ranking method. Our experiments show that ELViS outperforms competing methods by a large margin in out-of-domain scenarios and on average, while requiring only a fraction of their computational cost. Code available at: https://github.com/pavelsuma/ELViS/

comment: ICLR 2026

☆ Detection of Adversarial Attacks in Robotic Perception

Ziad Sharawy, Mohammad Nakshbandiand, Sorin Mihai Grigorescu

comment: 9 pages, 6 figures. Accepted and presented at STE 2025, Transilvania University of Brasov, Romania

☆ ORSIFlow: Saliency-Guided Rectified Flow for Optical Remote Sensing Salient Object Detection

Haojing Chen, Yutong Li, Zhihang Liu, Tao Tan, Haoyu Bian, Qiuju Ma

Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) remains challenging due to complex backgrounds, low contrast, irregular object shapes, and large variations in object scale. Existing discriminative methods directly regress saliency maps, while recent diffusion-based generative approaches suffer from stochastic sampling and high computational cost. In this paper, we propose ORSIFlow, a saliency-guided rectified flow framework that reformulates ORSI-SOD as a deterministic latent flow generation problem. ORSIFlow performs saliency mask generation in a compact latent space constructed by a frozen variational autoencoder, enabling efficient inference with only a few steps. To enhance saliency awareness, we design a Salient Feature Discriminator for global semantic discrimination and a Salient Feature Calibrator for precise boundary refinement. Extensive experiments on multiple public benchmarks show that ORSIFlow achieves state-of-the-art performance with significantly improved efficiency. Codes are available at: https://github.com/Ch3nSir/ORSIFlow.

comment: Accepted by ICME 2026

☆ Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering

Yanjie Zhang, Yafei Li, Rui Sheng, Zixin Chen, Yanna Lin, Huamin Qu, Lei Chen, Yushi Sun

Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics, an agentic dual-path framework designed to unmask visual deception via a "skeptical" reasoning paradigm. Unlike holistic models, ChartCynics decouples perception from verification: a Diagnostic Vision Path captures structural anomalies (e.g., inverted axes) through strategic ROI cropping, while an OCR-Driven Data Path ensures numerical grounding. To resolve cross-modal conflicts, we introduce an Agentic Summarizer optimized via a two-stage protocol: Oracle-Informed SFT for reasoning distillation and Deception-Aware GRPO for adversarial alignment. This pipeline effectively penalizes visual traps and enforces logical consistency. Evaluations on two benchmarks show that ChartCynics achieves 74.43% and 64.55% accuracy, providing an absolute performance boost of ~29% over the Qwen3-VL-8B backbone, outperforming state-of-the-art proprietary models. Our results demonstrate that specialized agentic workflows can grant smaller open-source models superior robustness, establishing a new foundation for trustworthy chart interpretation.

comment: 10pages, 4 figures

☆ XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs

Chengyin Hu, Jiaju Han, Xuemeng Sun, Qike Zhang, Yiwei Wei, Ang Li, Chunlei Meng, Xiang Chen, Jiahuan Long

Vision-language models (VLMs) rely on a shared visual-textual representation space to perform tasks such as zero-shot classification, image captioning, and visual question answering (VQA). While this shared space enables strong cross-task generalization, it may also introduce a common vulnerability: small visual perturbations can propagate through the shared embedding space and cause correlated semantic failures across tasks. This risk is particularly important in interactive and decision-support settings, yet it remains unclear whether VLMs are robust to highly constrained, sparse, and geometrically fixed perturbations. To address this question, we propose X-shaped Sparse Pixel Attack (XSPA), an imperceptible structured attack that restricts perturbations to two intersecting diagonal lines. Compared with dense perturbations or flexible localized patches, XSPA operates under a much stricter attack budget and thus provides a more stringent test of VLM robustness. Within this sparse support, XSPA jointly optimizes a classification objective, cross-task semantic guidance, and regularization on perturbation magnitude and along-line smoothness, inducing transferable misclassification as well as semantic drift in captioning and VQA while preserving visual subtlety. Under the default setting, XSPA modifies only about 1.76% of image pixels. Experiments on the COCO dataset show that XSPA consistently degrades performance across all three tasks. Zero-shot accuracy drops by 52.33 points on OpenAI CLIP ViT-L/14 and 67.00 points on OpenCLIP ViT-B/16, while GPT-4-evaluated caption consistency decreases by up to 58.60 points and VQA correctness by up to 44.38 points. These results suggest that even highly sparse and visually subtle perturbations with fixed geometric priors can substantially disrupt cross-task semantics in VLMs, revealing a notable robustness gap in current multimodal systems.

☆ StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation

Yiran Shi, Dongqi Guo, Tianchen Zhao, Feng Gao, Liangzhi Shi, Chao Yu, ZhiJian Mo, Qihua Xiao, XiaoShuai Peng, Qingmin Liao, Yu Wang

Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models poses significant efficiency challenges, particularly for resource-constrained edge platforms in real-world deployments. However, since different stages of VLA (observation, action generation and execution) must proceed sequentially, and wait for the completion of the preceding stage, the system suffers from frequent halting and high latency. To address this, We conduct a systematic analysis to identify the challenges for fast and fluent generation, and propose enabling VLAs with the ability to asynchronously parallelize across VLA stages in a "streaming" manner. First, we eliminate the reliance on action chunking and adopt action flow matching, which learns the trajectory of action flows rather than denoising chunk-wise actions. It overlaps the latency of action generation and execution. Second, we design an action saliency-aware adaptive observation mechanism, thereby overlapping the latency of execution and observation. Without sacrificing performance, StreamingVLA achieves substantial speedup and improves the fluency of execution. It achieves a 2.4 $\times$ latency speedup and reduces execution halting by 6.5 $\times$.

☆ Curriculum-Guided Myocardial Scar Segmentation for Ischemic and Non-ischemic Cardiomyopathy

Nivetha Jayakumar, Jonathan Pan, Shuo Wang, Bishow Paudel, Nisha Hosadurg, Cristiane C. Singulane, Sivam Bhatt, Amit R. Patel, Miaomiao Zhang

Identification and quantification of myocardial scar is important for diagnosis and prognosis of cardiovascular diseases. However, reliable scar segmentation from Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR) images remains a challenge due to variations in contrast enhancement across patients, suboptimal imaging conditions such as post contrast washout, and inconsistencies in ground truth annotations on diffuse scars caused by inter observer variability. In this work, we propose a curriculum learning-based framework designed to improve segmentation performance under these challenging conditions. The method introduces a progressive training strategy that guides the model from high-confidence, clearly defined scar regions to low confidence or visually ambiguous samples with limited scar burden. By structuring the learning process in this manner, the network develops robustness to uncertain labels and subtle scar appearances that are often underrepresented in conventional training pipelines. Experimental results show that the proposed approach enhances segmentation accuracy and consistency, particularly for cases with minimal or diffuse scar, outperforming standard training baselines. This strategy provides a principled way to leverage imperfect data for improved myocardial scar quantification in clinical applications. Our code is publicly available on GitHub.

☆ Domain-Invariant Prompt Learning for Vision-Language Models

Arsham Gholamzadeh Khoee, Yinan Yu, Robert Feldt

Large pre-trained vision-language models like CLIP have transformed computer vision by aligning images and text in a shared feature space, enabling robust zero-shot transfer via prompting. Soft-prompting, such as Context Optimization (CoOp), effectively adapts these models for downstream recognition tasks by learning a set of context vectors. However, CoOp lacks explicit mechanisms for handling domain shifts across unseen distributions. To address this, we propose Domain-invariant Context Optimization (DiCoOp), an extension of CoOp optimized for domain generalization. By employing an adversarial training approach, DiCoOp forces the model to learn domain-invariant prompts while preserving discriminative power for classification. Experimental results show that DiCoOp consistently surpasses CoOp in domain generalization tasks across diverse visual domains.

☆ Hydra: Unifying Document Retrieval and Generation in a Single Vision-Language Model

Athos Georgiou

Visual document understanding typically requires separate retrieval and generation models, doubling memory and system complexity. We present Hydra, a dual-head approach that provides both ColBERT-style late-interaction retrieval and autoregressive generation from a single vision-language model (VLM). A single LoRA adapter, trained only for retrieval, is toggled at inference: enabling it produces multi-vector embeddings; disabling it recovers the base model's generation quality -- byte-identical outputs in 100% of 10,500 greedy and stochastic samples, with max delta-ANLS = 0.0044 across 15,301 samples on four VQA benchmarks (three informative; ChartQA is near-zero for both models under greedy decoding) when compared against an independent base-model pipeline. We identify three engineering requirements (attention-mode restoration, lm_head preservation, KV-cache-aware decoding) whose omission silently breaks generation despite correct weight recovery. On ViDoRe V1, Hydra (4B) is within 1 percentage point of a controlled single-head baseline in a single training run, with higher aggregate scores on V2 and V3 that are concentrated on a subset of tasks; multi-seed experiments are needed to confirm these trends. The single-model design reduces peak GPU memory by 41%, though adapter switching introduces throughput overhead under concurrent serving loads. An ablation shows that GritLM-style joint training provides no benefit within the LoRA-based (r=16) training regime. A proof-of-concept extension to Qwen2.5-Omni-3B demonstrates that the mechanism generalizes to audio retrieval and video embedding, with speech generation.

comment: Comments: 17 pages, 2 figures, 7 tables. ## Model Cards - https://huggingface.co/athrael-soju/HydraQwen3.5-4B - https://huggingface.co/athrael-soju/HydraQwen2.5-Omni-3B - https://huggingface.co/athrael-soju/ColQwen3.5-4B-controlled-baseline - https://huggingface.co/athrael-soju/DualHead-GritLM-Qwen3.5-4B ## Scripts & evals - https://github.com/athrael-soju/hydra

☆ MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structures

Tim Strohmeyer, Lucas Morin, Gerhard Ingmar Meijer, Valéry Weber, Ahmed Nassar, Peter Staar

Automatically extracting chemical structures from documents is essential for the large-scale analysis of the literature in chemistry. Automatic pipelines have been developed to recognize molecules represented either in figures or in text independently. However, methods for recognizing chemical structures from multimodal descriptions (Markush structures) lag behind in precision and cannot be used for automatic large-scale processing. In this work, we present MarkushGrapher-2, an end-to-end approach for the multimodal recognition of chemical structures in documents. First, our method employs a dedicated OCR model to extract text from chemical images. Second, the text, image, and layout information are jointly encoded through a Vision-Text-Layout encoder and an Optical Chemical Structure Recognition vision encoder. Finally, the resulting encodings are effectively fused through a two-stage training strategy and used to auto-regressively generate a representation of the Markush structure. To address the lack of training data, we introduce an automatic pipeline for constructing a large-scale dataset of real-world Markush structures. In addition, we present IP5-M, a large manually-annotated benchmark of real-world Markush structures, designed to advance research on this challenging task. Extensive experiments show that our approach substantially outperforms state-of-the-art models in multimodal Markush structure recognition, while maintaining strong performance in molecule structure recognition. Code, models, and datasets are released publicly.

comment: 15 pages, to be published in CVPR 2026

☆ Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow

Quan Meng, Yujin Chen, Lei Li, Matthias Nießner, Angela Dai

We present Seen2Scene, the first flow matching-based approach that trains directly on incomplete, real-world 3D scans for scene completion and generation. Unlike prior methods that rely on complete and hence synthetic 3D data, our approach introduces visibility-guided flow matching, which explicitly masks out unknown regions in real scans, enabling effective learning from real-world, partial observations. We represent 3D scenes using truncated signed distance field (TSDF) volumes encoded in sparse grids and employ a sparse transformer to efficiently model complex scene structures while masking unknown regions. We employ 3D layout boxes as an input conditioning signal, and our approach is flexibly adapted to various other inputs such as text or partial scans. By learning directly from real-world, incomplete 3D scans, Seen2Scene enables realistic 3D scene completion for complex, cluttered real environments. Experiments demonstrate that our model produces coherent, complete, and realistic 3D scenes, outperforming baselines in completion accuracy and generation quality.

comment: Project page: https://quan-meng.github.io/projects/seen2scene/ Video: https://www.youtube.com/watch?v=5qJYLjMsJe8

☆ GEditBench v2: A Human-Aligned Benchmark for General Image Editing

Zhangqi Jiang, Zheng Sun, Xianfang Zeng, Yufeng Yang, Xuanyang Zhang, Yongliang Wu, Wei Cheng, Gang Yu, Xu Yang, Bihan Wen

Recent advances in image editing have enabled models to handle complex instructions with impressive realism. However, existing evaluation frameworks lag behind: current benchmarks suffer from narrow task coverage, while standard metrics fail to adequately capture visual consistency, i.e., the preservation of identity, structure and semantic coherence between edited and original images. To address these limitations, we introduce GEditBench v2, a comprehensive benchmark with 1,200 real-world user queries spanning 23 tasks, including a dedicated open-set category for unconstrained, out-of-distribution editing instructions beyond predefined tasks. Furthermore, we propose PVC-Judge, an open-source pairwise assessment model for visual consistency, trained via two novel region-decoupled preference data synthesis pipelines. Besides, we construct VCReward-Bench using expert-annotated preference pairs to assess the alignment of PVC-Judge with human judgments on visual consistency evaluation. Experiments show that our PVC-Judge achieves state-of-the-art evaluation performance among open-source models and even surpasses GPT-5.1 on average. Finally, by benchmarking 16 frontier editing models, we show that GEditBench v2 enables more human-aligned evaluation, revealing critical limitations of current models, and providing a reliable foundation for advancing precise image editing.

comment: 30 pages, 24 figures

☆ ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation

Yu Sun, Meng Cao, Ping Yang, Rongtao Xu, Yunxiao Yan, Runze Xu, Liang Ma, Roy Gan, Andy Zhai, Qingxuan Chen, Zunnan Xu, Hao Wang, Jincheng Yu, Lucy Liang, Qian Wang, Ivan Laptev, Ian D Reid, Xiaodan Liang

Vision-Language-Action (VLA) models and world models have recently emerged as promising paradigms for general-purpose robotic intelligence, yet their progress is hindered by the lack of reliable evaluation protocols that reflect real-world deployment. Existing benchmarks are largely simulator-centric, which provide controllability but fail to capture the reality gap caused by perception noise, complex contact dynamics, hardware constraints, and system latency. Moreover, fragmented real-world evaluations across different robot platforms prevent fair and reproducible comparison. To address these challenges, we introduce ManipArena, a standardized evaluation framework designed to bridge simulation and real-world execution. ManipArena comprises 20 diverse tasks across 10,812 expert trajectories emphasizing reasoning-oriented manipulation tasks requiring semantic and spatial reasoning, supports multi-level generalization through controlled out-of-distribution settings, and incorporates long-horizon mobile manipulation beyond tabletop scenarios. The framework further provides rich sensory diagnostics, including low-level motor signals, and synchronized real-to-sim environments constructed via high-quality 3D scanning. Together, these features enable fair, realistic, and reproducible evaluation for both VLA and world model approaches, providing a scalable foundation for diagnosing and advancing embodied intelligence systems.

comment: Technical report for CVPR 2026 Challenge ManipArena

☆ RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Time

Anurag Ghosh, Srinivasa Narasimhan, Manmohan Chandraker, Francesco Pittaluga

We present LAD, a real-time language--action planner with an interruptible architecture that produces a motion plan in a single forward pass (~20 Hz) or generates textual reasoning alongside a motion plan (~10 Hz). LAD is fast enough for real-time closed-loop deployment, achieving ~3x lower latency than prior driving language models while setting a new learning-based state of the art on nuPlan Test14-Hard and InterPlan. We also introduce RAD, a rule-based planner designed to address structural limitations of PDM-Closed. RAD achieves state-of-the-art performance among rule-based planners on nuPlan Test14-Hard and InterPlan. Finally, we show that combining RAD and LAD enables hybrid planning that captures the strengths of both approaches. This hybrid system demonstrates that rules and learning provide complementary capabilities: rules support reliable maneuvering, while language enables adaptive and explainable decision-making.

☆ Generalizable Detection of AI Generated Images with Large Models and Fuzzy Decision Tree

Fei Wu, Guanghao Ding, Zijian Niu, Zhenrui Wang, Lei Yang, Zhuosheng Zhang, Shilin Wang

The malicious use and widespread dissemination of AI-generated images pose a serious threat to the authenticity of digital content. Existing detection methods exploit low-level artifacts left by common manipulation steps within the generation pipeline, but they often lack generalization due to model-specific overfitting. Recently, researchers have resorted to Multimodal Large Language Models (MLLMs) for AIGC detection, leveraging their high-level semantic reasoning and broad generalization capabilities. While promising, MLLMs lack the fine-grained perceptual sensitivity to subtle generation artifacts, making them inadequate as standalone detectors. To address this issue, we propose a novel AI-generated image detection framework that synergistically integrates lightweight artifact-aware detectors with MLLMs via a fuzzy decision tree. The decision tree treats the outputs of basic detectors as fuzzy membership values, enabling adaptive fusion of complementary cues from semantic and perceptual perspectives. Extensive experiments demonstrate that the proposed method achieves state-of-the-art accuracy and strong generalization across diverse generative models.

☆ Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs

Jin Bai, Huiyao Zhang, Qi Wen, Ningyang Li, Shengyang Li, Atta ur Rahman, Xiaolin Tian

The segmentation of thin linear structures is inherently topology allowbreak-critical, where minor local errors can sever long-range connectivity. While recent State-Space Models (SSMs) offer efficient long-range modeling, their isotropic serialization (e.g., raster scanning) creates a geometry mismatch for anisotropic targets, causing state propagation across rather than along the structure trajectories. To address this, we propose FGOS-Net, a framework based on frequency allowbreak-geometric disentanglement. We first decompose features into a stable topology carrier and directional high-frequency bands, leveraging the latter to explicitly correct spatial misalignments induced by downsampling. Building on this calibrated topology, we introduce frequency-aligned scanning that elevates serialization to a geometry-conditioned decision, preserving direction-consistent traces. Coupled with an active probing strategy to selectively inject high-frequency details and suppress texture ambiguity, FGOS-Net consistently outperforms strong baselines across four challenging benchmarks. Notably, it achieves 91.3% mIoU and 97.1% clDice on DeepCrack while running at 80 FPS with only 7.87 GFLOPs.

☆ MRI-to-CT synthesis using drifting models

Qing Lyu, Jianxu Wang, Jeremy Hudson, Ge Wang, Chirstopher T. Whitlow

Accurate MRI-to-CT synthesis could enable MR-only pelvic workflows by providing CT-like images with bone details while avoiding additional ionizing radiation. In this work, we investigate recently proposed drifting models for synthesizing pelvis CT images from MRI and benchmark them against convolutional neural networks (UNet, VAE), a generative adversarial network (WGAN-GP), a physics-inspired probabilistic model (PPFM), and diffusion-based methods (FastDDPM, DDIM, DDPM). Experiments are performed on two complementary datasets: Gold Atlas Male Pelvis and the SynthRAD2023 pelvis subset. Image fidelity and structural consistency are evaluated with SSIM, PSNR, and RMSE, complemented by qualitative assessment of anatomically critical regions such as cortical bone and pelvic soft-tissue interfaces. Across both datasets, the proposed drifting model achieves high SSIM and PSNR and low RMSE, surpassing strong diffusion baselines and conventional CNN-, VAE-, GAN-, and PPFM-based methods. Visual inspection shows sharper cortical bone edges, improved depiction of sacral and femoral head geometry, and reduced artifacts or over-smoothing, particularly at bone-air-soft tissue boundaries. Moreover, the drifting model attains these gains with one-step inference and inference times on the order of milliseconds, yielding a more favorable accuracy-efficiency trade-off than iterative diffusion sampling while remaining competitive in image quality. These findings suggest that drifting models are a promising direction for fast, high-quality pelvic synthetic CT generation from MRI and warrant further investigation for downstream applications such as MRI-only radiotherapy planning and PET/MR attenuation correction.

☆ ConceptWeaver: Weaving Disentangled Concepts with Flow

Jintao Chen, Aiming Hao, Xiaoqing Chen, Chengyu Bai, Chubin Chen, Yanxun Li, Jiahong Wu, Xiangxiang Chu, Shanghang Zhang

Pre-trained flow-based models excel at synthesizing complex scenes yet lack a direct mechanism for disentangling and customizing their underlying concepts from one-shot real-world sources. To demystify this process, we first introduce a novel differential probing technique to isolate and analyze the influence of individual concept tokens on the velocity field over time. This investigation yields a critical insight: the generative process is not monolithic but unfolds in three distinct stages. An initial \textbf{Blueprint Stage} establishes low-frequency structure, followed by a pivotal \textbf{Instantiation Stage} where content concepts emerge with peak intensity and become naturally disentangled, creating an optimal window for manipulation. A final concept-insensitive refinement stage then synthesizes fine-grained details. Guided by this discovery, we propose \textbf{ConceptWeaver}, a framework for one-shot concept disentanglement. ConceptWeaver learns concept-specific semantic offsets from a single reference image using a stage-aware optimization strategy that aligns with the three-stage framework. These learned offsets are then deployed during inference via our novel ConceptWeaver Guidance (CWG) mechanism, which strategically injects them at the appropriate generative stage. Extensive experiments validate that ConceptWeaver enables high-fidelity, compositional synthesis and editing, demonstrating that understanding and leveraging the intrinsic, staged nature of flow models is key to unlocking precise, multi-granularity content manipulation.

☆ INSID3: Training-Free In-Context Segmentation with DINOv3

Claudia Cuttano, Gabriele Trivigno, Christoph Reich, Daniel Cremers, Carlo Masone, Stefan Roth

In-context segmentation (ICS) aims to segment arbitrary concepts, e.g., objects, parts, or personalized instances, given one annotated visual examples. Existing work relies on (i) fine-tuning vision foundation models (VFMs), which improves in-domain results but harms generalization, or (ii) combines multiple frozen VFMs, which preserves generalization but yields architectural complexity and fixed segmentation granularities. We revisit ICS from a minimalist perspective and ask: Can a single self-supervised backbone support both semantic matching and segmentation, without any supervision or auxiliary models? We show that scaled-up dense self-supervised features from DINOv3 exhibit strong spatial structure and semantic correspondence. We introduce INSID3, a training-free approach that segments concepts at varying granularities only from frozen DINOv3 features, given an in-context example. INSID3 achieves state-of-the-art results across one-shot semantic, part, and personalized segmentation, outperforming previous work by +7.5 % mIoU, while using 3x fewer parameters and without any mask or category-level supervision. Code is available at https://github.com/visinf/INSID3 .

comment: CVPR 2026. Project page: https://visinf.github.io/INSID3

☆ CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains

Wenhan Wang, Zhixiang Zhou, Zhongtian Ma, Yanzhu Chen, Ziyu Lin, Hao Sheng, Pengfei Liu, Honglin Ma, Wenqi Shao, Qiaosheng Zhang, Yu Qiao

The connoisseurship of antique Chinese porcelain demands extensive historical expertise, material understanding, and aesthetic sensitivity, making it difficult for non-specialists to engage. To democratize cultural-heritage understanding and assist expert connoisseurship, we introduce CiQi-Agent -- a domain-specific Porcelain Connoisseurship Agent for intelligent analysis of antique Chinese porcelain. CiQi-Agent supports multi-image porcelain inputs and enables vision tool invocation and multimodal retrieval-augmented generation, performing fine-grained connoisseurship analysis across six attributes: dynasty, reign period, kiln site, glaze color, decorative motif, and vessel shape. Beyond attribute classification, it captures subtle visual details, retrieves relevant domain knowledge, and integrates visual and textual evidence to produce coherent, explainable connoisseurship descriptions. To achieve this capability, we construct a large-scale, expert-annotated dataset CiQi-VQA, comprising 29,596 porcelain specimens, 51,553 images, and 557,940 visual question--answering pairs, and further establish a comprehensive benchmark CiQi-Bench aligned with the previously mentioned six attributes. CiQi-Agent is trained through supervised fine-tuning, reinforcement learning, and a tool-augmented reasoning framework that integrates two categories of tools: a vision tool and multimodal retrieval tools. Experimental results show that CiQi-Agent (7B) outperforms all competitive open- and closed-source models across all six attributes on CiQi-Bench, achieving on average 12.2\% higher accuracy than GPT-5. The model and dataset have been released and are publicly available at https://huggingface.co/datasets/SII-Monument-Valley/CiQi-VQA.

☆ Post-hoc Self-explanation of CNNs

Ahcène Boubekki, Line H. Clemmensen

Although standard Convolutional Neural Networks (CNNs) can be mathematically reinterpreted as Self-Explainable Models (SEMs), their built-in prototypes do not on their own accurately represent the data. Replacing the final linear layer with a $k$-means-based classifier addresses this limitation without compromising performance. This work introduces a common formalization of $k$-means-based post-hoc explanations for the classifier, the encoder's final output (B4), and combinations of intermediate feature activations. The latter approach leverages the spatial consistency of convolutional receptive fields to generate concept-based explanation maps, which are supported by gradient-free feature attribution maps. Empirical evaluation with a ResNet34 shows that using shallower, less compressed feature activations, such as those from the last three blocks (B234), results in a trade-off between semantic fidelity and a slight reduction in predictive performance.

☆ Decoupling Wavelet Sub-bands for Single Source Domain Generalization in Fundus Image Segmentation

Shramana Dey, Varun Ajith, Abhirup Banerjee, Sushmita Mitra

Domain generalization in fundus imaging is challenging due to variations in acquisition conditions across devices and clinical settings. The inability to adapt to these variations causes performance degradation on unseen domains for deep learning models. Besides, obtaining annotated data across domains is often expensive and privacy constraints restricts their availability. Although single-source domain generalization (SDG) offers a realistic solution to this problem, the existing approaches frequently fail to capture anatomical topology or decouple appearance from anatomical features. This research introduces WaveSDG, a new wavelet-guided segmentation network for SDG. It decouples anatomical structure from domain-specific appearance through a wavelet sub-band decomposition. A novel Wavelet-based Invariant Structure Extraction and Refinement (WISER) module is proposed to process encoder features by leveraging distinct semantic roles of each wavelet sub-band. The module refines low-frequency components to anchor global anatomy, while selectively enhancing directional edges and suppressing noise within the high-frequency sub-bands. Extensive ablation studies validate the effectiveness of the WISER module and its decoupling strategy. Our evaluations on optic cup and optic disc segmentation across one source and five unseen target datasets show that WaveSDG consistently outperforms seven state-of-the-art methods. Notably, it achieves the best balanced Dice score and lowest 95th percentile Hausdorff distance with reduced variance, indicating improved accuracy, robustness, and cross-domain stability.

☆ $R_{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation

Linqian Fan, Peiqin Sun, Tiancheng Wen, Shun Lu, Chengru Song

Diffusion models achieve state-of-the-art generative performance but are fundamentally bottlenecked by their slow iterative sampling process. While diffusion distillation techniques enable high-fidelity few-step generation, traditional objectives often restrict the student's performance by anchoring it solely to the teacher. Recent approaches have attempted to break this ceiling by integrating Reinforcement Learning (RL), typically through a simple summation of distillation and RL objectives. In this work, we propose a novel paradigm by reconceptualizing distribution matching as a reward, denoted as $R_{dm}$. This unified perspective bridges the algorithmic gap between Diffusion Matching Distillation (DMD) and RL, providing several key benefits. (1) Enhanced optimization stability: we introduce Group Normalized Distribution Matching (GNDM), which adapts standard RL group normalization to stabilize $R_{dm}$ estimation. By leveraging group-mean statistics, GNDM establishes a more robust and effective optimization direction. (2) Seamless reward integration: our reward-centric formulation inherently supports adaptive weighting mechanisms, allowing flexible combination of DMD with external reward models. (3) Improved sampling efficiency: by aligning with RL principles, the framework readily incorporates importance sampling (IS), leading to a significant boost in sampling efficiency. Extensive experiments demonstrate that GNDM outperforms vanilla DMD, reducing the FID by 1.87. Furthermore, our multi-reward variant, GNDMR, surpasses existing baselines by achieving a strong balance between aesthetic quality and fidelity, reaching a peak HPS of 30.37 and a low FID-SD of 12.21. Overall, $R_{dm}$ provides a flexible, stable, and efficient framework for real-time high-fidelity synthesis. Code will be released upon publication.

☆ FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation

Tiantian Wang, Xiang Xiang, Simon S. Du

In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical applications, data across agent nodes within the distributed framework often exhibits non-independent and identically distributed (non-IID) characteristics, rendering traditional continual learning methods inapplicable. To address these challenges, this paper covers more comprehensive incremental task scenarios and proposes a dynamic memory allocation strategy for exemplar storage based on the data replay mechanism. This strategy fully taps into the inherent potential of data heterogeneity, while taking into account the performance fairness of all participating clients, thereby establishing a balanced and adaptive solution to mitigate catastrophic forgetting. Unlike the fixed allocation of client exemplar memory, the proposed scheme emphasizes the rational allocation of limited storage resources among clients to improve model performance. Furthermore, extensive experiments are conducted on three medical image datasets, and the results demonstrate significant performance improvements compared to existing baseline models.

☆ GeoHCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting

Xuan Deng, Xiandong Meng, Hengyu Man, Qiang Zhu, Tiange Zhang, Debin Zhao, Xiaopeng Fan

Although 3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, its prohibitive storage overhead severely hinders practical deployment. Recent anchor-based 3DGS compression schemes reduce redundancy through context modeling, yet overlook explicit geometric dependencies, leading to structural degradation and suboptimal rate-distortion performance. In this paper, we propose GeoHCC, a geometry-aware 3DGS compression framework that incorporates inter-anchor geometric correlations into anchor pruning and entropy coding for compact representation. We first introduce Neighborhood-Aware Anchor Pruning (NAAP), which evaluates anchor importance via weighted neighborhood feature aggregation and merges redundant anchors into salient neighbors, yielding a compact yet geometry-consistent anchor set. Building upon this optimized structure, we further develop a hierarchical entropy coding scheme, in which coarse-to-fine priors are exploited through a lightweight Geometry-Guided Convolution (GG-Conv) operator to enable spatially adaptive context modeling and rate-distortion optimization. Extensive experiments demonstrate that GeoHCC effectively resolves the structure preservation bottleneck, maintaining superior geometric integrity and rendering fidelity over state-of-the-art anchor-based approaches.

comment: 10

☆ Tele-Catch: Adaptive Teleoperation for Dexterous Dynamic 3D Object Catching

Weiguang Zhao, Junting Dong, Rui Zhang, Kailin Li, Qin Zhao, Kaizhu Huang

Teleoperation is a key paradigm for transferring human dexterity to robots, yet most prior work targets objects that are initially static, such as grasping or manipulation. Dynamic object catch, where objects move before contact, remains underexplored. Pure teleoperation in this task often fails due to timing, pose, and force errors, highlighting the need for shared autonomy that combines human input with autonomous policies. To this end, we present Tele-Catch, a systematic framework for dexterous hand teleoperation in dynamic object catching. At its core, we design DAIM, a dynamics-aware adaptive integration mechanism that realizes shared autonomy by fusing glove-based teleoperation signals into the diffusion policy denoising process. It adaptively modulates control based on the interaction object state. To improve policy robustness, we introduce DP-U3R, which integrates unsupervised geometric representations from point cloud observations into diffusion policy learning, enabling geometry-aware decision making. Extensive experiments demonstrate that Tele-Catch significantly improves accuracy and robustness in dynamic catching tasks, while also exhibiting consistent gains across distinct dexterous hand embodiments and previously unseen object categories.

☆ From Pixels to Reality: Physical-Digital Patch Attacks on Real-World Camera

Victoria Leonenkova, Ekaterina Shumitskaya, Dmitriy Vatolin, Anastasia Antsiferova

This demonstration presents Digital-Physical Adversarial Attacks (DiPA), a new class of practical adversarial attacks against pervasive camera-based authentication systems, where an attacker displays an adversarial patch directly on a smartphone screen instead of relying on printed artifacts. This digital-only physical presentation enables rapid deployment, removes the need for total-variation regularization, and improves patch transferability in black-box conditions. DiPA leverages an ensemble of state-of-the-art face-recognition models (ArcFace, MagFace, CosFace) to enhance transfer across unseen commercial systems. Our interactive demo shows a real-time dodging attack against a deployed face-recognition camera, preventing authorized users from being recognized while participants dynamically adjust patch patterns and observe immediate effects on the sensing pipeline. We further demonstrate DiPA's superiority over existing physical attacks in terms of success rate, feature-space distortion, and reductions in detection confidence, highlighting critical vulnerabilities at the intersection of mobile devices, pervasive vision, and sensor-driven authentication infrastructures.

comment: Accepted to the PerCom 2026 Demo

☆ Unified Restoration-Perception Learning: Maritime Infrared-Visible Image Fusion and Segmentation

Weichao Cai, Weiliang Huang, Biao Xue, Chao Huang, Fei Yuan, Bob Zhang

Marine scene understanding and segmentation plays a vital role in maritime monitoring and navigation safety. However, prevalent factors like fog and strong reflections in maritime environments cause severe image degradation, significantly compromising the stability of semantic perception. Existing restoration and enhancement methods typically target specific degradations or focus solely on visual quality, lacking end-to-end collaborative mechanisms that simultaneously improve structural recovery and semantic effectiveness. Moreover, publicly available infrared-visible datasets are predominantly collected from urban scenes, failing to capture the authentic characteristics of coupled degradations in marine environments. To address these challenges, the Infrared-Visible Maritime Ship Dataset (IVMSD) is proposed to cover various maritime scenarios under diverse weather and illumination conditions. Building upon this dataset, a Multi-task Complementary Learning Framework (MCLF) is proposed to collaboratively perform image restoration, multimodal fusion, and semantic segmentation within a unified architecture. The framework includes a Frequency-Spatial Enhancement Complementary (FSEC) module for degradation suppression and structural enhancement, a Semantic-Visual Consistency Attention (SVCA) module for semantic-consistent guidance, and a cross-modality guided attention mechanism for selective fusion. Experimental results on IVMSD demonstrate that the proposed method achieves state-of-the-art segmentation performance, significantly enhancing robustness and perceptual quality under complex maritime conditions.

☆ EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation

Sravanth Kodavanti, Manjunath Arveti, Sowmya Vajrala, Srinivas Miriyala, Vikram N R

Diffusion Transformers (DiT) have established a new state-of-the-art in high-fidelity image synthesis; however, their massive computational complexity and memory requirements hinder local deployment on resource-constrained edge devices. In this paper, we introduce EdgeDiT, a family of hardware-efficient generative transformers specifically engineered for mobile Neural Processing Units (NPUs), such as the Qualcomm Hexagon and Apple Neural Engine (ANE). By leveraging a hardware-aware optimization framework, we systematically identify and prune structural redundancies within the DiT backbone that are particularly taxing for mobile data-flows. Our approach yields a series of lightweight models that achieve a 20-30% reduction in parameters, a 36-46% decrease in FLOPs, and a 1.65-fold reduction in on-device latency without sacrificing the scaling advantages or the expressive capacity of the original transformer architecture. Extensive benchmarking demonstrates that EdgeDiT offers a superior Pareto-optimal trade-off between Frechet Inception Distance (FID) and inference latency compared to both optimized mobile U-Nets and vanilla DiT variants. By enabling responsive, private, and offline generative AI directly on-device, EdgeDiT provides a scalable blueprint for transitioning large-scale foundation models from high-end GPUs to the palm of the user.

comment: Accepted at the Mobile AI Workshop, CVPR 2026

☆ SVH-BD : Synthetic Vegetation Hyperspectral Benchmark Dataset for Emulation of Remote Sensing Images

Chedly Ben Azizi, Claire Guilloteau, Gilles Roussel, Matthieu Puigt

This dataset provides a large collection of 10,915 synthetic hyperspectral image cubes paired with pixel-level vegetation trait maps, designed to support research in radiative transfer emulation, vegetation trait retrieval, and uncertainty quantification. Each hyperspectral cube contains 211 bands spanning 400--2500 nm at 10 nm resolution and a fixed spatial layout of 64 \times 64 pixels, offering continuous simulated surface reflectance spectra suitable for emulator development and machine-learning tasks requiring high spectral detail. Vegetation traits were derived by inverting Sentinel-2 Level-2A surface reflectance using a PROSAIL-based lookup-table approach, followed by forward PROSAIL simulations to generate hyperspectral reflectance under physically consistent canopy and illumination conditions. The dataset covers four ecologically diverse regions -- East Africa, Northern France, Eastern India, and Southern Spain -- and includes 5th and 95th percentile uncertainty maps as well as Sentinel-2 scene classification layers. This resource enables benchmarking of inversion methods, development of fast radiative transfer emulators, and studies of spectral--biophysical relationships under controlled yet realistic environmental variability.

☆ Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models

Tao Xia, Jiawei Liu, Yukun Zhang, Ting Liu, Wei Wang, Lei Zhang

Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise manipulation in diffusion-based methods to token-level operations, VAR-based approaches achieve better background preservation and significantly faster inference. However, existing VAR-based editing methods still face two key challenges: accurately localizing editable tokens and maintaining structural consistency in the edited results. In this work, we propose a novel text-guided image editing framework rooted in an analysis of intermediate feature distributions within VAR models. First, we introduce a coarse-to-fine token localization strategy that can refine editable regions, balancing editing fidelity and background preservation. Second, we analyze the intermediate representations of VAR models and identify structure-related features, by which we design a simple yet effective feature injection mechanism to enhance structural consistency between the edited and source images. Third, we develop a reinforcement learning-based adaptive feature injection scheme that automatically learns scale- and layer-specific injection ratios to jointly optimize editing fidelity and structure preservation. Extensive experiments demonstrate that our method achieves superior structural consistency and editing quality compared with state-of-the-art approaches, across both local and global editing scenarios.

☆ AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation

Milton Zhou, Sizhong Qin, Yongzhi Li, Quan Chen, Peng Jiang

Short-form videos have become a primary medium for digital advertising, requiring scalable and efficient content creation. However, current workflows and AI tools remain disjoint and modality-specific, leading to high production costs and low overall efficiency. To address this issue, we propose AutoCut, an end-to-end advertisement video editing framework based on multimodal discretization and controllable editing. AutoCut employs dedicated encoders to extract video and audio features, then applies residual vector quantization to discretize them into unified tokens aligned with textual representations, constructing a shared video-audio-text token space. Built upon a foundation model, we further develop a multimodal large language model for video editing through combined multimodal alignment and supervised fine-tuning, supporting tasks covering video selection and ordering, script generation, and background music selection within a unified editing framework. Finally, a complete production pipeline converts the predicted token sequences into deployable long video outputs. Experiments on real-world advertisement datasets show that AutoCut reduces production cost and iteration time while substantially improving consistency and controllability, paving the way for scalable video creation.

comment: Accepted by CVPR 2026

☆ SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering

Jiho Park, Sieun Choi, Jaeyoon Seo, Minho Sohn, Yeana Kim, Jihie Kim

A sketch is a distilled form of visual abstraction that conveys core concepts through simplified yet purposeful strokes while omitting extraneous detail. Despite its expressive power, quantifying the efficiency of semantic abstraction in sketches remains challenging. Existing evaluation methods that rely on reference images, low-level visual features, or recognition accuracy do not capture abstraction, the defining property of sketches. To address these limitations, we introduce SEA (Sketch Evaluation metric for Abstraction efficiency), a reference-free metric that assesses how economically a sketch represents class-defining visual elements while preserving semantic recognizability. These elements are derived per class from commonsense knowledge about features typically depicted in sketches. SEA leverages a visual question answering model to determine the presence of each element and returns a quantitative score that reflects semantic retention under visual economy. To support this metric, we present CommonSketch, the first semantically annotated sketch dataset, comprising 23,100 human-drawn sketches across 300 classes, each paired with a caption and element-level annotations. Experiments show that SEA aligns closely with human judgments and reliably discriminates levels of abstraction efficiency, while CommonSketch serves as a benchmark providing systematic evaluation of element-level sketch understanding across various vision-language models.

☆ Optimized Weighted Voting System for Brain Tumor Classification Using MRI Images

Ha Anh Vu

The accurate classification of brain tumors from MRI scans is essential for effective diagnosis and treatment planning. This paper presents a weighted ensemble learning approach that combines deep learning and traditional machine learning models to improve classification performance. The proposed system integrates multiple classifiers, including ResNet101, DenseNet121, Xception, CNN-MRI, and ResNet50 with edge-enhanced images, SVM, and KNN with HOG features. A weighted voting mechanism assigns higher influence to models with better individual accuracy, ensuring robust decision-making. Image processing techniques such as Balance Contrast Enhancement, K-means clustering, and Canny edge detection are applied to enhance feature extraction. Experimental evaluations on the Figshare and Kaggle MRI datasets demonstrate that the proposed method achieves state-of-the-art accuracy, outperforming existing models. These findings highlight the potential of ensemble-based learning for improving brain tumor classification, offering a reliable and scalable framework for medical image analysis.

☆ VistaGEN: Consistent Driving Video Generation with Fine-Grained Control Using Multiview Visual-Language Reasoning

Li-Heng Chen, Ke Cheng, Yahui Liu, Lei Shi, Shi-Sheng Huang, Hongbo Fu

Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to support fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal consistency, especially in long video generation. In this paper, we present a new driving video generation technique, called VistaGEN, which enables fine-grained control of specific entities, including 3D objects, images, and text descriptions, while maintaining spatiotemporal consistency in long video sequences. Our key innovation is the incorporation of multiview visual-language reasoning into the long driving video generation. To this end, we inject visual-language features into a multiview video generator to enable fine-grained controllability. More importantly, we propose a multiview vision-language evaluator (MV-VLM) to intelligently and automatically evaluate spatiotemporal consistency of the generated content, thus formulating a novel generation-evaluation-regeneration closed-loop generation mechanism. This mechanism ensures high-quality, coherent outputs, facilitating the creation of complex and reliable driving scenarios. Besides, within the closed-loop generation, we introduce an object-level refinement module to refine the unsatisfied results evaluated from the MV-VLM and then feed them back to the video generator for regeneration. Extensive evaluation shows that our VistaGEN achieves diverse driving video generation results with fine-grained controllability, especially for long-tail objects, and much better spatiotemporal consistency than previous approaches.

☆ Integrating Multimodal Large Language Model Knowledge into Amodal Completion

Heecheol Yun, Eunho Yang

With the widespread adoption of autonomous vehicles and robotics, amodal completion, which reconstructs the occluded parts of people and objects in an image, has become increasingly crucial. Just as humans infer hidden regions based on prior experience and common sense, this task inherently requires physical knowledge about real-world entities. However, existing approaches either depend solely on the image generation ability of visual generative models, which lack such knowledge, or leverage it only during the segmentation stage, preventing it from explicitly guiding the completion process. To address this, we propose AmodalCG, a novel framework that harnesses the real-world knowledge of Multimodal Large Language Models (MLLMs) to guide amodal completion. Our framework first assesses the extent of occlusion to selectively invoke MLLM guidance only when the target object is heavily occluded. If guidance is required, the framework further incorporates MLLMs to reason about both the (1) extent and (2) content of the missing regions. Finally, a visual generative model integrates these guidance and iteratively refines imperfect completions that may arise from inaccurate MLLM guidance. Experimental results on various real-world images show impressive improvements compared to all existing works, suggesting MLLMs as a promising direction for addressing challenging amodal completion.

☆ SFDemorpher: Generalizable Face Demorphing for Operational Morphing Attack Detection

Raul Ismayilov, Luuk Spreeuwers

Face morphing attacks compromise biometric security by creating document images that verify against multiple identities, posing significant risks from document issuance to border control. Differential Morphing Attack Detection (D-MAD) offers an effective countermeasure, particularly when employing face demorphing to disentangle identities blended in the morph. However, existing methods lack operational generalizability due to limited training data and the assumption that all document inputs are morphs. This paper presents SFDemorpher, a framework designed for the operational deployment of face demorphing for D-MAD that performs identity disentanglement within joint StyleGAN latent and high-dimensional feature spaces. We introduce a dual-pass training strategy handling both morphed and bona fide documents, leveraging a hybrid corpus with predominantly synthetic identities to enhance robustness against unseen distributions. Extensive evaluation confirms state-of-the-art generalizability across unseen identities, diverse capture conditions, and 13 morphing techniques, spanning both border verification and the challenging document enrollment stage. Our framework achieves superior D-MAD performance by widening the margin between the score distributions of bona fide and morphed samples while providing high-fidelity visual reconstructions facilitating explainability.

☆ Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenes

Luke Palmer, Petar Palasek, Hazem Abdelkawy

Accurately modelling human attention is essential for numerous computer vision applications, particularly in the domain of automotive safety. Existing methods typically collapse gaze into saliency maps or scanpaths, treating gaze dynamics only implicitly. We instead formulate gaze modelling as an autoregressive dynamical system and explicitly unroll raw gaze trajectories over time, conditioned on both gaze history and the evolving environment. Driving scenes are represented as gaze-centric graphs processed by the Affinity Relation Transformer (ART), a heterogeneous graph transformer that models interactions between driver gaze, traffic objects, and road structure. We further introduce the Object Density Network (ODN) to predict next-step gaze distributions, capturing the stochastic and object-centric nature of attentional shifts in complex environments. We also release Focus100, a new dataset of raw gaze data from 30 participants viewing egocentric driving footage. Trained directly on raw gaze, without fixation filtering, our unified approach produces more natural gaze trajectories, scanpath dynamics, and saliency maps than existing attention models, offering valuable insights for the temporal modelling of human attention in dynamic environments.

☆ Prototype-Enhanced Multi-View Learning for Thyroid Nodule Ultrasound Classification

Yangmei Chen, Zhongyuan Zhang, Xikun Zhang, Xinyu Hao, Mingliang Hou, Renqiang Luo, Ziqi Xu

Thyroid nodule classification using ultrasound imaging is essential for early diagnosis and clinical decision-making; however, despite promising performance on in-distribution data, existing deep learning methods often exhibit limited robustness and generalisation when deployed across different ultrasound devices or clinical environments. This limitation is mainly attributed to the pronounced heterogeneity of thyroid ultrasound images, which can lead models to capture spurious correlations rather than reliable diagnostic cues. To address this challenge, we propose PEMV-thyroid, a Prototype-Enhanced Multi-View learning framework that accounts for data heterogeneity by learning complementary representations from multiple feature perspectives and refining decision boundaries through a prototype-based correction mechanism with mixed prototype information. By integrating multi-view representations with prototype-level guidance, the proposed approach enables more stable representation learning under heterogeneous imaging conditions. Extensive experiments on multiple thyroid ultrasound datasets demonstrate that PEMV-thyroid consistently outperforms state-of-the-art methods, particularly in cross-device and cross-domain evaluation scenarios, leading to improved diagnostic accuracy and generalisation performance in real-world clinical settings. The source code is available at https://github.com/chenyangmeii/Prototype-Enhanced-Multi-View-Learning.

comment: 6 pages, IWCMC 2026 accepted

☆ DinoDental: Benchmarking DINOv3 as a Unified Vision Encoder for Dental Image Analysis

Kun Tang, Xinquan Yang, Mianjie Zheng, Xuefen Liu, Xuguang Li, Xiaoqi Guo, Ruihan Chen, Linlin Shen, He Meng

The scarcity and high cost of expert annotations in dental imaging present a significant challenge for the development of AI in dentistry. DINOv3, a state-of-the-art, self-supervised vision foundation model pre-trained on 1.7 billion images, offers a promising pathway to mitigate this issue. However, its reliability when transferred to the dental domain, with its unique imaging characteristics and clinical subtleties, remains unclear. To address this, we introduce DinoDental, a unified benchmark designed to systematically evaluate whether DINOv3 can serve as a reliable, off-the-shelf encoder for comprehensive dental image analysis without requiring domain-specific pre-training. Constructed from multiple public datasets, DinoDental covers a wide range of tasks, including classification, detection, and instance segmentation on both panoramic radiographs and intraoral photographs. We further analyze the model's transfer performance by scaling its size and input resolution, and by comparing different adaptation strategies, including frozen features, full fine-tuning, and the parameter-efficient Low-Rank Adaptation (LoRA) method. Our experiments show that DINOv3 can serve as a strong unified encoder for dental image analysis across both panoramic radiographs and intraoral photographs, remaining competitive across tasks while showing particularly clear advantages for intraoral image understanding and boundary-sensitive dense prediction. Collectively, DinoDental provides a systematic framework for comprehensively evaluating DINOv3 in dental analysis, establishing a foundational benchmark to guide efficient and effective model selection and adaptation for the dental AI community.

☆ TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K

Mattia D'Urso, Yuxi Hu, Christian Sormann, Mattia Rossi, Friedrich Fraundorfer

Despite the growing need for data of more and more sophisticated 3D reconstruction pipelines, we can still observe a scarcity of suitable public datasets. Existing 3D datasets are either low resolution, limited to a small amount of scenes, based on images of varying quality because retrieved from the internet, or limited to specific capturing scenarios. Motivated by this lack of suitable 3D datasets, we captured TerraSky3D, a high-resolution large-scale 3D reconstruction dataset comprising 50,000 images divided into 150 ground, aerial, and mixed scenes. The dataset focuses on European landmarks and comes with curated calibration data, camera poses, and depth maps. TerraSky3D tries to answer the need for challenging dataset that can be used to train and evaluate 3D reconstruction-related pipelines.

comment: Accepted at 3DMV at CVPR Workshop 2026

☆ DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning

Weimin Liu, Qingkun Li, Jiyuan Qiu, Wenjun Wang, Joshua H. Meng

Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-making and control maneuvers, where its absence can compromise traffic safety. To emulate drivers' perception patterns and advance visual attention prediction for intelligent vehicles, we propose DiffAttn, a diffusion-based framework that formulates this task as a conditional diffusion-denoising process, enabling more accurate modeling of drivers' attention. To capture both local and global scene features, we adopt Swin Transformer as encoder and design a decoder that combines a Feature Fusion Pyramid for cross-layer interaction with dense, multi-scale conditional diffusion to jointly enhance denoising learning and model fine-grained local and global scene contexts. Additionally, a large language model (LLM) layer is incorporated to enhance top-down semantic reasoning and improve sensitivity to safety-critical cues. Extensive experiments on four public datasets demonstrate that DiffAttn achieves state-of-the-art (SoTA) performance, surpassing most video-based, top-down-feature-driven, and LLM-enhanced baselines. Our framework further supports interpretable driver-centric scene understanding and has the potential to improve in-cabin human-machine interaction, risk perception, and drivers' state measurement in intelligent vehicles.

☆ TwinMixing: A Shuffle-Aware Feature Interaction Model for Multi-Task Segmentation

Minh-Khoi Do, Huy Che, Dinh-Duy Phan, Duc-Khai Lam, Duc-Lung Vu

Accurate and efficient perception is essential for autonomous driving, where segmentation tasks such as drivable-area and lane segmentation provide critical cues for motion planning and control. However, achieving high segmentation accuracy while maintaining real-time performance on low-cost hardware remains a challenging problem. To address this issue, we introduce TwinMixing, a lightweight multi-task segmentation model designed explicitly for drivable-area and lane segmentation. The proposed network features a shared encoder and task-specific decoders, enabling both feature sharing and task specialization. Within the encoder, we propose an Efficient Pyramid Mixing (EPM) module that enhances multi-scale feature extraction through a combination of grouped convolutions, depthwise dilated convolutions and channel shuffle operations, effectively expanding the receptive field while minimizing computational cost. Each decoder adopts a Dual-Branch Upsampling (DBU) Block composed of a learnable transposed convolution-based Fine detailed branch and a parameter-free bilinear interpolation-based Coarse grained branch, achieving detailed yet spatially consistent feature reconstruction. Extensive experiments on the BDD100K dataset validate the effectiveness of TwinMixing across three configurations - tiny, base, and large. Among them, the base configuration achieves the best trade-off between accuracy and computational efficiency, reaching 92.0% mIoU for drivable-area segmentation and 32.3% IoU for lane segmentation with only 0.43M parameters and 3.95 GFLOPs. Moreover, TwinMixing consistently outperforms existing segmentation models on the same tasks, as illustrated in Fig. 1. Thanks to its compact and modular design, TwinMixing demonstrates strong potential for real-time deployment in autonomous driving and embedded perception systems. The source code: https://github.com/Jun0se7en/TwinMixing.

☆ Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal

Kazuma Ikeda, Ryosei Hara, Rokuto Nagata, Ozora Sako. Zihao Ding, Takahiro Kado, Ibuki Fujioka, Taro Beppu, Mariko Isogawa, Kentaro Yoshioka

LiDAR has become an essential sensing modality in autonomous driving, robotics, and smart-city applications. However, ghost points (or ghosts), which are false reflections caused by multi-path laser returns from glass and reflective surfaces, severely degrade 3D mapping and localization accuracy. Prior ghost removal relies on geometric consistency in dense point clouds, failing on mobile LiDAR's sparse, dynamic data. We address this by exploiting full-waveform LiDAR (FWL), which captures complete temporal intensity profiles rather than just peak distances, providing crucial cues for distinguishing ghosts from genuine reflections in mobile scenarios. As this is a new task, we present Ghost-FWL, the first and largest annotated mobile FWL dataset for ghost detection and removal. Ghost-FWL comprises 24K frames across 10 diverse scenes with 7.5 billion peak-level annotations, which is 100x larger than existing annotated FWL datasets. Benefiting from this large-scale dataset, we establish a FWL-based baseline model for ghost detection and propose FWL-MAE, a masked autoencoder for efficient self-supervised representation learning on FWL data. Experiments show that our baseline outperforms existing methods in ghost removal accuracy, and our ghost removal further enhances downstream tasks such as LiDAR-based SLAM (66% trajectory error reduction) and 3D object detection (50x false positive reduction). The dataset and code is publicly available and can be accessed via the project page: https://keio-csg.github.io/Ghost-FWL

comment: Accepted to CVPR 2026 (Main)

☆ Explaining CLIP Zero-shot Predictions Through Concepts

Onat Ozdemir, Anders Christensen, Stephan Alaniz, Zeynep Akata, Emre Akbas

Large-scale vision-language models such as CLIP have achieved remarkable success in zero-shot image recognition, yet their predictions remain largely opaque to human understanding. In contrast, Concept Bottleneck Models provide interpretable intermediate representations by reasoning through human-defined concepts, but they rely on concept supervision and lack the ability to generalize to unseen classes. We introduce EZPC that bridges these two paradigms by explaining CLIP's zero-shot predictions through human-understandable concepts. Our method projects CLIP's joint image-text embeddings into a concept space learned from language descriptions, enabling faithful and transparent explanations without additional supervision. The model learns this projection via a combination of alignment and reconstruction objectives, ensuring that concept activations preserve CLIP's semantic structure while remaining interpretable. Extensive experiments on five benchmark datasets, CIFAR-100, CUB-200-2011, Places365, ImageNet-100, and ImageNet-1k, demonstrate that our approach maintains CLIP's strong zero-shot classification accuracy while providing meaningful concept-level explanations. By grounding open-vocabulary predictions in explicit semantic concepts, our method offers a principled step toward interpretable and trustworthy vision-language models. Code is available at https://github.com/oonat/ezpc.

comment: Accepted to CVPR 2026

☆ A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps

Xuanlong Yu, Youyang Sha, Longfei Liu, Xi Shen, Di Yang

Few-shot object detection (FSOD) is challenging due to unstable optimization and limited generalization arising from the scarcity of training samples. To address these issues, we propose a hybrid ensemble decoder that enhances generalization during fine-tuning. Inspired by ensemble learning, the decoder comprises a shared hierarchical layer followed by multiple parallel decoder branches, where each branch employs denoising queries either inherited from the shared layer or newly initialized to encourage prediction diversity. This design fully exploits pretrained weights without introducing additional parameters, and the resulting diverse predictions can be effectively ensembled to improve generalization. We further leverage a unified progressive fine-tuning framework with a plateau-aware learning rate schedule, which stabilizes optimization and achieves strong few-shot adaptation without complex data augmentations or extensive hyperparameter tuning. Extensive experiments on CD-FSOD, ODinW-13, and RF100-VL validate the effectiveness of our approach. Notably, on RF100-VL, which includes 100 datasets across diverse domains, our method achieves an average performance of 41.9 in the 10-shot setting, significantly outperforming the recent approach SAM3, which obtains 35.7. We further construct a mixed-domain test set from CD-FSOD to evaluate robustness to out-of-distribution (OOD) samples, showing that our proposed modules lead to clear improvement gains. These results highlight the effectiveness, generalization, and robustness of the proposed method. Code is available at: https://github.com/Intellindust-AI-Lab/FT-FSOD.

comment: Accepted at CVPR 2026

☆ ToLL: Topological Layout Learning with Structural Multi-view Augmentation for 3D Scene Graph Pretraining

Yucheng Huang, Luping Ji, Xiangwei Jiang, Wen Li, Mao Ye

3D Scene Graph (3DSG) generation plays a pivotal role in spatial understanding and semantic-affordance perception. However, its generalizability is often constrained by data scarcity. Current solutions primarily focus on cross-modal assisted representation learning and object-centric generation pre-training. The former relies heavily on predicate annotations, while the latter's predicate learning may be bypassed due to strong object priors. Consequently, they could not often provide a label-free and robust self-supervised proxy task for 3DSG fine-tuning. To bridge this gap, we propose a Topological Layout Learning (ToLL) for 3DSG pretraining framework. In detail, we design an Anchor-Conditioned Topological Geometry Reasoning, with a GNN to recover the global layout of zero-centered subgraphs by the spatial priors from sparse anchors. This process is strictly modulated by predicate features, thereby enforcing the predicate relation learning. Furthermore, we construct a Structural Multi-view Augmentation to avoid semantic corruption, and enhancing representations via self-distillation. The extensive experiments on 3DSSG dataset demonstrate that our ToLL could improve representation quality, outperforming state-of-the-art baselines.

comment: Under Reivew

☆ ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization

Bingchen Li, Zhixin Wang, Fan Li, Jiaqi Xu, Jiaming Guo, Renjing Pei, Xin Li, Zhibo Chen

Old photos preserve invaluable historical memories, making their restoration and colorization highly desirable. While existing restoration models can address some degradation issues like denoising and scratch removal, they often struggle with accurate colorization. This limitation arises from the unique degradation inherent in old photos, such as faded brightness and altered color hues, which are different from modern photo distributions, creating a substantial domain gap during colorization. In this paper, we propose a novel old photo colorization framework based on the generative diffusion model FLUX. Our approach introduces a structure-color decoupling strategy that separates structure preservation from color restoration, enabling accurate colorization of old photos while maintaining structural consistency. We further enhance the model with a progressive Direct Preference Optimization (Pro-DPO) strategy, which allows the model to learn subtle color preferences through coarse-to-fine transitions in color augmentation. Additionally, we address the limitations of text-based prompts by introducing visual semantic prompts, which extract fine-grained semantic information directly from old photos, helping to eliminate the color bias inherent in old photos. Experimental results on both synthetic and real datasets demonstrate that our approach outperforms existing state-of-the-art colorization methods, including closed-source commercial models, producing high-quality and vivid colorization.

comment: Accepted by CVPR26

☆ Event-Based Method for High-Speed 3D Deformation Measurement under Extreme Illumination Conditions

Banglei Guan, Yifei Bian, Zibin Liu, Haoyang Li, Xuanyu Bai, Taihang Lei, Bin Li, Yang Shang, Qifeng Yu

Background: Large engineering structures, such as space launch towers and suspension bridges, are subjected to extreme forces that cause high-speed 3D deformation and compromise safety. These structures typically operate under extreme illumination conditions. Traditional cameras often struggle to handle strong light intensity, leading to overexposure due to their limited dynamic range. Objective: Event cameras have emerged as a compelling alternative to traditional cameras in high dynamic range and low-latency applications. This paper presents an integrated method, from calibration to measurement, using a multi-event camera array for high-speed 3D deformation monitoring of structures in extreme illumination conditions. Methods: Firstly, the proposed method combines the characteristics of the asynchronous event stream and temporal correlation analysis to extract the corresponding marker center point. Subsequently, the method achieves rapid calibration by solving the Kruppa equations in conjunction with a parameter optimization framework. Finally, by employing a unified coordinate transformation and linear intersection, the method enables the measurement of 3D deformation of the target structure. Results: Experiments confirmed that the relative measurement error is below 0.08%. Field experiments under extreme illumination conditions, including self-calibration of a multi-event camera array and 3D deformation measurement, verified the performance of the proposed method. Conclusions: This paper addressed the critical limitation of traditional cameras in measuring high-speed 3D deformations under extreme illumination conditions. The experimental results demonstrate that, compared to other methods, the proposed method can accurately measure 3D deformations of structures under harsh lighting conditions, and the relative error of the measured deformation is less than 0.1%.

comment: Exp Mech (2026)

☆ ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGS Models

Yuhuan Xie, Aoxuan Pan, Yi-Hua Huang, Chirui Chang, Peng Dai, Xin Yu, Xiaojuan Qi

Achieving precise, object-level control in image editing remains challenging: 2D methods lack 3D awareness and often yield ambiguous or implausible results, while existing 3D-aware approaches rely on heavy optimization or incomplete monocular reconstructions. We present ObjectMorpher, a unified, interactive framework that converts ambiguous 2D edits into geometry-grounded operations. ObjectMorpher lifts target instances with an image-to-3D generator into editable 3D Gaussian Splatting (3DGS), enabling fast, identity-preserving manipulation. Users drag control points; a graph-based non-rigid deformation with as-rigid-as-possible (ARAP) constraints ensures physically sensible shape and pose changes. A composite diffusion module harmonizes lighting, color, and boundaries for seamless reintegration. Across diverse categories, ObjectMorpher delivers fine-grained, photorealistic edits with superior controllability and efficiency, outperforming 2D drag and 3D-aware baselines on KID, LPIPS, SIFID, and user preference.

comment: 11 pages, 8 figures

☆ BlankSkip: Early-exit Object Detection onboard Nano-drones

Carlo Marra, Beatrice Alessandra Motetti, Alessio Burrello, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

Deploying tiny computer vision Deep Neural Networks (DNNs) on-board nano-sized drones is key for achieving autonomy, but is complicated by the extremely tight constraints of their computational platforms (approximately 10 MiB memory, 1 W power budget). Early-exit adaptive DNNs that dial down the computational effort for "easy-to-process" input frames represent a promising way to reduce the average inference latency. However, while this approach is extensively studied for classification, its application to dense tasks like object detection (OD) is not straightforward. In this paper, we propose BlankSkip, an adaptive network for on-device OD that leverages a simple auxiliary classification task for early exit, i.e., identifying frames with no objects of interest. With experiments using a real-world nano-drone platform, the Bitcraze Crazyflie 2.1, we achieve up to 24% average throughput improvement with a limited 0.015 mean Average Precision (mAP) drop compared to a static MobileNet-SSD detector, on a state-of-the-art nano-drones OD dataset.

comment: Accepted for publication in the Embedded Vision Workshop of the 2026 Computer Vision and Pattern Recognition (CVPR) conference

☆ RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation

Chanseul Cho, Seokju Yun, Jeaseong Jeon, Seungjae Moon, Youngmin Ro

Domain Generalized Semantic Segmentation (DGSS) aims to maintain robust performance across unseen target domains. Vision Foundation Models (VFMs) offer rich multi-domain knowledge that can enhance generalization. However, strategies for actively exploiting the rich subspace structures within VFMs remain under-explored, with many existing methods focusing primarily on preserving pre-trained knowledge. Furthermore, their LoRA components often suffer from limited representational diversity and inefficient parameter utilization. We propose RecycleLoRA, which addresses both challenges by employing Rank-Revealing QR Decomposition (RRQR) to systematically exploit VFM's subspace structures and enhance LoRA's representational richness. Our main adapter leverages minor subspace directions identified by RRQR to learn diverse and independent features, achieving competitive performance even when used alone. We further introduce a sub adapter that carefully refines major directions with minimal adjustments, providing complementary improvements to the main adapter's strong baseline performance. This design enables the dual adapters to learn distinct representations without requiring additional regularization losses. Our systematic exploitation of pre-trained subspace structures through RRQR-based initialization leads to superior domain generalization performance. RecycleLoRA achieves state-of-the-art performance on both synthetic-to-real generalization and real-to-real generalization tasks without complex architectures or additional inference latency.

comment: Accepted to CVPR 2026 (Findings)

☆ Intelligent Road Condition Monitoring using 3D In-Air SONAR Sensing

Amber Cassimon, Robin Kerstens, Walter Daems, Jan Steckel

In this paper, we investigate the capabilities of in-air 3D SONAR sensors for the monitoring of road surface conditions. Concretely, we consider two applications: Road material classification and Road damage detection and classification. While such tasks can be performed with other sensor modalities, such as camera sensors and LiDAR sensors, these sensor modalities tend to fail in harsh sensing conditions, such as heavy rain, smoke or fog. By using a sensing modality that is robust to such interference, we enable the creation of opportunistic sensing applications, where vehicles performing other tasks (garbage collection, mail delivery, etc.) can also be used to monitor the condition of the road. For these tasks, we use a single dataset, in which different types of damages are annotated, with labels including the material of the road surface. In the material classification task, we differentiate between three different road materials: Asphalt, Concrete and Element roads. In the damage detection and classification task, we determine if there is damage, and what type of damage (independent of material type), without localizing the damage. We are succesful in determining the road surface type from SONAR sensor data, with F1 scores approaching 90% on the test set, but find that for the detection of damages performace lags, with F1 score around 75%. From this, we conclude that SONAR sensing is a promising modality to include in opportunistic sensing-based pavement management systems, but that further research is needed to reach the desired accuracy.

comment: 10 pages, 9 figures, 2 tables

☆ Robust Remote Sensing Image-Text Retrieval with Noisy Correspondence

Qiya Song, Yiqiang Xie, Yuan Sun, Renwei Dian, Xudong Kang

As a pivotal task that bridges remote visual and linguistic understanding, Remote Sensing Image-Text Retrieval (RSITR) has attracted considerable research interest in recent years. However, almost all RSITR methods implicitly assume that image-text pairs are matched perfectly. In practice, acquiring a large set of well-aligned data pairs is often prohibitively expensive or even infeasible. In addition, we also notice that the remote sensing datasets (e.g., RSITMD) truly contain some inaccurate or mismatched image text descriptions. Based on the above observations, we reveal an important but untouched problem in RSITR, i.e., Noisy Correspondence (NC). To overcome these challenges, we propose a novel Robust Remote Sensing Image-Text Retrieval (RRSITR) paradigm that designs a self-paced learning strategy to mimic human cognitive learning patterns, thereby learning from easy to hard from multi-modal data with NC. Specifically, we first divide all training sample pairs into three categories based on the loss magnitude of each pair, i.e., clean sample pairs, ambiguous sample pairs, and noisy sample pairs. Then, we respectively estimate the reliability of each training pair by assigning a weight to each pair based on the values of the loss. Further, we respectively design a new multi-modal self-paced function to dynamically regulate the training sequence and weights of the samples, thus establishing a progressive learning process. Finally, for noisy sample pairs, we present a robust triplet loss to dynamically adjust the soft margin based on semantic similarity, thereby enhancing the robustness against noise. Extensive experiments on three popular benchmark datasets demonstrate that the proposed RRSITR significantly outperforms the state-of-the-art methods, especially in high noise rates. The code is available at: https://github.com/MSFLabX/RRSITR

☆ MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

Zhang Li, Zhibo Lin, Qiang Liu, Ziyang Zhang, Shuo Zhang, Zidun Guo, Jiajun Song, Jiarui Zhang, Xiang Bai, Yuliang Liu

We introduce Multilingual Document Parsing Benchmark, the first benchmark for multilingual digital and photographed document parsing. Document parsing has made remarkable strides, yet almost exclusively on clean, digital, well-formatted pages in a handful of dominant languages. No systematic benchmark exists to evaluate how models perform on digital and photographed documents across diverse scripts and low-resource languages. MDPBench comprises 3,400 document images spanning 17 languages, diverse scripts, and varied photographic conditions, with high-quality annotations produced through a rigorous pipeline of expert model labeling, manual correction, and human verification. To ensure fair comparison and prevent data leakage, we maintain separate public and private evaluation splits. Our comprehensive evaluation of both open-source and closed-source models uncovers a striking finding: while closed-source models (notably Gemini3-Pro) prove relatively robust, open-source alternatives suffer dramatic performance collapse, particularly on non-Latin scripts and real-world photographed documents, with an average drop of 17.8% on photographed documents and 14.0% on non-Latin scripts. These results reveal significant performance imbalances across languages and conditions, and point to concrete directions for building more inclusive, deployment-ready parsing systems. Source available at https://github.com/Yuliang-Liu/MultimodalOCR.

☆ SVGS: Single-View to 3D Object Editing via Gaussian Splatting

Pengcheng Xue, Yan Tian, Qiutao Song, Ziyi Wang, Linyang He, Weiping Ding, Mahmoud Hassaballah, Karen Egiazarian, Wei-Fa Yang, Leszek Rutkowski

Text-driven 3D scene editing has attracted considerable interest due to its convenience and user-friendliness. However, methods that rely on implicit 3D representations, such as Neural Radiance Fields (NeRF), while effective in rendering complex scenes, are hindered by slow processing speeds and limited control over specific regions of the scene. Moreover, existing approaches, including Instruct-NeRF2NeRF and GaussianEditor, which utilize multi-view editing strategies, frequently produce inconsistent results across different views when executing text instructions. This inconsistency can adversely affect the overall performance of the model, complicating the task of balancing the consistency of editing results with editing efficiency. To address these challenges, we propose a novel method termed Single-View to 3D Object Editing via Gaussian Splatting (SVGS), which is a single-view text-driven editing technique based on 3D Gaussian Splatting (3DGS). Specifically, in response to text instructions, we introduce a single-view editing strategy grounded in multi-view diffusion models, which reconstructs 3D scenes by leveraging only those views that yield consistent editing results. Additionally, we employ sparse 3D Gaussian Splatting as the 3D representation, which significantly enhances editing efficiency. We conducted a comparative analysis of SVGS against existing baseline methods across various scene settings, and the results indicate that SVGS outperforms its counterparts in both editing capability and processing speed, representing a significant advancement in 3D editing technology. For further details, please visit our project page at: https://amateurc.github.io/svgs.github.io.

☆ MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding

Guangjing Yang, Ziyuan Qin, Chaoran Zhang, Chenlin Du, Jinlin Wang, Wanran Sun, Zhenyu Zhang, Bing Ji, Qicheng Lao

Medical visual grounding serves as a crucial foundation for fine-grained multimodal reasoning and interpretable clinical decision support. Despite recent advances in reinforcement learning (RL) for grounding tasks, existing approaches such as Group Relative Policy Optimization~(GRPO) suffer from severe reward sparsity when directly applied to medical images, primarily due to the inherent difficulty of localizing small or ambiguous regions of interest, which is further exacerbated by the rigid and suboptimal nature of fixed IoU-based reward schemes in RL. This leads to vanishing policy gradients and stagnated optimization, particularly during early training. To address this challenge, we propose MedLoc-R1, a performance-aware reward scheduling framework that progressively tightens the reward criterion in accordance with model readiness. MedLoc-R1 introduces a sliding-window performance tracker and a multi-condition update rule that automatically adjust the reward schedule from dense, easily obtainable signals to stricter, fine-grained localization requirements, while preserving the favorable properties of GRPO without introducing auxiliary networks or additional gradient paths. Experiments on three medical visual grounding benchmarks demonstrate that MedLoc-R1 consistently improves both localization accuracy and training stability over GRPO-based baselines. Our framework offers a general, lightweight, and effective solution for RL-based grounding in high-stakes medical applications. Code \& checkpoints are available at \hyperlink{}{https://github.com/MembrAI/MedLoc-R1}.

comment: 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

☆ $AutoDrive\text{-}P^3$: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning ICLR 2026

Yuqi Ye, Zijian Zhang, Junhong Lin, Shangkun Sun, Changhao Peng, Wei Gao

Vision-language models (VLMs) are increasingly being adopted for end-to-end autonomous driving systems due to their exceptional performance in handling long-tail scenarios. However, current VLM-based approaches suffer from two major limitations: 1) Some VLMs directly output planning results without chain-of-thought (CoT) reasoning, bypassing crucial perception and prediction stages which creates a significant domain gap and compromises decision-making capability; 2) Other VLMs can generate outputs for perception, prediction, and planning tasks but employ a fragmented decision-making approach where these modules operate separately, leading to a significant lack of synergy that undermines true planning performance. To address these limitations, we propose ${AutoDrive\text{-}P^3}$, a novel framework that seamlessly integrates $\textbf{P}$erception, $\textbf{P}$rediction, and $\textbf{P}$lanning through structured reasoning. We introduce the ${P^3\text{-}CoT}$ dataset to facilitate coherent reasoning and propose ${P^3\text{-}GRPO}$, a hierarchical reinforcement learning algorithm that provides progressive supervision across all three tasks. Specifically, ${AutoDrive\text{-}P^3}$ progressively generates CoT reasoning and answers for perception, prediction, and planning, where perception provides essential information for subsequent prediction and planning, while both perception and prediction collectively contribute to the final planning decisions, enabling safer and more interpretable autonomous driving. Additionally, to balance inference efficiency with performance, we introduce dual thinking modes: detailed thinking and fast thinking. Extensive experiments on both open-loop (nuScenes) and closed-loop (NAVSIMv1/v2) benchmarks demonstrate that our approach achieves state-of-the-art performance in planning tasks. Code is available at https://github.com/haha-yuki-haha/AutoDrive-P3.

comment: Accepted at ICLR 2026 (International Conference on Learning Representations)

☆ Attention Frequency Modulation: Training-Free Spectral Modulation of Diffusion Cross-Attention

Seunghun Oh, Unsang Park

Cross-attention is the primary interface through which text conditions latent diffusion models, yet its step-wise multi-resolution dynamics remain under-characterized, limiting principled training-free control. We cast diffusion cross-attention as a spatiotemporal signal on the latent grid by summarizing token-softmax weights into token-agnostic concentration maps and tracking their radially binned Fourier power over denoising. Across prompts and seeds, encoder cross-attention exhibits a consistent coarse-to-fine spectral progression, yielding a stable time-frequency fingerprint of token competition. Building on this structure, we introduce Attention Frequency Modulation (AFM), a plug-and-play inference-time intervention that edits token-wise pre-softmax cross-attention logits in the Fourier domain: low- and high-frequency bands are reweighted with a progress-aligned schedule and can be adaptively gated by token-allocation entropy, before the token softmax. AFM provides a continuous handle to bias the spatial scale of token-competition patterns without retraining, prompt editing, or parameter updates. Experiments on Stable Diffusion show that AFM reliably redistributes attention spectra and produces substantial visual edits while largely preserving semantic alignment. Finally, we find that entropy mainly acts as an adaptive gain on the same frequency-based edit rather than an independent control axis.

comment: 16 pages; preprint

☆ Contour-Guided Query-Based Feature Fusion for Boundary-Aware and Generalizable Cardiac Ultrasound Segmentation

Zahid Ullah, Sieun Choi, Jihie Kim

Accurate cardiac ultrasound segmentation is essential for reliable assessment of ventricular function in intelligent healthcare systems. However, echocardiographic images are challenging due to low contrast, speckle noise, irregular boundaries, and domain shifts across devices and patient populations. Existing methods, largely based on appearance-driven learning, often fail to preserve boundary precision and structural consistency under these conditions. To address these issues, we propose a Contour-Guided Query Refinement Network (CGQR-Net) for boundary-aware cardiac ultrasound segmentation. The framework integrates multi-resolution feature representations with contour-derived structural priors. An HRNet backbone preserves high-resolution spatial details while capturing multi-scale context. A coarse segmentation is first generated, from which anatomical contours are extracted and encoded into learnable query embeddings. These contour-guided queries interact with fused feature maps via cross-attention, enabling structure-aware refinement that improves boundary delineation and reduces noise artifacts. A dual-head supervision strategy jointly optimizes segmentation and boundary prediction to enforce structural consistency. The proposed method is evaluated on the CAMUS dataset and further validated on the CardiacNet dataset to assess cross-dataset generalization. Experimental results demonstrate improved segmentation accuracy, enhanced boundary precision, and robust performance across varying imaging conditions. These results highlight the effectiveness of integrating contour-level structural information with feature-level representations for reliable cardiac ultrasound segmentation.

☆ RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression

Chunhang Zheng, Tongda Xu, Mingli Xie, Yan Wang, Dou Li

Raw images preserve linear sensor measurements and high bit-depth information crucial for advanced vision tasks and photography applications, yet their storage remains challenging due to large file sizes, varying bit depths, and sensor-dependent characteristics. Existing learned lossless compression methods mainly target 8-bit sRGB images, while raw reconstruction approaches are inherently lossy and rely on camera-specific assumptions. To address these challenges, we introduce RAWIC, a bit-depth-adaptive learned lossless compression framework for Bayer-pattern raw images. We first convert single-channel Bayer data into a four-channel RGGB format and partition it into patches. For each patch, we compute its bit depth and use it as auxiliary input to guide compression. A bit-depth-adaptive entropy model is then designed to estimate patch distributions conditioned on their bit depths. This architecture enables a single model to handle raw images from diverse cameras and bit depths. Experiments show that RAWIC consistently surpasses traditional lossless codecs, achieving an average 7.7% bitrate reduction over JPEG-XL. Our code is available at https://github.com/chunbaobao/RAWIC.

comment: Accepted by ICME 2026

☆ Octree-based Learned Point Cloud Geometry Compression: A Lossy Perspective

Kaiyu Zheng, Wei Gao, Huiming Zheng

Octree-based context learning has recently become a leading method in point cloud compression. However, its potential on lossy compression remains undiscovered. The traditional lossy compression paradigm using lossless octree representation with quantization step adjustment may result in severe distortions due to massive missing points in quantization. Therefore, we analyze data characteristics of different point clouds and propose lossy approaches specifically. For object point clouds that suffer from quantization step adjustment, we propose a new leaf nodes lossy compression method, which achieves lossy compression by performing bit-wise coding and binary prediction on leaf nodes. For LiDAR point clouds, we explore variable rate approaches and propose a simple but effective rate control method. Experimental results demonstrate that the proposed leaf nodes lossy compression method significantly outperforms the previous octree-based method on object point clouds, and the proposed rate control method achieves about 1% bit error without finetuning on LiDAR point clouds.

☆ SHARP: Short-Window Streaming for Accurate and Robust Prediction in Motion Forecasting

Alexander Prutsch, Christian Fruhwirth-Reisinger, David Schinagl, Horst Possegger

In dynamic traffic environments, motion forecasting models must be able to accurately estimate future trajectories continuously. Streaming-based methods are a promising solution, but despite recent advances, their performance often degrades when exposed to heterogeneous observation lengths. To address this, we propose a novel streaming-based motion forecasting framework that explicitly focuses on evolving scenes. Our method incrementally processes incoming observation windows and leverages an instance-aware context streaming to maintain and update latent agent representations across inference steps. A dual training objective further enables consistent forecasting accuracy across diverse observation horizons. Extensive experiments on Argoverse 2, nuScenes, and Argoverse 1 demonstrate the robustness of our approach under evolving scene conditions and also on the single-agent benchmarks. Our model achieves state-of-the-art performance in streaming inference on the Argoverse 2 multi-agent benchmark, while maintaining minimal latency, highlighting its suitability for real-world deployment.

comment: CVPR 2026. Project page at https://a-pru.github.io/sharp

☆ To View Transform or Not to View Transform: NeRF-based Pre-training Perspective ICLR'26

Hyeonjun Jeong, Juyeb Shin, Dongsuk Kum

Neural radiance fields (NeRFs) have emerged as a prominent pre-training paradigm for vision-centric autonomous driving, which enhances 3D geometry and appearance understanding in a fully self-supervised manner. To apply NeRF-based pretraining to 3D perception models, recent approaches have simply applied NeRFs to volumetric features obtained from view transformation. However, coupling NeRFs with view transformation inherits conflicting priors; view transformation imposes discrete and rigid representations, whereas radiance fields assume continuous and adaptive functions. When these opposing assumptions are forced into a single pipeline, the misalignment surfaces as blurry and ambiguous 3D representations that ultimately limit 3D scene understanding. Moreover, the NeRF network for pre-training is discarded during downstream tasks, resulting in inefficient utilization of enhanced 3D representations through NeRF. In this paper, we propose a novel NeRF-Resembled Point-based 3D detector that can learn continuous 3D representation and thus avoid the misaligned priors from view transformation. NeRP3D preserves the pre-trained NeRF network regardless of the tasks, inheriting the principle of continuous 3D representation learning and leading to greater potentials for both scene reconstruction and detection tasks. Experiments on nuScenes dataset demonstrate that our proposed approach significantly improves previous state-of-the-art methods, outperforming not only pretext scene reconstruction tasks but also downstream detection tasks.

comment: The Fourteenth International Conference on Learning Representations (ICLR'26)

☆ GEMS: Agent-Native Multimodal Generation with Memory and Skills

Zefeng He, Siyuan Huang, Xiaoye Qu, Yafu Li, Tong Zhu, Yu Cheng, Yang Yang

Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downstream tasks. Inspired by the success of advanced agent frameworks such as Claude Code, we propose \textbf{GEMS} (Agent-Native Multimodal \textbf{GE}neration with \textbf{M}emory and \textbf{S}kills), a framework that pushes beyond the inherent limitations of foundational models on both general and downstream tasks. GEMS is built upon three core components. Agent Loop introduces a structured multi-agent framework that iteratively improves generation quality through closed-loop optimization. Agent Memory provides a persistent, trajectory-level memory that hierarchically stores both factual states and compressed experiential summaries, enabling a global view of the optimization process while reducing redundancy. Agent Skill offers an extensible collection of domain-specific expertise with on-demand loading, allowing the system to effectively handle diverse downstream applications. Across five mainstream tasks and four downstream tasks, evaluated on multiple generative backends, GEMS consistently achieves significant performance gains. Most notably, it enables the lightweight 6B model Z-Image-Turbo to surpass the state-of-the-art Nano Banana 2 on GenEval2, demonstrating the effectiveness of agent harness in extending model capabilities beyond their original limits.

comment: Project Page: https://gems-gen.github.io

♻ ☆ ViPRA: Video Prediction for Robot Actions ICLR 2026

Sandeep Routray, Hengkai Pan, Unnat Jain, Shikhar Bahl, Deepak Pathak

Can we turn a video prediction model into a robot policy? Videos, including those of humans or teleoperated robots, capture rich physical interactions. However, most of them lack labeled actions, which limits their use in robot learning. We present Video Prediction for Robot Actions (ViPRA), a simple pretraining-finetuning framework that learns continuous robot control from these actionless videos. Instead of directly predicting actions, we train a video-language model to predict both future visual observations and motion-centric latent actions, which serve as intermediate representations of scene dynamics. We train these latent actions using perceptual losses and optical flow consistency to ensure they reflect physically grounded behavior. For downstream control, we introduce a chunked flow matching decoder that maps latent actions to robot-specific continuous action sequences, using only 100 to 200 teleoperated demonstrations. This approach avoids expensive action annotation, supports generalization across embodiments, and enables smooth, high-frequency continuous control upto 22 Hz via chunked action decoding. Unlike prior latent action works that treat pretraining as autoregressive policy learning, ViPRA explicitly models both what changes and how. Our method outperforms strong baselines, with a 16% gain on the SIMPLER benchmark and a 13% improvement across real world manipulation tasks. We have released models and code at https://vipra-project.github.io

comment: In ICLR 2026. Website: https://vipra-project.github.io

♻ ☆ APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping

Jiwon Kang, Yeji Choi, JoungBin Lee, Wooseok Jang, Jinhyeok Choi, Taekeun Kang, Yongjae Park, Myungin Kim, Seungryong Kim

Face swapping aims to transfer the identity of a source face onto a target face while preserving target-specific attributes such as pose, expression, lighting, skin tone, and makeup. However, since real ground truth for face swapping is unavailable, achieving both accurate identity transfer and high-quality attribute preservation remains challenging. Recent diffusion-based approaches attempt to improve visual fidelity through conditional inpainting on masked target images, but the masked condition removes crucial appearance cues, resulting in plausible yet misaligned attributes. To address this limitation, we propose APPLE (Attribute-Preserving Pseudo-Labeling), a fully diffusion-based teacher-student framework for attribute-preserving face swapping. Our approach introduces a teacher design to produce pseudo-labels aligned with the target attributes through (1) a conditional deblurring formulation that improves the preservation of global attributes such as skin tone and illumination, and (2) an attribute-aware inversion scheme that further enhances fine-grained attribute preservation such as makeup. APPLE conditions the student on clean pseudo-labels rather than degraded masked inputs, enabling more faithful attribute preservation. As a result, APPLE achieves state-of-the-art performance in attribute preservation while maintaining competitive identity transferability.

comment: Accepted at CVPR 2026. Project Page: https://cvlab-kaist.github.io/APPLE/

♻ ☆ Equivariant symmetry-aware head pose estimation for fetal MRI

Ramya Muthukrishnan, Borjan Gagoski, Aryn Lee, P. Ellen Grant, Elfar Adalsteinsson, Benjamin Billot, Polina Golland

We present E(3)-Pose, a novel fast pose estimation method that jointly and explicitly models rotation equivariance and object symmetry. Our work is motivated by the challenging problem of accounting for fetal head motion during a diagnostic MRI scan. We aim to enable automatic adaptive prescription of diagnostic 2D MRI slices with 6-DoF head pose estimation, supported by rapid low-resolution 3D MRI volumes acquired before each 2D slice. Existing pose estimation methods struggle to generalize to clinical volumes due to pose ambiguities induced by inherent anatomical symmetries, as well as low resolution, noise, and artifacts. In contrast, E(3)-Pose captures anatomical symmetries and rigid pose equivariance by construction, and yields robust estimates of the fetal head pose. Our experiments on publicly available and representative clinical fetal MRI datasets demonstrate the superior robustness and generalization of our method across domains. Crucially, E(3)-Pose achieves state-of-the-art accuracy on clinical MRI volumes, supporting future clinical translation. Our implementation is publicly available at github.com/MedicalVisionGroup/E3-Pose.

♻ ☆ Image-Adaptive GAN based Reconstruction AAAI 2020

Shady Abu Hussein, Tom Tirer, Raja Giryes

In the recent years, there has been a significant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of these methods still do not capture the full distribution for complex classes of images, such as human faces. This deficiency has been clearly observed in previous works that use pre-trained generative models to solve imaging inverse problems. In this paper, we suggest to mitigate the limited representation capabilities of generators by making them image-adaptive and enforcing compliance of the restoration with the observations via back-projections. We empirically demonstrate the advantages of our proposed approach for image super-resolution and compressed sensing.

comment: Published to AAAI 2020. Code available at https://github.com/shadyabh/IAGAN

♻ ☆ A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations

Neelu Madan, Àlex Pujol, Andreas Møgelmose, Sergio Escalera, Kamal Nasrollahi, Graham W. Taylor, Thomas B. Moeslund

Slot attention has emerged as a powerful framework for unsupervised object-centric learning, decomposing visual scenes into a small set of compact vector representations called \emph{slots}, each capturing a distinct region or object. However, these slots are learned in Euclidean space, which provides no geometric inductive bias for the hierarchical relationships that naturally structure visual scenes. In this work, we propose a simple post-hoc pipeline to project Euclidean slot embeddings onto the Lorentz hyperboloid of hyperbolic space, without modifying the underlying training pipeline. We construct five-level visual hierarchies directly from slot attention masks and analyse whether hyperbolic geometry reveals latent hierarchical structure that remains invisible in Euclidean space. Integrating our pipeline with SPOT (images), VideoSAUR (video), and SlotContrast (video), We find that hyperbolic projection exposes a consistent scene-level to object-level organisation, where coarse slots occupy greater manifold depth than fine slots, which is absent in Euclidean space. We further identify a "curvature--task tradeoff": low curvature ($c{=}0.2$) matches or outperforms Euclidean on parent slot retrieval, while moderate curvature ($c{=}0.5$) achieves better inter-level separation. Together, these findings suggest that slot representations already encode latent hierarchy that hyperbolic geometry reveals, motivating end-to-end hyperbolic training as a natural next step. Code and models are available at \href{https://github.com/NeeluMadan/HHS}{github.com/NeeluMadan/HHS}.

comment: accepted at CVPR Workshops 2026

♻ ☆ Vision-Language Agents for Interactive Forest Change Analysis

James Brock, Ce Zhang, Nantheera Anantrasirichai

Modern forest monitoring workflows increasingly benefit from the growing availability of high-resolution satellite imagery and advances in deep learning. Two persistent challenges in this context are accurate pixel-level change detection and meaningful semantic change captioning for complex forest dynamics. While large language models (LLMs) are being adapted for interactive data exploration, their integration with vision-language models (VLMs) for remote sensing image change interpretation (RSICI) remains underexplored. To address this gap, we introduce an LLM-driven agent for integrated forest change analysis that supports natural language querying across multiple RSICI tasks. The proposed system builds upon a multi-level change interpretation (MCI) vision-language backbone with LLM-based orchestration. To facilitate adaptation and evaluation in forest environments, we further introduce the Forest-Change dataset, which comprises bi-temporal satellite imagery, pixel-level change masks, and multi-granularity semantic change captions generated using a combination of human annotation and rule-based methods. Experimental results show that the proposed system achieves mIoU and BLEU-4 scores of 67.10% and 40.17% on the Forest-Change dataset, and 88.13% and 34.41% on LEVIR-MCI-Trees, a tree-focused subset of LEVIR-MCI benchmark for joint change detection and captioning. These results highlight the potential of interactive, LLM-driven RSICI systems to improve accessibility, interpretability, and efficiency of forest change analysis. All data and code are publicly available at https://github.com/JamesBrockUoB/ForestChat.

comment: 5 pages, 4 figures, Accepted into IGARSS 2026

♻ ☆ NARVis: Neural Accelerated Rendering for Real-Time Scientific Point Cloud Visualization

Srinidhi Hegde, Kaur Kullman, Thomas Grubb, Leslie Lait, Stephen Guimond, Matthias Zwicker

Exploring scientific datasets with billions of samples in real-time visualization presents a challenge - balancing high-fidelity rendering with speed. This work introduces a neural accelerated renderer, NARVis, that uses the neural deferred rendering framework to visualize large-scale scientific point cloud data. NARVis augments a real-time point cloud rendering pipeline with high-quality neural post-processing, making the approach ideal for interactive visualization at scale. Specifically, we render the multi-attribute point cloud using a high-performance multi-attribute rasterizer and train a neural renderer to capture the desired post-processing effects from a conventional high-quality renderer. NARVis is effective in visualizing complex multidimensional Lagrangian flow fields and photometric scans of a large terrain as compared to the state-of-the-art high-quality renderers. Extensive evaluations demonstrate that NARVis prioritizes speed and scalability while retaining high visual fidelity. We achieve competitive frame rates of $>$126 fps for interactive rendering of $>$350M points (i.e., an effective throughput of $>$44 billion points per second) using ~12 GB of memory on RTX 2080 Ti GPU. Furthermore, NARVis is generalizable across different point clouds with similar visualization needs and the desired post-processing effects could be obtained with substantial high quality even at lower resolutions of the original point cloud, further reducing the memory requirements.

♻ ☆ CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling

Sayan Deb Sarkar, Rémi Pautrat, Ondrej Miksik, Marc Pollefeys, Iro Armeni, Mahdi Rad, Mihai Dusmanu

Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe sampling which often misses both macro-level events and micro-level details due to the sparse temporal coverage. Furthermore, processing full images and their tokens for each frame incurs substantial computational overhead. We address these limitations by leveraging video codec primitives (specifically motion vectors and residuals) which natively encode video redundancy and sparsity without requiring expensive full-image encoding for most frames. To this end, we introduce lightweight transformer-based encoders that aggregate codec primitives and align their representations with image encoder embeddings through a pre-training strategy that accelerates convergence during end-to-end fine-tuning. Our approach, CoPE-VideoLM, reduces the time-to-first-token by up to 86% and token usage by up to 93% compared to standard VideoLMs. Moreover, by varying the keyframe and codec primitive densities we maintain or exceed performance on 14 diverse video understanding benchmarks spanning general question answering, temporal and motion reasoning, long-form understanding, and spatial scene understanding.

comment: Project Page: https://microsoft.github.io/CoPE

♻ ☆ What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely $F_1$

Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck

Ranking methods or models based on their performance is of prime importance but is tricky because performance is fundamentally multidimensional. In the case of classification, precision and recall are scores with probabilistic interpretations that are both important to consider and complementary. The rankings induced by these two scores are often in partial contradiction. In practice, therefore, it is extremely useful to establish a compromise between the two views to obtain a single, global ranking. Over the last fifty years or so, it has been proposed to take a weighted harmonic mean, known as the F-score, F-measure, or $F_β$. Generally speaking, by averaging basic scores, we obtain a score that is intermediate in terms of values. However, there is no guarantee that these scores lead to meaningful rankings and no guarantee that the rankings are good tradeoffs between these base scores. Given the ubiquity of $F_β$ scores in the literature, some clarification is in order. Concretely: (1) We establish that $F_β$-induced rankings are meaningful and define a shortest path between precision- and recall-induced rankings. (2) We frame the problem of finding a tradeoff between two scores as an optimization problem expressed with Kendall rank correlations. We show that $F_1$ and its skew-insensitive version are far from being optimal in that regard. (3) We provide theoretical tools and a closed-form expression to find the optimal value for $β$ for any distribution or set of performances, and we illustrate their use on six case studies. Code is available at https://github.com/pierard/cvpr-2026-optimal-tradeoff-precision-recall.

comment: CVPR 2026

♻ ☆ Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation

Rui Yu, Runkai Zhao, Jiagen Li, Qingsong Zhao, HuaiCheng Yan, Meng Wang

The LiDAR 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many existing LiDAR detection models depend on complex feature transformations, leading to poor real-time performance and high resource consumption, which limits their practical effectiveness. In this work, we propose a faster LiDAR 3D object detector, a framework that adaptively aligns sparse voxels to enable efficient heterogeneous knowledge distillation, called FASD. We aim to distill the Transformer sequence modeling capability into Mamba models, significantly boosting accuracy through knowledge transfer. Specifically, we first design the architecture for cross-model knowledge distillation to impart the global contextual understanding capabilities of the Transformer to Mamba. Transformer-based teacher model employ a scale-adaptive attention mechanism to enhance multiscale fusion. In contrast, Mamba-based student model leverages feature alignment through spatial-based adapters, supervised with latent space feature and span-head distillation losses, leading to improved performance and efficiency. We evaluated the FASD on the Waymo and nuScenes datasets, achieving a 4x reduction in resource consumption and a 1-2% performance improvement over the baseline, while also delivering significant gains in accuracy and efficiency in real deployment.

♻ ☆ Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification

Nghia Nguyen, Tianjiao Ding, René Vidal

Interpretable-by-design models are gaining traction in computer vision because they provide faithful explanations for their predictions. In image classification, these models typically recover human-interpretable concepts from an image and use them for classification. Sparse concept recovery methods leverage the latent space of vision-language models to represent image embeddings as sparse combinations of concept embeddings. However, by ignoring the hierarchical structure of semantic concepts, these methods may produce correct predictions with explanations that are inconsistent with the hierarchy. In this work, we propose Hierarchical Concept Embedding & Pursuit (HCEP), a framework that induces a hierarchy of concept embeddings in the latent space and performs hierarchical sparse coding to recover the concepts present in an image. Given a hierarchy of semantic concepts, we introduce a geometric construction for the corresponding hierarchy of embeddings. Under the assumption that the true concepts form a rooted path in the hierarchy, we derive sufficient conditions for their recovery in the embedding space. We further show that hierarchical sparse coding reliably recovers hierarchical concept embeddings, whereas standard sparse coding fails. Experiments on real-world datasets show that HCEP improves concept precision and recall compared to existing methods while maintaining competitive classification accuracy. Moreover, when the number of samples available for concept estimation and classifier training is limited, HCEP achieves superior classification accuracy and concept recovery. Our results demonstrate that incorporating hierarchical structure into sparse concept recovery leads to more faithful and interpretable image classification models.

comment: To be published in Conference on Computer Vision and Pattern Recognition (CVPR) 2026

♻ ☆ 3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks

Vineet Bhat, Yu-Hsiang Lan, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami

Robotic manipulation in 3D requires effective computation of N degree-of-freedom joint-space trajectories that enable precise and robust control. To achieve this, robots must integrate semantic understanding with visual perception to transform real-world observations into low-level control for object interaction. Recent advances in Vision-Language-Action (VLA) models have shown promise by mapping RGB images and language instructions to task space velocities, typically trained on large datasets of teleoperated demonstrations. However, these models often struggle with generalization beyond their training distributions. In this work, we introduce 3D-CAVLA, a novel finetuning framework that enhances task generalization of VLA policies by incorporating three key components: (i) chain-of-thought reasoning for structured decision-making, (ii) depth-aware perception for 3D spatial understanding, and (iii) task-oriented region-of-interest detection for focused manipulation. Extensive experiments in the LIBERO simulation environment demonstrate that 3D-CAVLA achieves an average success rate of 98.1% across diverse in-domain task suites. On unseen tasks, 3D-CAVLA delivers an absolute improvement of 8.8% in success rate, underscoring the benefits of 3D scene awareness for robust generalization. We validate our approach on real-world tabletop experiments demonstrating that the proposed model translates effectively from simulation to physical robots. 3D-CAVLA achieves over a 3X faster training convergence and delivers a 25% gain in success rate on unseen real world tasks. We will open-source our code and the unseen tasks dataset to promote community-driven research here: https://3d-cavla.github.io

comment: Accepted at the 1st Workshop on 3D LLM/VLA, CVPR 2025. This work has been submitted to the IEEE for possible publication

♻ ☆ FastVMT: Eliminating Redundancy in Video Motion Transfer ICLR2026

Yue Ma, Zhikai Wang, Tianhao Ren, Mingzhe Zheng, Hongyu Liu, Jiayi Guo, Kunyu Feng, Yuxuan Xue, Zixiang Zhao, Konrad Schindler, Qifeng Chen, Linfeng Zhang

Video motion transfer aims to synthesize videos by generating visual content according to a text prompt while transferring the motion pattern observed in a reference video. Recent methods predominantly use the Diffusion Transformer (DiT) architecture. To achieve satisfactory runtime, several methods attempt to accelerate the computations in the DiT, but fail to address structural sources of inefficiency. In this work, we identify and remove two types of computational redundancy in earlier work: motion redundancy arises because the generic DiT architecture does not reflect the fact that frame-to-frame motion is small and smooth; gradient redundancy occurs if one ignores that gradients change slowly along the diffusion trajectory. To mitigate motion redundancy, we mask the corresponding attention layers to a local neighborhood such that interaction weights are not computed unnecessarily distant image regions. To exploit gradient redundancy, we design an optimization scheme that reuses gradients from previous diffusion steps and skips unwarranted gradient computations. On average, FastVMT achieves a 3.43x speedup without degrading the visual fidelity or the temporal consistency of the generated videos.

comment: Accepted by ICLR2026, Project page: fastvmt.gitHub.io, Code: https://github.com/mayuelala/FastVMT

♻ ☆ Effort-Optimized, Accuracy-Driven Labelling and Validation of Test Inputs for DL Systems: A Mixed-Integer Linear Programming Approach

Mohammad Hossein Amini, Mehrdad Sabetzadeh, Shiva Nejati

Software systems increasingly include AI components based on deep learning (DL). Reliable testing of such systems requires near-perfect test-input validity and label accuracy, with minimal human effort. Yet, the DL community has largely overlooked the need to build highly accurate datasets with minimal effort, since DL training is generally tolerant of labelling errors. This challenge, instead, reflects concerns more familiar to software engineering, where a central goal is to construct high-accuracy test inputs, with accuracy as close to 100% as possible, while keeping associated costs in check. In this article we introduce OPAL, a human-assisted labelling method that can be configured to target a desired accuracy level while minimizing the manual effort required for labelling. The main contribution of OPAL is a mixed-integer linear programming (MILP) formulation that minimizes labelling effort subject to a specified accuracy target. To evaluate OPAL we instantiate it for two tasks in the context of testing vision systems: automatic labelling of test inputs and automated validation of test inputs. Our evaluation, based on more than 2500 experiments performed on nine datasets, comparing OPAL with eight baseline methods, shows that OPAL, relying on its MILP formulation, achieves an average accuracy of 98.8%, while cutting manual labelling by more than half. OPAL significantly outperforms automated labelling baselines in labelling accuracy across all nine datasets, when all methods are provided with the same manual-labelling budget. For automated test-input validation, on average, OPAL reduces manual effort by 28.8% while achieving 4.5% higher accuracy than the SOTA test-input validation baselines. Finally, we show that augmenting OPAL with an active-learning loop leads to an additional 4.5% reduction in required manual labelling, without compromising accuracy.

comment: Accepted in the Empirical Software Engineering (EMSE) Journal (2026)

♻ ☆ Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning ICLR 2026

Yue Ma, Yulong Liu, Qiyuan Zhu, Ayden Yang, Kunyu Feng, Xinhua Zhang, Zexuan Yan, Zhifeng Li, Sirui Han, Chenyang Qi, Qifeng Chen

Recently, breakthroughs in the video diffusion transformer have shown remarkable capabilities in diverse motion generations. As for the motion-transfer task, current methods mainly use two-stage Low-Rank Adaptations (LoRAs) finetuning to obtain better performance. However, existing adaptation-based motion transfer still suffers from motion inconsistency and tuning inefficiency when applied to large video diffusion transformers. Naive two-stage LoRA tuning struggles to maintain motion consistency between generated and input videos due to the inherent spatial-temporal coupling in the 3D attention operator. Additionally, they require time-consuming fine-tuning processes in both stages. To tackle these issues, we propose Follow-Your-Motion, an efficient two-stage video motion transfer framework that finetunes a powerful video diffusion transformer to synthesize complex motion. Specifically, we propose a spatial-temporal decoupled LoRA to decouple the attention architecture for spatial appearance and temporal motion processing. During the second training stage, we design the sparse motion sampling and adaptive RoPE to accelerate the tuning speed. To address the lack of a benchmark for this field, we introduce MotionBench, a comprehensive benchmark comprising diverse motion, including creative camera motion, single object motion, multiple object motion, and complex human motion. We show extensive evaluations on MotionBench to verify the superiority of Follow-Your-Motion.

comment: Accepted by ICLR 2026, project page: https://follow-your-motion.github.io/

♻ ☆ FigEx2: Visual-Conditioned Panel Detection and Captioning for Scientific Compound Figures

Jifeng Song, Arun Das, Pan Wang, Hui Ji, Kun Zhao, Yufei Huang

Scientific compound figures combine multiple labeled panels into a single image. However, in a PMC-scale crawl of 346,567 compound figures, 16.3% have no caption and 1.8% only have captions shorter than ten words, causing them to be discarded by existing caption-decomposition pipelines. We propose FigEx2, a visual-conditioned framework that localizes panels and generates panel-wise captions directly from the image, converting otherwise unusable figures into aligned panel-text pairs for downstream pretraining and retrieval. To mitigate linguistic variance in open-ended captioning, we introduce a noise-aware gated fusion module that adaptively controls how caption features condition the detection query space, and employ a staged SFT+RL strategy with CLIP-based alignment and BERTScore-based semantic rewards. To support high-quality supervision, we curate BioSci-Fig-Cap, a refined benchmark for panel-level grounding, alongside cross-disciplinary test suites in physics and chemistry. FigEx2 achieves 0.728 mAP@0.5:0.95 for detection, outperforms Qwen3-VL-8B by 0.44 in METEOR and 0.22 in BERTScore, and transfers zero-shot to out-of-distribution scientific domains without fine-tuning.

♻ ☆ $φ$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models

Thanh-Dat Truong, Huu-Thien Tran, Jackson Cothren, Bhiksha Raj, Khoa Luu

Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can lead to biased model updates and suboptimal performance across tasks. While recent continual learning studies have made progress in addressing catastrophic forgetting, the problem of fairness caused the imbalanced data remains largely underexplored. This paper presents a novel Fairness Direct Preference Optimization (FaiDPO or $φ$-DPO) framework for continual learning in LMMs. In particular, we first propose a new continual learning paradigm based on Direct Preference Optimization (DPO) to mitigate catastrophic forgetting by aligning learning with pairwise preference signals. Then, we identify the limitations of conventional DPO in imbalanced data and present a new $φ$-DPO loss that explicitly addresses distributional biases. We provide a comprehensive theoretical analysis demonstrating that our approach addresses both forgetting and data imbalance. Additionally, to enable $φ$-DPO-based continual learning, we construct pairwise preference annotations for existing benchmarks in the context of continual learning. Extensive experiments and ablation studies show the proposed $φ$-DPO achieves State-of-the-Art performance across multiple benchmarks, outperforming prior continual learning methods of LMMs.

comment: Accepted to CVPR'26

♻ ☆ Coarse-Guided Visual Generation via Weighted h-Transform Sampling

Yanghao Wang, Ziqi Jiang, Zhen Wang, Long Chen

Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently limited by high training costs and restricted generalization due to paired data collection. Accordingly, recent training-free works propose to leverage pretrained diffusion models and incorporate guidance during the sampling process. However, these training-free methods either require knowing the forward (fine-to-coarse) transformation operator, e.g., bicubic downsampling, or are difficult to balance between guidance and synthetic quality. To address these challenges, we propose a novel guided method by using the h-transform, a tool that can constrain stochastic processes (e.g., sampling process) under desired conditions. Specifically, we modify the transition probability at each sampling timestep by adding to the original differential equation with a drift function, which approximately steers the generation toward the ideal fine sample. To address unavoidable approximation errors, we introduce a noise-level-aware schedule that gradually de-weights the term as the error increases, ensuring both guidance adherence and high-quality synthesis. Extensive experiments across diverse image and video generation tasks demonstrate the effectiveness and generalization of our method.

♻ ☆ P$^2$HCT: Plug-and-Play Hierarchical C2F Transformer for Multi-Scale Feature Fusion

Junyi Hu, Tian Bai, Fengyi Wu, Zhenming Peng, Yi Zhang

Feature fusion plays a pivotal role in achieving high performance in vision models, yet existing attention-based fusion techniques often suffer from substantial computational overhead and implementation complexity, particularly in resource-constrained settings. To address these limitations, we introduce the Plug-and-Play Hierarchical C2F Transformer (P$^2$HCT), a lightweight module that combines coarse-to-fine token selection with shared attention parameters to preserve spatial details while reducing inference cost. P$^2$HCT is trainable using coarse attention alone and can be seamlessly activated at inference to enhance accuracy without retraining. Integrated into real-time detectors such as YOLOv11-N/S/M, P$^2$HCT achieves mAP gains of 0.9\%, 0.5\%, and 0.4\% on MS COCO with minimal latency increase. Similarly, embedding P$^2$HCT into ResNet-18/50/101 backbones improves ImageNet top-1 accuracy by 6.5\%, 1.7\%, and 1.0\%, respectively. These results underscore P$^2$HCT's effectiveness as a hardware-friendly and general-purpose enhancement for both detection and classification tasks.

comment: 12 pages, 6 figures, ICME2026

♻ ☆ Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting

Arthur Moreau, Richard Shaw, Michal Nazarczuk, Jisu Shin, Thomas Tanay, Zhensong Zhang, Songcen Xu, Eduardo Pérez-Pellitero

Feed-forward 3D Gaussian Splatting (3DGS) models enable real-time scene generation but are hindered by suboptimal pixel-aligned primitive placement, which relies on a dense, rigid grid that limits both quality and efficiency. We introduce a new feed-forward architecture that detects 3D Gaussian primitives at a sub-pixel level, replacing the pixel grid with an adaptive, ``Off-The-Grid" distribution. Inspired by keypoint detection, our decoder learns to locally distribute primitives across image patches. We also provide an Adaptive Density mechanism by assigning varying number of primitives per patch based on Shannon entropy. We combine the proposed decoder with a pre-trained 3D reconstruction backbone and train them end-to-end using photometric supervision without any 3D annotation. The resulting pose-free model generates photorealistic 3DGS scenes in seconds, achieving state-of-the-art novel view synthesis for feed-forward models. It outperforms competitors while using far fewer primitives, demonstrating a more accurate and efficient allocation that captures fine details and reduces artifacts. Project page: https://arthurmoreau.github.io/OffTheGrid/.

comment: CVPR 2026 camera ready version

♻ ☆ AutoRegressive Generation with B-rep Holistic Token Sequence Representation

Jiahao Li, Yunpeng Bai, Yongkang Dai, Hao Guo, Hongping Gan, Yilei Shi

Previous representation and generation approaches for the B-rep relied on graph-based representations that disentangle geometric and topological features through decoupled computational pipelines, thereby precluding the application of sequence-based generative frameworks, such as transformer architectures that have demonstrated remarkable performance. In this paper, we propose BrepARG, the first attempt to encode B-rep's geometry and topology into a holistic token sequence representation, enabling sequence-based B-rep generation with an autoregressive architecture. Specifically, BrepARG encodes B-rep into 3 types of tokens: geometry and position tokens representing geometric features, and face index tokens representing topology. Then the holistic token sequence is constructed hierarchically, starting with constructing the geometry blocks (i.e., faces and edges) using the above tokens, followed by geometry block sequencing. Finally, we assemble the holistic sequence representation for the entire B-rep. We also construct a transformer-based autoregressive model that learns the distribution over holistic token sequences via next-token prediction, using a multi-layer decoder-only architecture with causal masking. Experiments demonstrate that BrepARG achieves state-of-the-art (SOTA) performance. BrepARG validates the feasibility of representing B-rep as holistic token sequences, opening new directions for B-rep generation.

♻ ☆ UniGame: Turning a Unified Multimodal Model Into Its Own Adversary

Zhaolong Su, Wang Lu, Hao Chen, Sharon Li, Jindong Wang

Unified Multimodal Models (UMMs) have shown impressive performance in both understanding and generation with a single architecture. However, UMMs still exhibit a fundamental inconsistency: understanding favors compact embeddings, whereas generation favors reconstruction-rich representations. This structural trade-off produces misaligned decision boundaries, degraded cross-modal coherence, and heightened vulnerability under distributional and adversarial shifts. In this paper, we present UniGame, a self-adversarial post-training framework that directly targets the inconsistencies. By applying a lightweight perturber at the shared token interface, UniGame enables the generation branch to actively seek and challenge fragile understanding, turning the model itself into its own adversary. Experiments demonstrate that UniGame significantly improves the consistency (+4.6%). Moreover, it also achieves substantial improvements in understanding (+3.6%), generation (+0.02)on GenEval, out-of-distribution and adversarial robustness (+4.8% and +6.2% on NaturalBench and AdVQA). The framework is architecture-agnostic, introduces less than 1% additional parameters, and is complementary to existing post-training methods. These results position adversarial self-play as a general and effective principle for enhancing the coherence, stability, and unified competence of future multimodal foundation models. The official code is available at: https://github.com/AIFrontierLab/TorchUMM

comment: Accepted to CVPR 2026

♻ ☆ A Benchmark for Incremental Micro-expression Recognition

Zhengqin Lai, Xiaopeng Hong, Yabin Wang, Xiaobai Li

Micro-expression recognition plays a pivotal role in understanding hidden emotions and has applications across various fields. Traditional recognition methods assume access to all training data at once, but real-world scenarios involve continuously evolving data streams. To respond to the requirement of adapting to new data while retaining previously learned knowledge, we introduce the first benchmark specifically designed for incremental micro-expression recognition. Our contributions include: Firstly, we formulate the incremental learning setting tailored for micro-expression recognition. Secondly, we organize sequential datasets with carefully curated learning orders to reflect real-world scenarios. Thirdly, we define two cross-evaluation-based testing protocols, each targeting distinct evaluation objectives. Finally, we provide six baseline methods and their corresponding evaluation results. This benchmark lays the groundwork for advancing incremental micro-expression recognition research. All source code used in this study will be publicly available at https://github.com/ZhengQinLai/IMER-benchmark.

♻ ☆ Self-Attention And Beyond the Infinite: Towards Linear Transformers with Infinite Self-Attention

Giorgio Roffo, Hazem Abdelkawy, Nilli Lavie, Luke Palmer

The quadratic cost of softmax attention limits Transformer scalability in high-resolution vision. We introduce Infinite Self-Attention (InfSA), a spectral reformulation that treats each attention layer as a diffusion step on a content-adaptive token graph, accumulating multi-hop interactions through a discounted Neumann series over attention matrices. This links self-attention to classical graph centrality (Katz, PageRank, eigenvector centrality) for interpretable token weighting. We also show the Neumann kernel equals the fundamental matrix of an absorbing Markov chain, so a token's centrality is its expected number of random-walk visits before absorption. We then propose Linear-InfSA, a linear-time variant that approximates the principal eigenvector of the implicit attention operator without forming the full attention matrix. It keeps an auxiliary state of fixed size proportional to per-head dimension dh (independent of sequence length N), is drop-in compatible with Vision Transformers, and supports stable training at 4096 by 4096 and inference at 9216 by 9216 (about 332k tokens). In a 4-layer ViT (53.5M parameters, 59 GFLOPs at 224 by 224), Linear-InfSA reaches 84.7% top-1 on ImageNet-1K, a +3.2 point architectural gain over an equal-depth softmax ViT trained with the same recipe. On ImageNet-V2, InfViT variants outperform all compared baselines (up to 79.8% vs 76.8%), indicating robustness under distribution shift. On an A100 40GB GPU, Linear-InfViT runs at 231 images/s and 0.87 J/image (13x better throughput and energy than equal-depth ViT) and is the only tested model to complete 9216 by 9216 inference without out-of-memory. The linear approximation closely matches the dominant eigenvector of the quadratic operator (cosine 0.985).

comment: This work was initiated and primarily carried out while working at MindVisionLabs. We gratefully acknowledge the support of Toyota Motor Europe (TME) and Equixly API Security for this work

♻ ☆ DeH4R: A Decoupled and Hybrid Method for Road Network Graph Extraction

Dengxian Gong, Shunping Ji

The automated extraction of complete and precise road network graphs from remote sensing imagery remains a critical challenge in geospatial computer vision. Segmentation-based approaches, while effective in pixel-level recognition, struggle to maintain topology fidelity after vectorization postprocessing. Graph-growing methods build more topologically faithful graphs but suffer from computationally prohibitive iterative ROI cropping. Graph-generating methods first predict global static candidate road network vertices, and then infer possible edges between vertices. They achieve fast topology-aware inference, but limits the dynamic insertion of vertices. To address these challenges, we propose DeH4R, a novel hybrid model that combines graph-generating efficiency and graph-growing dynamics. This is achieved by decoupling the task into candidate vertex detection, adjacent vertex prediction, initial graph contruction, and graph expansion. This architectural innovation enables dynamic vertex (edge) insertions while retaining fast inference speed and enhancing both topology fidelity and spatial consistency. Comprehensive evaluations on CityScale and SpaceNet benchmarks demonstrate state-of-the-art (SOTA) performance. DeH4R outperforms the prior SOTA graph-growing method RNGDet++ by 4.62 APLS and 10.18 IoU on CityScale, while being approximately 10 $\times$ faster. The code will be made publicly available at https://github.com/7777777FAN/DeH4R.

comment: Accepted for publication in the IEEE Transactions on Geoscience and Remote Sensing (TGRS)

♻ ☆ VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding

Yufei Yin, Qianke Meng, Minghao Chen, Jiajun Ding, Zhenwei Shao, Zhou Yu

Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming video preprocessing to guide MLLMs in autonomous reasoning. To overcome these limitations, we introduce VideoARM, an Agentic Reasoning-over-hierarchical-Memory paradigm for long-form video understanding. Instead of static, exhaustive preprocessing, VideoARM performs adaptive, on-the-fly agentic reasoning and memory construction. Specifically, VideoARM performs an adaptive and continuous loop of observing, thinking, acting, and memorizing, where a controller autonomously invokes tools to interpret the video in a coarse-to-fine manner, thereby substantially reducing token consumption. In parallel, a hierarchical multimodal memory continuously captures and updates multi-level clues throughout the operation of the agent, providing precise contextual information to support the controller in decision-making. Experiments on prevalent benchmarks demonstrate that VideoARM outperforms the state-of-the-art method, DVD, while significantly reducing token consumption for long-form videos.

comment: Accepted to CVPR 2026, code available at https://milvlg.github.io/videoarm/

♻ ☆ MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations

Changlu Guo, Anders Nymark Christensen, Anders Bjorholm Dahl, Morten Rieger Hannemose

Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neural networks. However, existing diffusion-based counterfactual generation methods are often computationally expensive, slow to sample, and imprecise in localizing the modified regions. To address these limitations, we propose MaskDiME, a simple, fast, yet effective diffusion framework that unifies semantic consistency and spatial precision through localized sampling. Our approach adaptively focuses on decision-relevant regions to achieve localized and semantically consistent counterfactual generation while preserving high image fidelity. Our training-free framework, MaskDiME, performs inference over 30x faster than the baseline and achieves comparable or state-of-the-art performance across five benchmark datasets spanning diverse visual domains, establishing a practical and generalizable solution for efficient counterfactual explanation.

comment: Accepted by CVPR2026

♻ ☆ SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domains

Qingmei Li, Yang Zhang, Peifeng Zhang, Haohuan Fu, Juepeng Zheng

Domain generalization for semantic segmentation aims to mitigate the degradation in model performance caused by domain shifts. However, in many real-world scenarios, we are unable to access the model parameters and architectural details due to privacy concerns and security constraints. Traditional fine-tuning or adaptation is hindered, leading to the demand for input-level strategies that can enhance generalization without modifying model weights. To this end, we propose a \textbf{S}tyle-\textbf{A}daptive \textbf{GE}neralization framework (\textbf{SAGE}), which improves the generalization of frozen models under privacy constraints. SAGE learns to synthesize visual prompts that implicitly align feature distributions across styles instead of directly fine-tuning the backbone. Specifically, we first utilize style transfer to construct a diverse style representation of the source domain, thereby learning a set of style characteristics that can cover a wide range of visual features. Then, the model adaptively fuses these style cues according to the visual context of each input, forming a dynamic prompt that harmonizes the image appearance without touching the interior of the model. Through this closed-loop design, SAGE effectively bridges the gap between frozen model invariance and the diversity of unseen domains. Extensive experiments on five benchmark datasets demonstrate that SAGE achieves competitive or superior performance compared to state-of-the-art methods under privacy constraints and outperforms full fine-tuning baselines in all settings.

♻ ☆ CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities

Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni

Recent research on vision backbone architectures has predominantly focused on optimizing efficiency for hardware platforms with high parallel processing capabilities. This category increasingly includes embedded systems such as mobile phones and embedded AI accelerator modules. In contrast, CPUs do not have the possibility to parallelize operations in the same manner, wherefore models benefit from a specific design philosophy that balances amount of operations (MACs) and hardware-efficient execution by having high MACs per second (MACpS). In pursuit of this, we investigate two modifications to standard convolutions, aimed at reducing computational cost: grouping convolutions and reducing kernel sizes. While both adaptations substantially decrease the total number of MACs required for inference, sustaining low latency necessitates preserving hardware-efficiency. Our experiments across diverse CPU devices confirm that these adaptations successfully retain high hardware-efficiency on CPUs. Based on these insights, we introduce CPUBone, a new family of vision backbone models optimized for CPU-based inference. CPUBone achieves state-of-the-art Speed-Accuracy Trade-offs (SATs) across a wide range of CPU devices and effectively transfers its efficiency to downstream tasks such as object detection and semantic segmentation. Models and code are available at https://github.com/altair199797/CPUBone.

comment: Accepted at CVPR Findings 2026

♻ ☆ Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making

Shufeng Nan, Mengtian Li, Sixiao Zheng, Yuwei Lu, Han Zhang, Yanwei Fu

We present Mind-of-Director, a multi-modal agent-driven framework for film previz that models the collaborative decision-making process of a film production team. Given a creative idea, Mind-of-Director orchestrates multiple specialized agents to produce previz sequences within the game engine. The framework consists of four cooperative modules: Script Development, where agents draft and refine the screenplay iteratively; Virtual Scene Design, which transforms text into semantically aligned 3D environments; Character Behaviour Control, which determines character blocking and motion; and Camera Planning, which optimizes framing, movement, and composition for cinematic camera effects. A real-time visual editing system built in the game engine further enables interactive inspection and synchronized timeline adjustment across scenes, behaviours, and cameras. Extensive experiments and human evaluations show that Mind-of-Director generates high-quality, semantically grounded previz sequences in approximately 25 minutes per idea, demonstrating the effectiveness of agent collaboration for both automated prototyping and human-in-the-loop filmmaking.

♻ ☆ Relightable Holoported Characters: Capturing and Relighting Dynamic Human Performance from Sparse Views

Kunwar Maheep Singh, Jianchun Chen, Vladislav Golyanik, Stephan J. Garbin, Thabo Beeler, Rishabh Dabral, Marc Habermann, Christian Theobalt

We present Relightable Holoported Characters (RHC), a novel person-specific method for free-view rendering and relighting of full-body and highly dynamic humans solely observed from sparse-view RGB videos at inference. In contrast to classical one-light-at-a-time (OLAT)-based human relighting, our transformer-based RelightNet predicts relit appearance within a single network pass, avoiding costly OLAT-basis capture and generation. For training such a model, we introduce a new capture strategy and dataset recorded in a multi-view lightstage, where we alternate frames lit by random environment maps with uniformly lit tracking frames, simultaneously enabling accurate motion tracking and diverse illumination as well as dynamics coverage. Inspired by the rendering equation, we derive physics-informed features that encode geometry, albedo, shading, and the virtual camera view from a coarse human mesh proxy and the input views. Our RelightNet then takes these features as input and cross-attends them with a novel lighting condition, and regresses the relit appearance in the form of texel-aligned 3D Gaussian splats attached to the coarse mesh proxy. Consequently, our RelightNet implicitly learns to efficiently compute the rendering equation for novel lighting conditions within a single feed-forward pass. Experiments demonstrate our method's superior visual fidelity and lighting reproduction compared to state-of-the-art approaches. Project page: https://vcai.mpi-inf.mpg.de/projects/RHC/

♻ ☆ MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation

Mehrshad Taji, Arad Mahdinezhad Kashani, Iman Ahmadi, AmirHossein Jadidi, Saina Kashani, Babak Khalaj

Task planning for robotic manipulation with large language models (LLMs) is an emerging area. Prior approaches rely on specialized models, fine tuning, or prompt tuning, and often operate in an open loop manner without robust environmental feedback, making them fragile in dynamic settings. MALLVI presents a Multi Agent Large Language and Vision framework that enables closed-loop feedback driven robotic manipulation. Given a natural language instruction and an image of the environment, MALLVI generates executable atomic actions for a robot manipulator. After action execution, a Vision Language Model (VLM) evaluates environmental feedback and decides whether to repeat the process or proceed to the next step. Rather than using a single model, MALLVI coordinates specialized agents, Decomposer, Localizer, Thinker, and Reflector, to manage perception, localization, reasoning, and high level planning. An optional Descriptor agent provides visual memory of the initial state. The Reflector supports targeted error detection and recovery by reactivating only relevant agents, avoiding full replanning. Experiments in simulation and real-world settings show that iterative closed loop multi agent coordination improves generalization and increases success rates in zero shot manipulation tasks. Code available at https://github.com/iman1234ahmadi/MALLVI .

♻ ☆ Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes

Joseph Hoche, Andrei Bursuc, David Brellmann, Gilles Louppe, Pavel Izmailov, Angela Yao, Gianni Franchi

Large Vision-Language Models (LVLMs) often produce plausible but unreliable outputs, making robust uncertainty estimation essential. Recent work on semantic uncertainty estimates relies on external models to cluster multiple sampled responses and measure their semantic consistency. However, these clustering methods are often fragile, highly sensitive to minor phrasing variations, and can incorrectly group or separate semantically similar answers, leading to unreliable uncertainty estimates. We propose Semantic Gaussian Process Uncertainty (SGPU), a Bayesian framework that quantifies semantic uncertainty by analyzing the geometric structure of answer embeddings, avoiding brittle clustering. SGPU maps generated answers into a dense semantic space, computes the Gram matrix of their embeddings, and summarizes their semantic configuration via the eigenspectrum. This spectral representation is then fed into a Gaussian Process Classifier that learns to map patterns of semantic consistency to predictive uncertainty, and that can be applied in both black-box and white-box settings. Across six LLMs and LVLMs on eight datasets spanning VQA, image classification, and textual QA, SGPU consistently achieves state-of-the-art calibration (ECE) and discriminative (AUROC, AUARC) performance. We further show that SGPU transfers across models and modalities, indicating that its spectral representation captures general patterns of semantic uncertainty.

♻ ☆ Target-aware Image Editing via Cycle-consistent Constraints

Yanghao Wang, Zhen Wang, Long Chen

Recent pre-trained text-to-image flow models have enabled remarkable progress in text-based image editing. Mainstream approaches adopt a corruption-then-restoration paradigm, where the source image is first corrupted into an editable ``intermediate state'' and then restored to the target image under the prompt guidance. However, current methods construct this intermediate state in a target-agnostic manner, i.e., they mainly focus on realizing source image reconstruction while neglecting the semantic gaps towards the specific editing target. This design inherently results in limited editability or inconsistency when the desired modifications substantially deviate from the source. In this paper, we argue that the intermediate state should be target-aware, i.e., selectively corrupting editing-relevant contents while preserving editing-irrelevant ones. Thus, we propose FlowCycle, an inversion-free and flow-based editing framework that parameterizes corruption with learnable noises and optimizes them through a cycle-consistent process. By iteratively editing the source to the target and recovering back to the source with dual consistency constraints, FlowCycle learns to produce a target-aware intermediate state, enabling faithful modifications while preserving source consistency. For efficiency, we further accelerate the optimization by dynamically adjusting the sampling steps. Extensive ablations demonstrated that FlowCycle achieves superior editing performance.

♻ ☆ Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop

YoungJae Cheong, Jhonghyun An

LiDAR semantic segmentation degrades in adverse weather because refraction, scattering, and point dropouts corrupt geometry. Prior work in weather simulation, mixing-based augmentation, domain randomization, and uncertainty or boundary regularization improves robustness but still overlooks structural vulnerabilities near boundaries, corners, and sparse regions. We present a Light Geometry-aware adapter. The module aligns azimuth and applies horizontal circular padding to preserve neighbor continuity across the 0~360 degree wrap-around boundary. A local-window K-Nearest Neighbors gathers nearby points and computes simple local statistics, which are compressed into compact geometry-aware cues. During training, these cues drive region-aware regularization that stabilizes predictions in structurally fragile areas. The adapter is plug and play, complements augmentation, and can be enabled only during training with negligible inference cost. We adopt a source-only cross-weather setup where models train on SemanticKITTI and are evaluated on SemanticSTF without target labels or fine-tuning. The adapter improves mIoU by 7.9 percentage points over the data-centric augmentation baseline and by 0.6 points over the class-centric regularization baseline. These results indicate that geometry-driven regularization is a key direction for all-weather LiDAR segmentation.

comment: Accepted by ICRA 2026

♻ ☆ Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers

Cris Claessens, Christiaan Viviers, Giacomo D'Amicantonio, Egor Bondarev, Fons van der Sommen

We introduce SPECTRE, a fully transformer-based foundation model for volumetric computed tomography (CT). Our Self-Supervised & Cross-Modal Pretraining for CT Representation Extraction (SPECTRE) approach utilizes scalable 3D Vision Transformer architectures and modern self-supervised and vision-language pretraining strategies to learn general-purpose CT representations. Volumetric CT poses unique challenges, such as extreme token scaling, geometric anisotropy, and weak or noisy clinical supervision, that make standard transformer and contrastive learning recipes ineffective out of the box. The framework jointly optimizes a local transformer for high-resolution volumetric feature extraction and a global transformer for whole-scan context modeling, making large-scale 3D attention computationally tractable. Notably, SPECTRE is trained exclusively on openly available CT datasets, demonstrating that high-performing, generalizable representations can be achieved without relying on private data. Pretraining combines DINO-style self-distillation with SigLIP-based vision-language alignment using paired radiology reports, yielding features that are both geometrically consistent and clinically meaningful. Across multiple CT benchmarks, SPECTRE consistently outperforms prior CT foundation models in both zero-shot and fine-tuned settings, establishing SPECTRE as a scalable, open, and fully transformer-based foundation model for 3D medical imaging.

♻ ☆ OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models

Tengjin Weng, Wenhao Jiang, Jingyi Wang, Ming Li, Lin Ma, Zhong Ming

Multimodal large language models (MLLMs) have achieved remarkable performance across a wide range of vision language tasks. However, their ability in low-level visual perception, particularly in detecting fine-grained visual discrepancies, remains underexplored and lacks systematic analysis. In this work, we introduce OddGridBench, a controllable benchmark for evaluating the visual discrepancy sensitivity of MLLMs. OddGridBench comprises over 1,400 grid-based images, where a single element differs from all others by one or multiple visual attributes such as color, size, rotation, or position. Experiments reveal that all evaluated MLLMs, including open-source families such as Qwen3-VL and InternVL3.5, and proprietary systems like Gemini-2.5-Pro and GPT-5, perform far below human levels in visual discrepancy detection. We further propose OddGrid-GRPO, a reinforcement learning framework that integrates curriculum learning and distance-aware reward. By progressively controlling the difficulty of training samples and incorporating spatial proximity constraints into the reward design, OddGrid-GRPO significantly enhances the model's fine-grained visual discrimination ability. We hope OddGridBench and OddGrid-GRPO will lay the groundwork for advancing perceptual grounding and visual discrepancy sensitivity in multimodal intelligence. Code and dataset are available at https://wwwtttjjj.github.io/OddGridBench/.

comment: accepted by CVPR 2026

♻ ☆ TimeFlow: Temporal Conditioning for Longitudinal Brain MRI Registration and Aging Analysis

Bailiang Jian, Jiazhen Pan, Yitong Li, Fabian Bongratz, Ruochen Li, Daniel Rueckert, Benedikt Wiestler, Christian Wachinger

Longitudinal brain analysis is essential for understanding healthy aging and identifying pathological deviations. Longitudinal registration of sequential brain MRI underpins such analyses. However, existing methods are limited by reliance on densely sampled time series, a trade-off between accuracy and temporal smoothness, and an inability to prospectively forecast future brain states. To overcome these challenges, we introduce \emph{TimeFlow}, a learning-based framework for longitudinal brain MRI registration. TimeFlow uses a U-Net backbone with temporal conditioning to model neuroanatomy as a continuous function of age. Given only two scans from an individual, TimeFlow estimates accurate and temporally coherent deformation fields, enabling non-linear extrapolation to predict future brain states. This is achieved by our proposed inter-/extra-polation consistency constraints applied to both the deformation fields and deformed images. Remarkably, these constraints preserve temporal consistency and continuity without requiring explicit smoothness regularizers or densely sampled sequential data. Extensive experiments demonstrate that TimeFlow outperforms state-of-the-art methods in terms of both future timepoint forecasting and registration accuracy. Moreover, TimeFlow supports novel biological brain aging analyses by differentiating neurodegenerative trajectories from normal aging without requiring segmentation, thereby eliminating the need for labor-intensive annotations and mitigating segmentation inconsistency. TimeFlow offers an accurate, data-efficient, and annotation-free framework for longitudinal analysis of brain aging and chronic diseases, capable of forecasting brain changes beyond the observed study period.

♻ ☆ ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization

Minseo Kim, Minchan Kwon, Dongyeun Lee, Yunho Jeon, Junmo Kim

Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant residual information. Lacking such disentanglement, capturing high-fidelity features often incorporates undesired attributes that conflict with user prompts, compromising the trade-off between concept fidelity and text alignment. While existing methods rely on manual guidance, they often fail to represent intricate visual details and lack scalability. We introduce ConceptPrism, a framework that extracts shared features exclusively through cross-image comparison without external information. We jointly optimize a target token and image-wise residual tokens via reconstruction and exclusion losses. By suppressing shared information in residual tokens, the exclusion loss creates an information vacuum that forces the target token to capture the common concept. Extensive evaluations demonstrate that ConceptPrism achieves accurate concept disentanglement and significantly improves overall performance across diverse and complex visual concepts. The code is available at https://github.com/Minseo-Kimm/ConceptPrism.

comment: Accepted to CVPR 2026

♻ ☆ From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings

Jiajie Zhang, Sören Schwertfeger, Alexander Kleiner

We present a novel unsupervised framework to unlock vast unlabeled human demonstration data from continuous industrial video streams for Vision-Language-Action (VLA) model pre-training. Our method first trains a lightweight motion tokenizer to encode motion dynamics, then employs an unsupervised action segmenter leveraging a novel "Latent Action Energy" metric to discover and segment semantically coherent action primitives. The pipeline outputs both segmented video clips and their corresponding latent action sequences, providing structured data directly suitable for VLA pre-training. Evaluations on public benchmarks and a proprietary electric motor assembly dataset demonstrate effective segmentation of key tasks performed by humans at workstations. Further clustering and quantitative assessment via a Vision-Language Model confirm the semantic coherence of the discovered action primitives. To our knowledge, this is the first fully automated end-to-end system for extracting and organizing VLA pre-training data from unstructured industrial videos, offering a scalable solution for embodied AI integration in manufacturing.

comment: 10 pages, 5 figures, Accepted to CVPR 2026

♻ ☆ ScenePilot-4K: A Large-Scale First-Person Dataset and Benchmark for Vision-Language Models in Autonomous Driving

Yujin Wang, Yutong Zheng, Wenxian Fan, Tianyi Wang, Hongqing Chu, Li Zhang, Bingzhao Gao, Daxin Tian, Jianqiang Wang, Hong Chen

In this paper, we introduce ScenePilot-4K, a large-scale first-person dataset for safety-aware vision-language learning and evaluation in autonomous driving. Built from public online driving videos, ScenePilot-4K contains 3,847 hours of video and 27.7M front-view frames spanning 63 countries/regions and 1,210 cities. It jointly provides scene-level natural-language descriptions, risk assessment labels, key-participant annotations, ego trajectories, and camera parameters through a unified multi-stage annotation pipeline. Building on this dataset, we establish ScenePilot-Bench, a standardized benchmark that evaluates vision-language models along four complementary axes: scene understanding, spatial perception, motion planning, and GPT-based semantic alignment. The benchmark includes fine-grained metrics and geographic generalization settings that expose model robustness under cross-region and cross-traffic domain shifts. Baseline results on representative open-source and proprietary vision-language models show that current models remain competitive in high-level scene semantics but still exhibit substantial limitations in geometry-aware perception and planning-oriented reasoning. Beyond the released dataset itself, the proposed annotation pipeline serves as a reusable and extensible recipe for scalable dataset construction from public Internet driving videos. The codes and supplementary materials are available at: https://github.com/yjwangtj/ScenePilot-4K, with the dataset available at https://huggingface.co/datasets/larswangtj/ScenePilot-4K.

♻ ☆ Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization

Liao Shen, Wentao Jiang, Yiran Zhu, Jiahe Li, Tiezheng Ge, Zhiguo Cao, Bo Zheng

Recent advances in image-to-video (I2V) generation have achieved remarkable progress in synthesizing high-quality, temporally coherent videos from static images. Among all the applications of I2V, human-centric video generation includes a large portion. However, existing I2V models encounter difficulties in maintaining identity consistency between the input human image and the generated video, especially when the person in the video exhibits significant expression changes and movements. This issue becomes critical when the human face occupies merely a small fraction of the image. Since humans are highly sensitive to identity variations, this poses a critical yet under-explored challenge in I2V generation. In this paper, we propose Identity-Preserving Reward-guided Optimization (IPRO), a novel video diffusion framework based on reinforcement learning to enhance identity preservation. Instead of introducing auxiliary modules or altering model architectures, our approach introduces a direct and effective tuning algorithm that optimizes diffusion models using a face identity scorer. To improve performance and accelerate convergence, our method backpropagates the reward signal through the last steps of the sampling chain, enabling richer gradient feedback. We also propose a novel facial scoring mechanism that treats faces in ground-truth videos as facial feature pools, providing multi-angle facial information to enhance generalization. A KL-divergence regularization is further incorporated to stabilize training and prevent overfitting to the reward signal. Extensive experiments on Wan 2.2 I2V model and our in-house I2V model demonstrate the effectiveness of our method. Our project and code are available at https://ipro-alimama.github.io/.

comment: accepted by CVPR 2026

♻ ☆ Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with Structured Output (SLSO) Framework

Nanaka Hosokawa, Ryo Takahashi, Tomoya Kitano, Yukihiro Iida, Chisako Muramatsu, Tatsuro Hayashi, Yuta Seino, Xiangrong Zhou, Takeshi Hara, Akitoshi Katsumata, Hiroshi Fujita

Vision-language models (VLMs) such as GPT (Generative Pre-Trained Transformer) have shown potential for medical image interpretation; however, challenges remain in generating reliable radiological findings in clinical practice, as exemplified by dental pathologies. This study proposes a Self-correction Loop with Structured Output (SLSO) framework as an integrated processing methodology to enhance the accuracy and reliability of AI-generated findings for jaw cysts in dental panoramic radiographs. Dental panoramic radiographs with jaw cysts were used to implement a 10-step integrated processing framework incorporating image analysis, structured data generation, tooth number extraction, consistency checking, and iterative regeneration. The framework functioned as an external validation mechanism for GPT outputs. Performance was compared against the conventional Chain-of-Thought (CoT) method across seven evaluation items: transparency, internal structure, borders, root resorption, tooth movement, relationships with other structures, and tooth number. The SLSO framework improved output accuracy for multiple items compared to the CoT method, with the most notable improvements observed in tooth number identification, tooth movement detection, and root resorption assessment. In successful cases, consistently structured outputs were achieved after up to five regenerations. The framework enforced explicit negative finding descriptions and suppressed hallucinations, although accurate identification of extensive lesions spanning multiple teeth remained limited. This investigation established the feasibility of the proposed integrated processing methodology and provided a foundation for future validation studies with larger, more diverse datasets.

comment: Revised manuscript; supplementary materials added. Submitted to Diagnostics

♻ ☆ OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition

Haochen Chang, Pengfei Ren, Buyuan Zhang, Da Li, Tianhao Han, Haoyang Zhang, Liang Xie, Hongbo Chen, Erwei Yin

Online micro gesture recognition from hand skeletons is critical for VR/AR interaction but faces challenges due to limited public datasets and task-specific algorithms. Micro gestures involve subtle motion patterns, which make constructing datasets with precise skeletons and frame-level annotations difficult. To this end, we develop a multi-view self-supervised pipeline to automatically generate skeleton data, complemented by heuristic rules and expert refinement for semi-automatic annotation. Based on this pipeline, we introduce OMG-Bench, the first large-scale public benchmark for skeleton-based online micro gesture recognition. It features 40 fine-grained gesture classes with 13,948 instances across 1,272 sequences, characterized by subtle motions, rapid dynamics, and continuous execution. To tackle these challenges, we propose Hierarchical Memory-Augmented Transformer (HMATr), an end-to-end framework that unifies gesture detection and classification by leveraging hierarchical memory banks which store frame-level details and window-level semantics to preserve historical context. In addition, it employs learnable position-aware queries initialized from the memory to implicitly encode gesture positions and semantics. Experiments show that HMATr outperforms state-of-the-art methods by 7.6% in detection rate, establishing a strong baseline for online micro gesture recognition. Project page: https://omg-bench.github.io/

comment: Accepted by CVPR 2026

♻ ☆ Vega: Learning to Drive with Natural Language Instructions

Sicheng Zuo, Yuxuan Li, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu

Vision-language-action models have reshaped autonomous driving to incorporate languages into the decision-making process. However, most existing pipelines only utilize the language modality for scene descriptions or reasoning and lack the flexibility to follow diverse user instructions for personalized driving. To address this, we first construct a large-scale driving dataset (InstructScene) containing around 100,000 scenes annotated with diverse driving instructions with the corresponding trajectories. We then propose a unified Vision-Language-World-Action model, Vega, for instruction-based generation and planning. We employ the autoregressive paradigm to process visual inputs (vision) and language instructions (language) and the diffusion paradigm to generate future predictions (world modeling) and trajectories (action). We perform joint attention to enable interactions between the modalities and use individual projection layers for different modalities for more capabilities. Extensive experiments demonstrate that our method not only achieves superior planning performance but also exhibits strong instruction-following abilities, paving the way for more intelligent and personalized driving systems.

comment: Code is available at https://github.com/zuosc19/Vega

♻ ☆ Habitat Classification from Ground-Level Imagery Using Deep Neural Networks

Hongrui Shi, Lisa Norton, Lucy Ridding, Simon Rolph, Tom August, Claire M Wood, Lan Qie, Petra Bosilj, James M Brown

Habitat assessment at local scales--critical for enhancing biodiversity and guiding conservation priorities--often relies on expert field surveys that can be costly, motivating the exploration of AI-driven tools to automate and refine this process. While most AI-driven habitat mapping depends on remote sensing, it is often constrained by sensor availability, weather, and coarse resolution. In contrast, ground-level imagery captures essential structural and compositional cues invisible from above and remains underexplored for robust, fine-grained habitat classification. This study addresses this gap by applying state-of-the-art deep neural network architectures to ground-level habitat imagery. Leveraging data from the UK Countryside Survey covering 18 broad habitat types, we evaluate two families of models - convolutional neural networks (CNNs) and vision transformers (ViTs) - under both supervised and supervised contrastive learning paradigms. Our results demonstrate that ViTs consistently outperform state-of-the-art CNN baselines on key classification metrics (Top-3 accuracy = 91%, MCC = 0.66) and offer more interpretable scene understanding tailored to ground-level images. Moreover, supervised contrastive learning significantly reduces misclassification rates among visually similar habitats (e.g., Improved vs. Neutral Grassland), driven by a more discriminative embedding space. Finally, our best model performs on par with experienced ecological experts in habitat classification from images, underscoring the promise of expert-level automated assessment. By integrating advanced AI with ecological expertise, this research establishes a scalable, cost-effective framework for ground-level habitat monitoring to accelerate biodiversity conservation and inform land-use decisions at a national scale.

comment: Accepted to Ecological Informatics. Main paper has 19 pages, 7 figures, 4 tables. Appendix has 10 pages, 8 figures, 2 tables

♻ ☆ From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation

Dawid Malarz, Filip Manjak, Maciej Zięba, Przemysław Spurek, Artur Kasymov

The rapid progress of text-to-image diffusion models raises significant concerns regarding the unauthorized reproduction of trademarked content. While prior work targets general concepts (e.g., styles, celebrities), it fails to address specific brand identifiers. Brand recognition is multi-dimensional, extending beyond explicit logos to encompass distinctive structural features (e.g., a car's front grille). To tackle this, we introduce unbranding, a novel task for the fine-grained removal of both trademarks and subtle structural brand features, while preserving semantic coherence. We construct a benchmark dataset and introduce a novel evaluation framework combining Vision Language Models (VLMs) with segmentation-based classifiers trained on human annotations of logos and trade dress features, addressing the limitations of existing brand detectors that fail to capture abstract trade dress. Furthermore, we observe that newer, higher-fidelity systems (SDXL, FLUX) synthesize brand identifiers more readily than older models, highlighting the urgency of this challenge. Our results confirm that unbranding is a distinct problem requiring specialized techniques. Project Page: https://gmum.github.io/UNBRANDING/.

♻ ☆ OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective

Markus Gross, Sai B. Matha, Aya Fahmy, Rui Song, Daniel Cremers, Henri Meess

Semantic Scene Completion (SSC) is essential for 3D perception in mobile robotics, as it enables holistic scene understanding by jointly estimating dense volumetric occupancy and per-voxel semantics. Although SSC has been widely studied in terrestrial domains such as autonomous driving, aerial settings like autonomous flying remain largely unexplored, thereby limiting progress on downstream applications. Furthermore, LiDAR sensors are the primary modality for SSC data generation, which poses challenges for most uncrewed aerial vehicles (UAVs) due to flight regulations, mass and energy constraints, and the sparsity of LiDAR point clouds from elevated viewpoints. To address these limitations, we propose a LiDAR-free, camera-based data generation framework. By leveraging classical 3D reconstruction, our framework automates semantic label transfer by lifting <10% of annotated images into the reconstructed point cloud, substantially minimizing manual 3D annotation effort. Based on this framework, we introduce OccuFly, the first real-world, camera-based aerial SSC benchmark, captured across multiple altitudes and all seasons. OccuFly provides over 20,000 samples of images, semantic voxel grids, and metric depth maps across 21 semantic classes in urban, industrial, and rural environments, and follows established data organization for seamless integration. We benchmark both SSC and metric monocular depth estimation on OccuFly, revealing fundamental limitations of current vision foundation models in aerial settings and establishing new challenges for robust 3D scene understanding in the aerial domain. Visit https://github.com/markus-42/occufly.

comment: Accepted to CVPR 2026

♻ ☆ Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation

Zhiwang Zhou, Yuandong Pu, Xuming He, Yidi Liu, Yixin Chen, Junchao Gong, Xiang Zhuang, Wanghan Xu, Qinglong Cao, Shixiang Tang, Yihao Liu, Wenlong Zhang, Lei Bai

Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first multimodal foundation model that unifies weather generation and understanding within a single architecture. Omni-Weather integrates a radar encoder for weather generation tasks, followed by unified processing using a shared self-attention mechanism. Moreover, we construct a Chain-of-Thought dataset for causal reasoning in weather generation, enabling interpretable outputs and improved perceptual quality. Extensive experiments show Omni-Weather achieves state-of-the-art performance in both weather generation and understanding. Our findings further indicate that generative and understanding tasks in the weather domain can mutually enhance each other. Omni-Weather also demonstrates the feasibility and value of unifying weather generation and understanding.

♻ ☆ Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation

Yunzhe Xu, Yiyuan Pan, Zhe Liu

Vision-and-Language Navigation (VLN) requires agents to follow natural language instructions through environments, with memory-persistent variants demanding progressive improvement through accumulated experience. Existing approaches for memory-persistent VLN face critical limitations: they lack effective memory access mechanisms, instead relying on entire memory incorporation or fixed-horizon lookup, and predominantly store only environmental observations while neglecting navigation behavioral patterns that encode valuable decision-making strategies. We present Memoir, which employs imagination as a retrieval mechanism grounded by explicit memory: a world model imagines future navigation states as queries to selectively retrieve relevant environmental observations and behavioral histories. The approach comprises: 1) a language-conditioned world model that imagines future states serving dual purposes: encoding experiences for storage and generating retrieval queries; 2) Hybrid Viewpoint-Level Memory that anchors both observations and behavioral patterns to viewpoints, enabling hybrid retrieval; and 3) an experience-augmented navigation model that integrates retrieved knowledge through specialized encoders. Extensive evaluation across diverse memory-persistent VLN benchmarks with 10 distinct testing scenarios demonstrates Memoir's effectiveness: significant improvements across all scenarios, with 5.4% SPL gains on IR2R over the best memory-persistent baseline, accompanied by 8.3x training speedup and 74% inference memory reduction. The results validate that predictive retrieval of both environmental and behavioral memories enables more effective navigation, with analysis indicating substantial headroom (73.3% vs 93.4% upper bound) for this imagination-guided paradigm.

comment: Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

♻ ☆ LitePT: Lighter Yet Stronger Point Transformer

Yuanwen Yue, Damien Robert, Jianyuan Wang, Sunghwan Hong, Jan Dirk Wegner, Christian Rupprecht, Konrad Schindler

Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains unclear. We analyse the role of different computational blocks in 3D point cloud networks and find an intuitive behaviour: convolution is adequate to extract low-level geometry at high-resolution in early layers, where attention is expensive without bringing any benefits; attention captures high-level semantics and context in low-resolution, deep layers more efficiently, where convolution inflates the parameter count. Guided by this design principle, we propose a new, improved 3D point cloud backbone that employs convolutions in early stages and switches to attention for deeper layers. To avoid the loss of spatial layout information when discarding redundant convolution layers, we introduce a novel, parameter-free 3D positional encoding, PointROPE. The resulting LitePT model has $3.6\times$ fewer parameters, runs $2\times$ faster, and uses $2\times$ less memory than the state-of-the-art Point Transformer V3, but nonetheless matches or outperforms it on a range of tasks and datasets. Code and models are available at: https://github.com/prs-eth/LitePT.

comment: CVPR 2026, Project page: https://litept.github.io/

♻ ☆ OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar

Jianqiang Ren, Lin Liu, Steven Hoi

We propose OMG-Avatar, a novel One-shot method that leverages a Multi-LOD (Level-of-Detail) Gaussian representation for animatable 3D head reconstruction from a single image in 0.2s. Our method enables LOD head avatar modeling using a unified model that accommodates diverse hardware capabilities and inference speed requirements. To capture both global and local facial characteristics, we employ a transformer-based architecture for global feature extraction and projection-based sampling for local feature acquisition. These features are effectively fused under the guidance of a depth buffer, ensuring occlusion plausibility. We further introduce a coarse-to-fine learning paradigm to support Level-of-Detail functionality and enhance the perception of hierarchical details. To address the limitations of 3DMMs in modeling non-head regions such as the shoulders, we introduce a multi-region decomposition scheme in which the head and shoulders are predicted separately and then integrated through cross-region combination. Extensive experiments demonstrate that OMG-Avatar outperforms state-of-the-art methods in reconstruction quality, reenactment performance, and computational efficiency. The project homepage is https://human3daigc.github.io/OMGAvatar_project_page/ .

♻ ☆ Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning

Tommaso Galliena, Stefano Rosa, Tommaso Apicella, Pietro Morerio, Alessio Del Bue, Lorenzo Natale

Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved inconsistencies using offline multi-view aggregation or multi-stage pipelines that decouple exploration, data association, and caption learning, with limited capacity to reason over previously observed objects. In this paper, we introduce a unified, memory-augmented Vision-Language agent that simultaneously handles data association, object captioning, and exploration policy within a single autoregressive framework. The model processes the current RGB observation, a top-down explored map, and an object-level episodic memory serialized into object-level tokens, ensuring persistent object identity and semantic consistency across extended sequences. To train the model in a self-supervised manner, we collect a dataset in photorealistic 3D environments using a disagreement-based policy and a pseudo-captioning model that enforces consistency across multi-view caption histories. Extensive evaluation on a manually annotated object-level test set, demonstrate improvements of up to +11.86% in standard captioning scores and +7.39% in caption self-similarity over baseline models, while enabling scalable performance through a compact scene representation. Code, model weights, and data are available at https://hsp-iit.github.io/epos-vlm/.

comment: 24 pages, 7 figures, 7 tables (including Supplementary Materials)

♻ ☆ FA-Seg: A Fast and Accurate Diffusion-Based Method for Open-Vocabulary Segmentation

Huy Che, Vinh-Tiep Nguyen

Open-vocabulary semantic segmentation (OVSS) aims to segment objects from arbitrary text categories without requiring densely annotated datasets. Although contrastive learning based models enable zero-shot segmentation, they often lose fine spatial precision at pixel level, due to global representation bias. In contrast, diffusion-based models naturally encode fine-grained spatial features via attention mechanisms that capture both global context and local details. However, they often face challenges in balancing the computation costs and the quality of the segmentation mask. In this work, we present FA-Seg, a Fast and Accurate training-free framework for open-vocabulary segmentation based on diffusion models. FA-Seg performs segmentation using only a (1+1)-step from a pretrained diffusion model. Moreover, instead of running multiple times for different classes, FA-Seg performs segmentation for all classes at once. To further enhance the segmentation quality, FA-Seg introduces three key components: (i) a dual-prompt mechanism for discriminative, class-aware attention extraction, (ii) a Hierarchical Attention Refinement Method (HARD) that enhances semantic precision via multi-resolution attention fusion, and (iii) a Test-Time Flipping (TTF) scheme designed to improve spatial consistency. Extensive experiments show that FA-Seg achieves state-of-the-art training-free performance, obtaining 43.8% average mIoU across PASCAL VOC, PASCAL Context, and COCO Object benchmarks while maintaining superior inference efficiency. Our results demonstrate that FA-Seg provides a strong foundation for extendability, bridging the gap between segmentation quality and inference efficiency. The source code is available at https://github.com/chequanghuy/FA-Seg.

♻ ☆ Multimodal Graph Network Modeling for Human-Object Interaction Detection with PDE Graph Diffusion

Wenxuan Ji, Haichao Shi, Xiao-Yu Zhang

Existing GNN-based Human-Object Interaction (HOI) detection methods rely on simple MLPs to fuse instance features and propagate information. However, this mechanism is largely empirical and lack of targeted information propagation process. To address this problem, we propose Multimodal Graph Network Modeling (MGNM) for HOI detection with Partial Differential Equation (PDE) graph diffusion. Specifically, we first design a multimodal graph network framework that explicitly models the HOI detection task within a four-stage graph structure. Next, we propose a novel PDE diffusion mechanism to facilitate information propagation within this graph. This mechanism leverages multimodal features to propaganda information via a white-box PDE diffusion equation. Furthermore, we design a variational information squeezing (VIS) mechanism to further refine the multimodal features extracted from CLIP, thereby mitigating the impact of noise inherent in pretrained Vision-Language Models. Extensive experiments demonstrate that our MGNM achieves state-of-the-art performance on two widely used benchmarks: HICO-DET and V-COCO. Moreover, when integrated with a more advanced object detector, our method yields significant performance gains while maintaining an effective balance between rare and non-rare categories.

♻ ☆ Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction

Ruihong Yin, Xuepeng Shi, Oleksandr Bailo, Marco Manfredi, Theo Gevers

comment: 15 pages, 14 figures

♻ ☆ Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers

Xinyu Peng, Han Li, Yuyang Huang, Ziyang Zheng, Yaoming Wang, Xin Chen, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

Existing video frame interpolation (VFI) methods often adopt a frame-centric approach, processing videos as independent short segments (e.g., triplets), which leads to temporal inconsistencies and motion artifacts. To overcome this, we propose a holistic, video-centric paradigm named Local Diffusion Forcing for Video Frame Interpolation (LDF-VFI). Our framework is built upon an auto-regressive diffusion transformer that models the entire video sequence to ensure long-range temporal coherence. To mitigate error accumulation inherent in auto-regressive generation, we introduce a novel skip-concatenate sampling strategy that effectively maintains temporal stability. Furthermore, LDF-VFI incorporates sparse, local attention and tiled VAE encoding, a combination that not only enables efficient processing of long sequences but also allows generalization to arbitrary spatial resolutions (e.g., 4K) at inference without retraining. An enhanced conditional VAE decoder, which leverages multi-scale features from the input video, further improves reconstruction fidelity. Empirically, LDF-VFI achieves state-of-the-art performance on challenging VFI benchmarks, demonstrating superior per-frame quality and temporal consistency, especially in scenes with large motion. The source code is available at https://github.com/xypeng9903/LDF-VFI.

♻ ☆ UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking

Xuangeng Chu, Ruicong Liu, Yifei Huang, Yun Liu, Yichen Peng, Bo Zheng

comment: CVPR 2026, code is available at https://github.com/xg-chu/UniLS, more demos are available at https://xg-chu.site/project_unils/

♻ ☆ A$^3$: Towards Advertising Aesthetic Assessment

Kaiyuan Ji, Yixuan Gao, Lu Sun, Yushuo Zheng, Zijian Chen, Jianbo Zhang, Xiangyang Zhu, Yuan Tian, Zicheng Zhang, Guangtao Zhai

Advertising images significantly impact commercial conversion rates and brand equity, yet current evaluation methods rely on subjective judgments, lacking scalability, standardized criteria, and interpretability. To address these challenges, we present A^3 (Advertising Aesthetic Assessment), a comprehensive framework encompassing four components: a paradigm (A^3-Law), a dataset (A^3-Dataset), a multimodal large language model (A^3-Align), and a benchmark (A^3-Bench). Central to A^3 is a theory-driven paradigm, A^3-Law, comprising three hierarchical stages: (1) Perceptual Attention, evaluating perceptual image signals for their ability to attract attention; (2) Formal Interest, assessing formal composition of image color and spatial layout in evoking interest; and (3) Desire Impact, measuring desire evocation from images and their persuasive impact. Building on A^3-Law, we construct A^3-Dataset with 120K instruction-response pairs from 30K advertising images, each richly annotated with multi-dimensional labels and Chain-of-Thought (CoT) rationales. We further develop A^3-Align, trained under A^3-Law with CoT-guided learning on A^3-Dataset. Extensive experiments on A^3-Bench demonstrate that A^3-Align achieves superior alignment with A^3-Law compared to existing models, and this alignment generalizes well to quality advertisement selection and prescriptive advertisement critique, indicating its potential for broader deployment. Dataset, code, and models can be found at: https://github.com/euleryuan/A3-Align.

comment: Accepted to CVPR 2026

♻ ☆ SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion

Jungbin Cho, Minsu Kim, Jisoo Kim, Ce Zheng, Laszlo A. Jeni, Ming-Hsuan Yang, Youngjae Yu, Seonjoo Kim

Human motion is inherently diverse and semantically rich, while also shaped by the surrounding scene. However, existing motion generation approaches fail to generate semantically diverse motion while simultaneously respecting geometric scene constraints, since constructing large-scale datasets with both rich text-motion coverage and precise scene interactions is extremely challenging. In this work, we introduce SceneAdapt, a two-stage adaptation framework that enables semantically diverse, scene-aware human motion generation from text without large-scale paired text--scene--motion data. Our key idea is to use motion inbetweening, a learnable proxy task that requires no text, as a bridge between two disjoint resources: a text-motion dataset and a scene-motion dataset. By first adapting a text-to-motion model through inbetweening and then through scene-aware inbetweening, SceneAdapt injects geometric scene constraints into text-conditioned generation while preserving semantic diversity. To enable adaptation for inbetweening, we propose a novel Context-aware Keyframing (CaKey) layer that modulates motion latents for keyframe-conditioned synthesis while preserving the original latent manifold. To further adapt the model for scene-aware inbetweening, we introduce a Scene-conditioning (SceneCo) layer that injects geometric scene information by adaptively querying local context via cross-attention. Experimental results show that SceneAdapt effectively injects scene-awareness into text-to-motion models without sacrificing semantic diversity, and we further analyze the mechanisms through which this awareness emerges. Code and models will be released. Project page: \href{https://sceneadapt.github.io/}{sceneadapt.github.io}

comment: 15 pages

♻ ☆ RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answering

Léo Butsanets, Charles Corbière, Julien Khlaut, Pierre Manceron, Corentin Dancette

In this work, we introduce RadImageNet-VQA, a large-scale dataset designed to advance radiologic visual question answering (VQA) on CT and MRI exams. Existing medical VQA datasets are limited in scale, dominated by X-ray imaging or biomedical illustrations, and often prone to text-based shortcuts. RadImageNet-VQA is built from expert-curated annotations and provides 750K images paired with 7.5M question-answer samples. It covers three key tasks - abnormality detection, anatomy recognition, and pathology identification - spanning eight anatomical regions and 97 pathology categories, and supports open-ended, closed-ended, and multiple-choice questions. Extensive experiments show that state-of-the-art vision-language models still struggle with fine-grained pathology identification, particularly in open-ended settings and even after fine-tuning. Text-only analysis further reveals that model performance collapses to near-random without image inputs, confirming that RadImageNet-VQA is free from linguistic shortcuts. The full dataset and benchmark are publicly available at https://huggingface.co/datasets/raidium/RadImageNet-VQA.

comment: Preprint, 33 pages, 15 figures, 11 tables

♻ ☆ Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval

Shuyu Yang, Yaxiong Wang, Yongrui Li, Li Zhu, Zhedong Zheng

In this work, we focus on text-based person retrieval, which identifies individuals based on textual descriptions. Despite advancements enabled by synthetic data for pretraining, a significant domain gap, due to variations in lighting, color, and viewpoint, limits the effectiveness of the pretrain-finetune paradigm. To overcome this issue, we propose a unified pipeline incorporating domain adaptation at both image and region levels. Our method features two key components: Domain-aware Diffusion (DaD) for image-level adaptation, which aligns image distributions between synthetic and real-world domains, e.g., CUHK-PEDES, and Multi-granularity Relation Alignment (MRA) for region-level adaptation, which aligns visual regions with descriptive sentences, thereby addressing disparities at a finer granularity. This dual-level strategy effectively bridges the domain gap, achieving state-of-the-art performance on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets. The dataset, model, and code are available at https://github.com/Shuyu-XJTU/MRA.

♻ ☆ GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction

Mai Su, Qihan Yu, Zhongtao Wang, Yilong Li, Chengwei Pan, Yisong Chen, Guoping Wang, Fei Zhu

3D Gaussian Splatting (3DGS) enables efficient rendering, yet accurate surface reconstruction remains challenging due to unreliable geometric supervision. Existing approaches predominantly rely on depth-based reprojection to infer visibility and enforce multi-view consistency, leading to a fundamental circular dependency: visibility estimation requires accurate depth, while depth supervision itself is conditioned on visibility. In this work, we revisit multi-view geometric supervision from the perspective of visibility modeling. Instead of inferring visibility from pixel-wise depth consistency, we explicitly model visibility at the level of Gaussian primitives. We introduce a Gaussian visibility-aware multi-view geometric consistency (GVMV) formulation, which aggregates cross-view visibility of shared Gaussians to construct reliable supervision over co-visible regions. To further incorporate monocular priors, we propose a progressive quadtree-calibrated depth alignment (QDC) strategy that performs block-wise affine calibration under visibility-aware guidance, effectively mitigating scale ambiguity while preserving local geometric structures. Extensive experiments on DTU and Tanks and Temples demonstrate that our method consistently improves reconstruction accuracy over prior Gaussian-based approaches. Our code is fully open-sourced and available at an anonymous repository: https://github.com/GVGScode/GVGS.

♻ ☆ AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models

Zhen Qu, Xian Tao, Xiaoyi Bao, Dingrong Wang, ShiChen Qu, Zhengtao Zhang, Xingang Wang

Large multimodal models (LMMs) exhibit strong task generalization capabilities, offering new opportunities for zero-shot visual anomaly segmentation (ZSAS). However, existing LMM-based segmentation approaches still face fundamental limitations: anomaly concepts are inherently abstract and context-dependent, lacking stable visual prototypes, and the weak alignment between high-level semantic embeddings and pixel-level spatial features hinders precise anomaly localization. To address these challenges, we present AG-VAS (Anchor-Guided Visual Anomaly Segmentation), a new framework that expands the LMM vocabulary with three learnable semantic anchor tokens-[SEG], [NOR], and [ANO], establishing a unified anchor-guided segmentation paradigm. Specifically, [SEG] serves as an absolute semantic anchor that translates abstract anomaly semantics into explicit, spatially grounded visual entities (e.g., holes or scratches), while [NOR] and [ANO] act as relative anchors that model the contextual contrast between normal and abnormal patterns across categories. To further enhance cross-modal alignment, we introduce a Semantic-Pixel Alignment Module (SPAM) that aligns language-level semantic embeddings with high-resolution visual features, along with an Anchor-Guided Mask Decoder (AGMD) that performs anchor-conditioned mask prediction for precise anomaly localization. In addition, we curate Anomaly-Instruct20K, a large-scale instruction dataset that organizes anomaly knowledge into structured descriptions of appearance, shape, and spatial attributes, facilitating effective learning and integration of the proposed semantic anchors. Extensive experiments on six industrial and medical benchmarks demonstrate that AG-VAS achieves consistent state-of-the-art performance in the zero-shot setting.

♻ ☆ DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving

Xiaosong Jia, Yanhao Liu, Yu Hong, Renqiu Xia, Junqi You, Bin Sun, Zhihui Hao, Junchi Yan

Feed-forward reconstruction has been progressed rapidly, with the Visual Geometry Grounded Transformer (VGGT) being a notable baseline. However, directly applying VGGT to autonomous driving (AD) fails to capture three domain-specific priors: (i) Sparse Spatial Overlap: the overlap among mutli-view cameras is minimal due to $360^{\circ}$ coverage requirements under budget control, which renders global attention among all images inefficient; (ii) Calibrated Geometric Constraints: the absolute distance among cameras is generally accessible for AD data with calibration process before driving. Standard VGGT is unable to directly utilize such information for absolute scale scene reconstruction; (iii) Rigid Extrinsic Constancy: relative poses of multi-view cameras are approximately static, i.e., the ego-motion is the same for all cameras. To bridge these gaps, we propose DriveVGGT, a scale-aware reconstruction framework that explicitly integrates these priors through three targeted components. First, for the Sparse Spatial Overlap in (i), we introduce a Temporal Video Attention (TVA) module to process multi-camera videos independently. Second, for Calibrated Geometric Constraints in (ii), a Multi-camera Consistency Attention (MCA) module is designed to directly utilize the calibration information among cameras with a scale head for absolute scale scene reconstruction. Finally, to utilize Rigid Extrinsic Constancy in (iii), we reformulate the decoding process of VGGT into factorized sequential pose head and ego motion head. On AD datasets, experiments demonstrate that DriveVGGT reduces inference time by 49.3\% while improving depth and pose estimation compared to vanilla VGGT in long-sequence scenarios. It consistently outperforms recent SOTA variants. Meanwhile, extensive ablation studies verify the effectiveness of each devised module.

♻ ☆ SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning

Wenhan Yu, Zhaoxi Zhang, Wang Chen, Guanqiang Qi, Weikang Li, Lei Sha, Deguo Xia, Jizhou Huang

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at the page level without explicitly annotating the evidence regions that support the answer, which limits both interpretability and the reliability of evaluation. To address this limitation, we introduce SciEGQA, a scientific document question answering and reasoning dataset with semantic evidence grounding, where supporting evidence is represented as semantically coherent document regions annotated with bounding boxes. SciEGQA consists of two components: a **human-annotated fine-grained benchmark** containing 1,623 high-quality question--answer pairs, and a **large-scale automatically constructed training set** with over 30K QA pairs generated through an automated data construction pipeline. Extensive experiments on a wide range of Vision-Language Models (VLMs) show that existing models still struggle with evidence localization and evidence-based question answering in scientific documents. Training on the proposed dataset significantly improves the scientific reasoning capabilities of VLMs. The project page is available at https://yuwenhan07.github.io/SciEGQA-project/.

comment: 8 pages, 4 figures, 3 tables

2026-03-29

Sound 6

☆ HumMusQA: A Human-written Music Understanding QA Benchmark Dataset

Benno Weck, Pablo Puentes, Andrea Poltronieri, Satyajeet Prabhu, Dmitry Bogdanov

The evaluation of music understanding in Large Audio-Language Models (LALMs) requires a rigorously defined benchmark that truly tests whether models can perceive and interpret music, a standard that current data methodologies frequently fail to meet. This paper introduces a meticulously structured approach to music evaluation, proposing a new dataset of 320 hand-written questions curated and validated by experts with musical training, arguing that such focused, manual curation is superior for probing complex audio comprehension. To demonstrate the use of the dataset, we benchmark six state-of-the-art LALMs and additionally test their robustness to uni-modal shortcuts.

comment: Dataset available at https://doi.org/10.5281/zenodo.18462523

☆ EvA: An Evidence-First Audio Understanding Paradigm for LALMs

Xinyuan Xie, Shunian Chen, Zhiheng Liu, Yuhao Zhang, Zhiqiang Lv, Liyin Liang, Benyou Wang

Large Audio Language Models (LALMs) still struggle in complex acoustic scenes because they often fail to preserve task-relevant acoustic evidence before reasoning begins. We call this failure the evidence bottleneck: state-of-the-art systems show larger deficits in evidence extraction than in downstream reasoning, suggesting that the main limitation lies in upstream perception rather than reasoning policy. To address this problem, we propose EvA (Evidence-First Audio), a dual-path architecture that combines Whisper and CED-Base through non-compressive, time-aligned fusion. EvA first aggregates intermediate CED layers to preserve multi-scale acoustic cues, then aligns the aggregated CED features to the Whisper timeline and adds the two streams without changing sequence length. We also build EvA-Perception, a large-scale open-source training set with about 54K event-ordered captions (150 h) and about 500K QA pairs. Under a unified zero-shot protocol, EvA achieves the best open-source Perception scores on MMAU, MMAR, and MMSU, and improves over Kimi-Audio-7B on all reported metrics, with the largest gains on perception-heavy splits. These results support the evidence-first hypothesis: stronger audio understanding depends on preserving acoustic evidence before reasoning.

☆ A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators

Lam Pham, Khoi Vu, Dat Tran, David Fischinger, Simon Freitter, Marcel Hasenbalg, Davide Antonutti, Alexander Schindler, Martin Boyer, Ian McLoughlin

In this paper, we analyze two main factors of Bonafide Resource (BR) or AI-based Generator (AG) which affect the performance and the generality of a Deepfake Speech Detection (DSD) model. To this end, we first propose a deep-learning based model, referred to as the baseline. Then, we conducted experiments on the baseline by which we indicate how Bonafide Resource (BR) and AI-based Generator (AG) factors affect the threshold score used to detect fake or bonafide input audio in the inference process. Given the experimental results, a dataset, which re-uses public Deepfake Speech Detection (DSD) datasets and shows a balance between Bonafide Resource (BR) or AI-based Generator (AG), is proposed. We then train various deep-learning based models on the proposed dataset and conduct cross-dataset evaluation on different benchmark datasets. The cross-dataset evaluation results prove that the balance of Bonafide Resources (BR) and AI-based Generators (AG) is the key factor to train and achieve a general Deepfake Speech Detection (DSD) model.

☆ Advancing Multi-Instrument Music Transcription: Results from the 2025 AMT Challenge NeurIPS 2025

Ojas Chaturvedi, Kayshav Bhardwaj, Tanay Gondil, Benjamin Shiue-Hal Chou, Kristen Yeon-Ji Yun, Yung-Hsiang Lu, Yujia Yan, Sungkyun Chang

This paper presents the results of the 2025 Automatic Music Transcription (AMT) Challenge, an online competition to benchmark progress in multi-instrument transcription. Eight teams submitted valid solutions; two outperformed the baseline MT3 model. The results highlight both advances in transcription accuracy and the remaining difficulties in handling polyphony and timbre variation. We conclude with directions for future challenges: broader genre coverage and stronger emphasis on instrument detection.

comment: 7 pages, 3 figures. Accepted to the AI for Music Workshop at NeurIPS 2025

☆ Investigation on the Robustness of Acoustic Foundation Models on Post Exercise Speech

Xiangyuan Xue, Yuyu Wang, Ruijie Yao, Xiaoyue Ni, Xiaofan Jiang, Jingping Nie

Automatic speech recognition (ASR) has been extensively studied on neutral and stationary speech, yet its robustness under post-exercise physiological shift remains underexplored. Compared with resting speech, post-exercise speech often contains micro-breaths, non-semantic pauses, unstable phonation, and repetitions caused by reduced breath support, making transcription more difficult. In this work, we benchmark acoustic foundation models on post-exercise speech under a unified evaluation protocol. We compare sequence-to-sequence models (Whisper and FunASR/Paraformer) and self-supervised encoders with CTC decoding (Wav2Vec2, HuBERT, and WavLM), under both off-the-shelf inference and post-exercise in-domain fine-tuning. Across the Static/Post-All benchmark, most models degrade on post-exercise speech, while FunASR shows the strongest baseline robustness at 14.57% WER and 8.21% CER on Post-All. Fine-tuning substantially improves several CTC-based models, whereas Whisper shows unstable adaptation. As an exploratory case study, we further stratify results by fluent and non-fluent speakers; although the non-fluent subset is small, it is consistently more challenging than the fluent subset. Overall, our findings show that post-exercise ASR robustness is strongly model-dependent, that in-domain adaptation can be highly effective but not uniformly stable, and that future post-exercise ASR studies should explicitly separate fluency-related effects from exercise-induced speech variation.

♻ ☆ Foundation Models for Bioacoustics -- a Comparative Review

Raphael Schwinger, Paria Vali Zadeh, Lukas Rauch, Mats Kurz, Tom Hauschild, Sam Lapp, Sven Tomforde

Automated bioacoustic analysis is essential for biodiversity monitoring and conservation, requiring advanced deep learning models that can adapt to diverse bioacoustic tasks. This article presents a comprehensive review of large-scale pretrained bioacoustic foundation models and systematically investigates their transferability across multiple bioacoustic classification tasks. We overview bioacoustic representation learning by analysing pretraining data sources and benchmarks. On this basis, we review bioacoustic foundation models, dissecting the models' training data, preprocessing, augmentations, architecture, and training paradigm. Additionally, we conduct an extensive empirical study of selected models on the BEANS and BirdSet benchmarks, evaluating generalisability under linear and attentive probing. Our experimental analysis reveals that Perch~2.0 achieves the highest BirdSet score (restricted evaluation) and the strongest linear probing result on BEANS, building on diverse multi-taxa supervised pretraining; that BirdMAE is the best model among probing-based strategies on BirdSet and second on BEANS after BEATs$_{NLM}$, the encoder of NatureLM-audio; that attentive probing is beneficial to extract the full performance of transformer-based models; and that general-purpose audio models trained with self-supervised learning on AudioSet outperform many specialised bird sound models on BEANS when evaluated with attentive probing. These findings provide valuable guidance for practitioners selecting appropriate models to adapt them to new bioacoustic classification tasks via probing.

comment: Preprint

Audio and Speech Processing 1

♻ ☆ Foundation Models for Bioacoustics -- a Comparative Review

Raphael Schwinger, Paria Vali Zadeh, Lukas Rauch, Mats Kurz, Tom Hauschild, Sam Lapp, Sven Tomforde

comment: Preprint

2026-03-28

Sound 6

☆ SHroom: A Python Framework for Ambisonics Room Acoustics Simulation and Binaural Rendering

Yhonatan Gayer

Spherical Harmonics ROOM), an open-source Python library for room acoustics simulation using Ambisonics, available at https://github.com/Yhonatangayer/shroom and installable via \texttt{pip install pyshroom}. \textbf{shroom} projects image-source contributions onto a Spherical Harmonics (SH) basis, yielding a composable pipeline for binaural decoding, spherical array simulation, and real-time head rotation. Benchmarked against \texttt{pyroomacoustics} with an $N=30$ reference, \textbf{shroom} with Magnitude Least Squares (MagLS) achieves perceptual transparency (2.02~dB Log Spectral Distance (LSD) at $N=5$, within the 1--2~dB Just Noticeable Difference (JND)) while its fixed-once decode amortises over multiple sources ($K=1$-to-$8$: slowdown narrows from $7\times$ to $3.1\times$). For dynamic head rotation, \textbf{shroom} applies a Wigner-D multiply at $<1$~ms/frame, making it the only architecturally viable real-time choice.

☆ TokenDance: Token-to-Token Music-to-Dance Generation with Bidirectional Mamba

Ziyue Yang, Kaixing Yang, Xulong Tang

Music-to-dance generation has broad applications in virtual reality, dance education, and digital character animation. However, the limited coverage of existing 3D dance datasets confines current models to a narrow subset of music styles and choreographic patterns, resulting in poor generalization to real-world music. Consequently, generated dances often become overly simplistic and repetitive, substantially degrading expressiveness and realism. To tackle this problem, we present TokenDance, a two-stage music-to-dance generation framework that explicitly addresses this limitation through dual-modality tokenization and efficient token-level generation. In the first stage, we discretize both dance and music using Finite Scalar Quantization, where dance motions are factorized into upper and lower-body components with kinematic-dynamic constraints, and music is decomposed into semantic and acoustic features with dedicated codebooks to capture choreography-specific structures. In the second stage, we introduce a Local-Global-Local token-to-token generator built on a Bidirectional Mamba backbone, enabling coherent motion synthesis, strong music-dance alignment, and efficient non-autoregressive inference. Extensive experiments demonstrate that TokenDance achieves overall state-of-the-art (SOTA) performance in both generation quality and inference speed, highlighting its effectiveness and practical value for real-world music-to-dance applications.

comment: CVPR2026 Workshop on HuMoGen

☆ Can pre-trained Deep Learning models predict groove ratings?

Axel Marmoret, Nicolas Farrugia, Jan Alexander Stupacher

This study explores the extent to which deep learning models can predict groove and its related perceptual dimensions directly from audio signals. We critically examine the effectiveness of seven state-of-the-art deep learning models in predicting groove ratings and responses to groove-related queries through the extraction of audio embeddings. Additionally, we compare these predictions with traditional handcrafted audio features. To better understand the underlying mechanics, we extend this methodology to analyze predictions based on source-separated instruments, thereby isolating the contributions of individual musical elements. Our analysis reveals a clear separation of groove characteristics driven by the underlying musical style of the tracks (funk, pop, and rock). These findings indicate that deep audio representations can successfully encode complex, style-dependent groove components that traditional features often miss. Ultimately, this work highlights the capacity of advanced deep learning models to capture the multifaceted concept of groove, demonstrating the strong potential of representation learning to advance predictive Music Information Retrieval methodologies.

comment: Submitted to the SMC 2026 conference. 3 figures and 2 tables

☆ Unsupervised Evaluation of Deep Audio Embeddings for Music Structure Analysis

Axel Marmoret

Music Structure Analysis (MSA) aims to uncover the high-level organization of musical pieces. State-of-the-art methods are often based on supervised deep learning, but these methods are bottlenecked by the need for heavily annotated data and inherent structural ambiguities. In this paper, we propose an unsupervised evaluation of nine open-source, generic pre-trained deep audio models, on MSA. For each model, we extract barwise embeddings and segment them using three unsupervised segmentation algorithms (Foote's checkerboard kernels, spectral clustering, and Correlation Block-Matching (CBM)), focusing exclusively on boundary retrieval. Our results demonstrate that modern, generic deep embeddings generally outperform traditional spectrogram-based baselines, but not systematically. Furthermore, our unsupervised boundary estimation methodology generally yields stronger performance than recent linear probing baselines. Among the evaluated techniques, the CBM algorithm consistently emerges as the most effective downstream segmentation method. Finally, we highlight the artificial inflation of standard evaluation metrics and advocate for the systematic adoption of ``trimming'', or even ``double trimming'' annotations to establish more rigorous MSA evaluation standards.

comment: Submitted to the SMC 2026 conference. 2 figures and 2 tables in the main document, 7 figures in Appendix

☆ Two-Stage Acoustic Adaptation with Gated Cross-Attention Adapters for LLM-Based Multi-Talker Speech Recognition

Hao Shi, Yuan Gao, Xugang Lu, Tatsuya Kawahara

Large Language Models (LLMs) are strong decoders for Serialized Output Training (SOT) in two-talker Automatic Speech Recognition (ASR), yet their performance degrades substantially in challenging conditions such as three-talker mixtures. A key limitation is that current systems inject acoustic evidence only through a projected prefix, which can be lossy and imperfectly aligned with the LLM input space, providing insufficient fine-grained grounding during decoding. Addressing this limitation is crucial for robust multi-talker ASR, especially in three-talker mixtures. This paper improves LLM-based multi-talker ASR by explicitly injecting talker-aware acoustic evidence into the decoder. We first revisit Connectionist Temporal Classification (CTC)-derived prefix prompting and compare three variants with increasing acoustic content. The CTC information is obtained using the serialized CTC proposed in our previous works. While acoustic-enriched prompts outperform the SOT-only baseline, prefix-only conditioning remains inadequate for three-talker mixtures. We therefore propose a lightweight gated residual cross-attention adapter and design a two-stage acoustic adaptation framework based on low-rank updates (LoRA). In Stage 1, we insert gated cross-attention adapters after the self-attention sub-layer to stably inject acoustic embeddings as external memory. In Stage 2, we refine both the cross-attention adapters and the pretrained LLM's self-attention projections using parameter-efficient LoRA, improving robustness for large backbones under limited data; the learned updates are merged into the base weights for inference. Experiments on Libri2Mix/Libri3Mix under clean and noisy conditions show consistent gains, with particularly large improvements in three-talker settings.

♻ ☆ Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation

Nghia Phan, Rong Jin, Gang Liu, Xiao Dong

Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire. At the same time, open-weight pre-trained models are currently more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use a pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on these pseudo-labels. In the second stage, the student is continually trained on ground-truth labels as they become available. To prevent catastrophic forgetting of the representations learned in the first stage, we apply selective knowledge distillation (KD) from the teacher as a regularizer. In our experiments, two models (BTC, 2E1D) were used as students. In stage 1, using only pseudo-labels, the BTC student achieves over 99% of the teacher's performance, while the 2E1D model achieves about 97% across seven standard mir_eval metrics. After a single training run for both students in stage 2, the resulting BTC student model surpasses the traditional supervised learning baseline by 2.5% and the original pre-trained teacher model by 1.1-3.2% across all metrics. The resulting 2E1D student model improves over the traditional supervised learning baseline by 2.67% on average and achieves almost the same performance as the teacher. Both cases show large gains on rare chord qualities.

comment: 8 pages, 6 figures, 3 tables

Audio and Speech Processing 2

☆ SHroom: A Python Framework for Ambisonics Room Acoustics Simulation and Binaural Rendering

Yhonatan Gayer

☆ Can pre-trained Deep Learning models predict groove ratings?

Axel Marmoret, Nicolas Farrugia, Jan Alexander Stupacher

comment: Submitted to the SMC 2026 conference. 3 figures and 2 tables

2026-03-27

Sound 21

☆ Diachronic Modeling of Tonal Coherence on the Tonnetz Across Classical and Popular Repertoires

Weilun Xu, Edward Hall, Martin Rohrmeier

How do different musical traditions achieve tonal coherence? Most computational measures to date have analysed tonal coherence in terms of a single dimension, whereas a multi-dimensional analyses have not been sufficiently explored. We propose a new model drawing on the concept of the Tonnetz -- we define two partially independent measures: \emph{tonal focus}, the concentration of pitch content near a tonal center; and \emph{tonal connection}, the degree to which pitch content reflects structured intervallic pathways back to that center. Analyzing over 2,800 pieces from Western classical and popular traditions, we find that these traditions occupy overlapping yet distinguishable regions of the two-dimensional space. Popular music shows higher tonal focus, while classical music exhibits higher tonal connection. Our complementary measures ground the differences between different tonal styles in quantitative evidence, and offer interpretable dimensions for computational music analysis and controllable generation.

☆ Algo Pärt: An Algorithmic Reconstruction of Arvo Pärt's Summa

Bas Cornelissen

Arvo Pärt is one of the most popular contemporary composers, known for his highly original tintinnabuli style. Works in this style are typically composed according to precise procedures and have even been described as algorithmic compositions. To understand how algorithmic Pärt's music exactly is, this paper presents an analysis by synthesis: it proposes an algorithm that almost completely reconstructs the score of Summa, his "most strictly constructed and most encrypted work," according to Pärt himself in 1994. The piece is analyzed and then formalized using so-called tintinnabuli processes. An implementation of the resulting algorithm generates a musical score matching Summa in over 93% of the notes. Due to interdependencies between the voices, only half of the mistakes (3.5%) need to be corrected to reproduce the original score faithfully. This study shows that Summa is a largely algorithmic composition and offers new perspectives on the music of Arvo Pärt.

comment: 21 pages, 15 figures

☆ Rhythmic segment analysis: Conceptualizing, visualizing, and measuring rhythmic data

Bas Cornelissen

This paper develops a framework for conceptualizing, visualizing, and measuring regularities in rhythmic data. I propose to think about rhythmic data in terms of interval segments: fixed-length groups of consecutive intervals, which can be decomposed into a duration and a pattern (the ratios between the intervals). This simple conceptual framework unifies three rhythmic visualization methods and yields a fourth: the pattern-duration plot. When paired with a cluster transition network, it intuitively reveals regularities in both synthetic and real-world rhythmic data. Moreover, the framework generalizes two common measures of rhythmic structure: rhythm ratios and the normalized pairwise variability index (nPVI). In particular, nPVI can be reconstructed as the average distance from isochrony, and I propose a more general measure of anisochrony to replace it. Finally, the novel concept of quantality may shed light on wider debates regarding small-integer-ratio rhythms.

comment: 15 pages, 7 figures

☆ Multilingual Stutter Event Detection for English, German, and Mandarin Speech

Felix Haas, Sebastian P. Bayerl

This paper presents a multi-label stuttering detection system trained on multi-corpus, multilingual data in English, German, and Mandarin.By leveraging annotated stuttering data from three languages and four corpora, the model captures language-independent characteristics of stuttering, enabling robust detection across linguistic contexts. Experimental results demonstrate that multilingual training achieves performance comparable to and, in some cases, even exceeds that of previous systems. These findings suggest that stuttering exhibits cross-linguistic consistency, which supports the development of language-agnostic detection systems. Our work demonstrates the feasibility and advantages of using multilingual data to improve generalizability and reliability in automated stuttering detection.

☆ Probabilistic Multilabel Graphical Modelling of Motif Transformations in Symbolic Music

Ron Taieb, Yoel Greenberg, Barak Sober

Motifs often recur in musical works in altered forms, preserving aspects of their identity while undergoing local variation. This paper investigates how such motivic transformations occur within their musical context in symbolic music. To support this analysis, we develop a probabilistic framework for modeling motivic transformations and apply it to Beethoven's piano sonatas by integrating multiple datasets that provide melodic, rhythmic, harmonic, and motivic information within a unified analytical representation. Motif transformations are represented as multilabel variables by comparing each motif instance to a designated reference occurrence within its local context, ensuring consistent labeling across transformation families. We introduce a multilabel Conditional Random Field to model how motif-level musical features influence the occurrence of transformations and how different transformation families tend to co-occur. Our goal is to provide an interpretable, distributional analysis of motivic transformation patterns, enabling the study of their structural relationships and stylistic variation. By linking computational modeling with music-theoretical interpretation, the proposed framework supports quantitative investigation of musical structure and complexity in symbolic corpora and may facilitate the analysis of broader compositional patterns and writing practices.

comment: 23 pages (21 pages main text), 2 figures. Submitted to Journal of New Music Research (Special Issue on Computational and Cognitive Musicology)

☆ AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

Hai-Son Nguyen-Le, Hung-Cuong Nguyen-Thanh, Nhien-An Le-Khac, Dinh-Thuc Nguyen, Hong-Hanh Nguyen-Le

The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused Self-Synthesis (AFSS), a method designed to mitigate this bias by generating pseudo-fake samples from real audio via two mechanisms: self-conversion and self-reconstruction. The core insight of AFSS lies in enforcing same-speaker constraints, ensuring that real and pseudo-fake samples share identical speaker identity and semantic content. This forces the detector to focus exclusively on generation artifacts rather than irrelevant confounding factors. Furthermore, we introduce a learnable reweighting loss to dynamically emphasize synthetic samples during training. Extensive experiments across 7 datasets demonstrate that AFSS achieves state-of-the-art performance with an average EER of 5.45\%, including a significant reduction to 1.23\% on WaveFake and 2.70\% on In-the-Wild, all while eliminating the dependency on pre-collected fake datasets. Our code is publicly available at https://github.com/NguyenLeHaiSonGit/AFSS.

comment: Accepted at International Joint Conference on Neural Networks 2026

☆ CA-TCN: A Causal-Anticausal Temporal Convolutional Network for Direct Auditory Attention Decoding

Iñigo García-Ugarte, Rubén Eguinoa, Ricardo San Martín, Daniel Paternain, Carmen Vidaurre

A promising approach for steering auditory attention in complex listening environments relies on Auditory Attention Decoding (AAD), which aim to identify the attended speech stream in a multiple speaker scenario from neural recordings. Entrainment-based AAD approaches, typically assume access to clean speech sources and electroencephalography (EEG) signals to exploit low-frequency correlations between the neural response and the attended stimulus. In this study, we propose CA-TCN, a Causal-Anticausal Temporal Convolutional Network that directly classifies the attended speaker. The proposed architecture integrates several best practices from convolutional neural networks in sequence processing tasks. Importantly, it explicitly aligns auditory stimuli and neural responses by employing separate causal and anticausal convolutions respectively, with distinct receptive fields operating in opposite temporal directions. Experimental results, obtained through comparisons with three baseline AAD models, demonstrated that CA-TCN consistently improved decoding accuracy across datasets and decision windows, with gains ranging from 0.5% to 3.2% for subject-independent models and from 0.8% to 2.9% for subject-specific models compared with the next best-performing model, AADNet. Moreover, these improvements were statistically significant in four of the six evaluated settings when comparing Minimum Expected Switch Duration distributions. Beyond accuracy, the model demonstrated spatial robustness across different conditions, as the EEG spatial filters exhibited stable patterns across datasets. Overall, this work introduces an accurate and unified AAD model that outperforms existing methods while considering practical benefits for online processing scenarios. These findings contribute to advancing the state of AAD and its applicability in real-world systems.

☆ LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling

Xiaoyu Fan, Huizhi Xie, Wei Zou, Yunzhang Chen

Large language model (LLM)-based text-to-speech (TTS) systems achieve remarkable naturalness via autoregressive (AR) decoding, but require N sequential steps to generate N speech tokens. We present LLaDA-TTS, which replaces the AR LLM with a masked diffusion model that completes generation in a fixed number of parallel steps, decoupling inference latency from sequence length. Remarkably, using only 50 hours of fine-tuning data, we successfully transfer a pretrained AR checkpoint to the masked diffusion paradigm via bidirectional attention. At 64 steps, LLaDA-TTS achieves 0.98% CER (zh) and 1.96% WER (en) on Seed-TTS-Eval, matching the original CosyVoice 3 baseline performance while delivering a 2x LLM-stage speedup--a notable acceleration achieved despite the absence of KV cache, an optimization the AR baseline heavily relies on. Beyond acceleration, the bidirectional architecture naturally enables zero-shot speech editing--including word-level insertion, deletion, and substitution--without any additional training. Theoretically, we prove that AR-pretrained weights are near-optimal for bidirectional masked prediction under the locality property of acoustic tokens, explaining this rapid convergence. This general method modifies only the attention mask and objective, applying seamlessly to any LLM-based AR TTS system. Code and audio samples will be available at https://deft-piroshki-b652b5.netlify.app/.

comment: 11 pages, 6 figures, 2 tables

☆ A Power-Weighted Noncentral Complex Gaussian Distribution

Toru Nakashika

The complex Gaussian distribution has been widely used as a fundamental spectral and noise model in signal processing and communication. However, its Gaussian structure often limits its ability to represent the diverse amplitude characteristics observed in individual source signals. On the other hand, many existing non-Gaussian amplitude distributions derived from hyperspherical models achieve good empirical fit due to their power-law structures, while they do not explicitly account for the complex-plane geometry inherent in complex-valued observations. In this paper, we propose a new probabilistic model for complex-valued random variables, which can be interpreted as a power-weighted noncentral complex Gaussian distribution. Unlike conventional hyperspherical amplitude models, the proposed model is formulated directly on the complex plane and preserves the geometric structure of complex-valued observations while retaining a higher-dimensional interpretation. The model introduces a nonlinear phase diffusion through a single shape parameter, enabling continuous control of the distributional geometry from arc-shaped diffusion along the phase direction to concentration of probability mass toward the origin. We formulate the proposed distribution and analyze the statistical properties of the induced amplitude distribution. The derived amplitude and power distributions provide a unified framework encompassing several widely used distributions in signal modeling, including the Rice, Nakagami, and gamma distributions. Experimental results on speech power spectra demonstrate that the proposed model consistently outperforms conventional distributions in terms of log-likelihood.

☆ Cinematic Audio Source Separation Using Visual Cues

Kang Zhang, Suyeon Lee, Arda Senocak, Joon Son Chung

Cinematic Audio Source Separation (CASS) aims to decompose mixed film audio into speech, music, and sound effects, enabling applications like dubbing and remastering. Existing CASS approaches are audio-only, overlooking the inherent audio-visual nature of films, where sounds often align with visual cues. We present the first framework for audio-visual CASS (AV-CASS), leveraging visual context to enhance separation quality. Our method formulates CASS as a conditional generative modeling problem using conditional flow matching, enabling multimodal audio source separation. To address the lack of cinematic datasets with isolated sound tracks, we introduce a training data synthesis pipeline that pairs in-the-wild audio and video streams (e.g., facial videos for speech, scene videos for effects) and design a dedicated visual encoder for this dual-stream setup. Trained entirely on synthetic data, our model generalizes effectively to real-world cinematic content and achieves strong performance on synthetic, real-world, and audio-only CASS benchmarks. Code and demo are available at \url{https://cass-flowmatching.github.io}.

comment: CVPR 2026. Project page: https://cass-flowmatching.github.io

☆ A Human-Inspired Decoupled Architecture for Efficient Audio Representation Learning

Harunori Kawano, Takeshi Sasaki

While self-supervised learning (SSL) has revolutionized audio representation, the excessive parameterization and quadratic computational cost of standard Transformers limit their deployment on resource-constrained devices. To address this bottleneck, we propose HEAR (Human-inspired Efficient Audio Representation), a novel decoupled architecture. Inspired by the human cognitive ability to isolate local acoustic features from global context, HEAR splits the processing pipeline into two dedicated modules: an Acoustic Model for local feature extraction and a Task Model for global semantic integration. Coupled with an Acoustic Tokenizer trained via knowledge distillation, our approach enables robust Masked Audio Modeling (MAM). Extensive experiments demonstrate that HEAR requires only 15M parameters and 9.47 GFLOPs for inference, operating at a fraction of the computational cost of conventional foundation models (which typically require 85M-94M parameters). Despite this high efficiency, HEAR achieves highly competitive performance across diverse audio classification benchmarks. The code and pre-trained models are available at https://github.com/HarunoriKawano/HEAR

♻ ☆ Acoustic Overspecification in Electronic Dance Music Taxonomy

Weilun Xu, Tianhao Dai, Oscar Goudet, Xiaoxuan Wang

Electronic Dance Music (EDM) classification typically relies on industry-defined taxonomies, with current supervised approaches naturally assuming the validity of prescribed subgenre labels. However, whether these commercial distinctions reflect genuine acoustic differences remains largely unexplored. In this paper, we propose an unsupervised approach to discover the natural acoustic structure of EDM independent of commercial labels. To address the historical lack of EDM-specific feature design in MIR, we systematically construct a tailored, interpretable acoustic feature space capturing the genre's defining production techniques, spectral textures, and layered rhythmic patterns. To ensure our findings reflect inherent acoustic structure rather than feature engineering artifacts, we validate our clustering against state-of-the-art pre-trained audio embeddings (MERT and CLAP). Across both our bespoke feature space and the pre-trained embeddings, clustering consistently identifies 20 or fewer natural acoustic families -- suggesting current commercial EDM taxonomy is acoustically overspecified by nearly one-half.

♻ ☆ DiffAU: Diffusion-Based Ambisonics Upscaling

Amit Milstein, Nir Shlezinger, Boaz Rafaely

Spatial audio enhances immersion by reproducing 3D sound fields, with Ambisonics offering a scalable format for this purpose. While first-order Ambisonics (FOA) notably facilitates hardware-efficient acquisition and storage of sound fields as compared to high-order Ambisonics (HOA), its low spatial resolution limits realism, highlighting the need for Ambisonics upscaling (AU) as an approach for increasing the order of Ambisonics signals. In this work we propose DiffAU, a cascaded AU method that leverages recent developments in diffusion models combined with novel adaptation to spatial audio to generate 3rd order Ambisonics from FOA. By learning data distributions, DiffAU provides a principled approach that rapidly and reliably reproduces HOA in various settings. Experiments in anechoic conditions with multiple speakers, show strong objective and perceptual performance.

♻ ☆ Does Audio Deepfake Detection Generalize?

Nicolas M. Müller, Pavel Czempin, Franziska Dieckmann, Adam Froghyar, Konstantin Böttinger

Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake detection a much-needed area of research. While researchers have presented various techniques for detecting audio spoofs, it is often unclear exactly why these architectures are successful: Preprocessing steps, hyperparameter settings, and the degree of fine-tuning are not consistent across related work. Which factors contribute to success, and which are accidental? In this work, we address this problem: We systematize audio spoofing detection by re-implementing and uniformly evaluating architectures from related work. We identify overarching features for successful audio deepfake detection, such as using cqtspec or logspec features instead of melspec features, which improves performance by 37% EER on average, all other factors constant. Additionally, we evaluate generalization capabilities: We collect and publish a new dataset consisting of 37.9 hours of found audio recordings of celebrities and politicians, of which 17.2 hours are deepfakes. We find that related work performs poorly on such real-world data (performance degradation of up to one thousand percent). This may suggest that the community has tailored its solutions too closely to the prevailing ASVSpoof benchmark and that deepfakes are much harder to detect outside the lab than previously thought.

comment: Interspeech 2022

♻ ☆ Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs

Sara Papi, Javier Garcia Gilabert, Zachary Hopton, Vilém Zouhar, Carlos Escolano, Gerard I. Gállego, Jorge Iranzo-Sánchez, Ahrii Kim, Dominik Macháček, Patricia Schmidtova, Maike Züfle

As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which directly process spoken language and enable speech-to-text translation (ST) and other downstream tasks, bypassing traditional transcription-based pipelines. Whether this integration improves ST quality over established cascaded architectures, however, remains an open question. We present Hearing to Translate, the first comprehensive test suite rigorously benchmarking 6 state-of-the-art SpeechLLMs against 16 strong direct and cascade systems that couple leading speech foundation models (SFM), with multilingual LLMs. Our analysis spans 16 benchmarks, 13 language pairs, and 9 challenging conditions, including disfluent, noisy, and long-form speech. Across this extensive evaluation, we find that cascaded systems remain the most reliable solution overall, but most recent SpeechLLMs can match or even outperform cascades in various settings while SFMs lag behind both, highlighting that integrating an LLM, either within the model or in a pipeline, is essential for high-quality speech translation.

comment: Project available at https://github.com/sarapapi/hearing2translate

♻ ☆ Hear What Matters! Text-conditioned Selective Video-to-Audio Generation

Junwon Lee, Juhan Nam, Jiyoung Lee

This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability is especially crucial in multimedia production, where audio tracks are handled individually for each sound source for precise editing, mixing, and creative control. We propose SELVA, a novel text-conditioned V2A model that treats the text prompt as an explicit selector to distinctly extract prompt-relevant sound-source visual features from the video encoder. To suppress text-irrelevant activations with efficient video encoder finetuning, the proposed supplementary tokens promote cross-attention to yield robust semantic and temporal grounding. SELVA further employs an autonomous video-mixing scheme in a self-supervised manner to overcome the lack of mono audio track supervision. We evaluate SELVA on VGG-MONOAUDIO, a curated benchmark of clean single-source videos for such a task. Extensive experiments and ablations consistently verify its effectiveness across audio quality, semantic alignment, and temporal synchronization.

comment: accepted to CVPR 2026

♻ ☆ TW-Sound580K: A Regional Audio-Text Dataset with Verification-Guided Curation for Localized Audio-Language Modeling

Hao-Hui Xie, Ho-Lam Chung, Yi-Cheng Lin, Ke-Han Lu, Wenze Ren, Xie Chen, Hung-yi Lee

Large Audio-Language Models (LALMs) typically struggle with localized dialectal prosody due to the scarcity of specialized corpora. We present TW-Sound580K, a Taiwanese audio-text instruction dataset developed through a Verify-Generate-Critique (VGC) protocol. This pipeline leverages Dual-ASR validation to filter 522K raw clips, subsequently expanding them into 580,000 high-fidelity instruction pairs using a teacher model. The dataset's utility is demonstrated through Tai-LALM, which fine-tunes a DeSTA 2.5-Audio-initialized backbone and incorporates a dynamic Dual-ASR Arbitration strategy to optimize transcription selection during inference. On the TAU Benchmark, Tai-LALM reaches 49.1% accuracy, marking a 6.5% absolute improvement over the zero-shot baseline (42.6% with ASR text conditioning). This confirms that integrating regional corpora with rigorous curation and dynamic arbitration significantly enhances LALM performance on localized speech.

comment: The authors have decided to withdraw this submission as the work is no longer intended for public dissemination at this time

♻ ☆ Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction ICASSP 2026

Téo Guichoux, Théodor Lemerle, Shivam Mehta, Jonas Beskow, Gustav Eje Henter, Laure Soulier, Catherine Pelachaud, Nicolas Obin

Human communication is multimodal, with speech and gestures tightly coupled, yet most computational methods for generating speech and gestures synthesize them sequentially, weakening synchrony and prosody alignment. We introduce Gelina, a unified framework that jointly synthesizes speech and co-speech gestures from text using interleaved token sequences in a discrete autoregressive backbone, with modality-specific decoders. Gelina supports multi-speaker and multi-style cloning and enables gesture-only synthesis from speech inputs. Subjective and objective evaluations demonstrate competitive speech quality and improved gesture generation over unimodal baselines.

comment: Paper accepted at ICASSP 2026, 5 pages

♻ ☆ Joint Learning Global-Local Speaker Classification to Enhance End-to-End Speaker Diarization and Recognition

Yuhang Dai, Haopeng Lin, Jiale Qian, Ruiqi Yan, Hao Meng, Hanke Xie, Hanlin Wen, Shunshun Yin, Ming Tao, Xie Chen, Lei Xie, Xinsheng Wang

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in end-to-end speaker diarization and recognition. However, their speaker discriminability remains limited due to the scarcity of large-scale conversational data and the absence of explicit speaker representation optimization. To address this, we propose GLSC-SDR, a paradigm that jointly trains speaker classification with diarization and recognition. We further introduce a Global-Local Speaker Classification strategy, which uses clustered speakers as global labels and re-encoded intra-cluster speakers as local labels. This hierarchical design enhances fine-grained speaker discrimination while preserving semantic transcription accuracy. Experiments on AliMeeting, AISHELL-4, and AMI-SDM demonstrate that GLSC-SDR achieves competitive or superior performance compared to simulation-based and multi-encoder approaches, without relying on large-scale real conversational data.

comment: 5 pages, 2 figures, 2 tables

♻ ☆ DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization

Ngoc-Son Nguyen, Thanh V. T. Tran, Jeongsoo Choi, Hieu-Nghia Huynh-Nguyen, Truong-Son Hy, Van Nguyen

Video dubbing has broad applications in filmmaking, multimedia creation, and assistive speech technology. Existing approaches either train directly on limited dubbing datasets or adopt a two-stage pipeline that adapts pre-trained text-to-speech (TTS) models, which often struggle to produce expressive prosody, rich acoustic characteristics, and precise synchronization. To address these issues, we propose DiFlowDubber with a novel two-stage training framework that effectively transfers knowledge from a pre-trained TTS model to video-driven dubbing, with a discrete flow matching generative backbone. Specifically, we design a FaPro module that captures global prosody and stylistic cues from facial expressions and leverages this information to guide the modeling of subsequent speech attributes. To ensure precise speech-lip synchronization, we introduce a Synchronizer module that bridges the modality gap among text, video, and speech, thereby improving cross-modal alignment and generating speech that is temporally synchronized with lip movements. Experiments on two primary benchmark datasets demonstrate that DiFlowDubber outperforms previous methods across multiple metrics.

comment: Accepted at CVPR 2026 Findings

♻ ☆ Acoustic Imaging for UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwanth Bethi, Saeed Afshar

We introduce a U-net model for 360° acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth & elevation) into regions of active sound presence. Using delay-and-sum (DAS) beamforming on a custom 24-microphone array, we generate signals aligned with drone GPS telemetry to create binary supervision masks. A modified U-Net, trained on frequency-domain representations of these maps, learns to identify spatially distributed source regions while addressing class imbalance via the Tversky loss. Because the network operates on beamformed energy maps, the approach is inherently array-independent and can adapt to different microphone configurations and can be transferred to different microphone configurations with minimal adaptation. The segmentation outputs are post-processed by computing centroids over activated regions, enabling robust DoA estimates. Our dataset includes real-world open-field recordings of a DJI Air 3 drone, synchronized with 360° video and flight logs across multiple dates and locations. Experimental results show that U-net generalizes across environments, providing improved angular precision, offering a new paradigm for dense spatial audio understanding beyond traditional Sound Source Localization (SSL). We additionally validate the same beamforming-plus-segmentation formulation on the DCASE 2019 TAU Spatial Sound Events benchmark, showing that the approach generalizes beyond drone acoustics to multiclass Sound Event Localization and Detection (SELD) scenarios.

Audio and Speech Processing 13

☆ PHONOS: PHOnetic Neutralization for Online Streaming Applications

Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah, Ricardo Gutierrez-Osuna

Speaker anonymization (SA) systems modify timbre while leaving regional or non-native accents intact, which is problematic because accents can narrow the anonymity set. To address this issue, we present PHONOS, a streaming module for real-time SA that neutralizes non-native accent to sound native-like. Our approach pre-generates golden speaker utterances that preserve source timbre and rhythm but replace foreign segmentals with native ones using silence-aware DTW alignment and zero-shot voice conversion. These utterances supervise a causal accent translator that maps non-native content tokens to native equivalents with at most 40ms look-ahead, trained using joint cross-entropy and CTC losses. Our evaluations show an 81% reduction in non-native accent confidence, with listening-test ratings consistent with this shift, and reduced speaker linkability as accent-neutralized utterances move away from the original speaker in embedding space while having latency under 241 ms on single GPU.

comment: The paper is submitted to Interspeech 2026 and currently under review

☆ Rhythmic segment analysis: Conceptualizing, visualizing, and measuring rhythmic data

Bas Cornelissen

comment: 15 pages, 7 figures

☆ Multilingual Stutter Event Detection for English, German, and Mandarin Speech

Felix Haas, Sebastian P. Bayerl

☆ AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

Hai-Son Nguyen-Le, Hung-Cuong Nguyen-Thanh, Nhien-An Le-Khac, Dinh-Thuc Nguyen, Hong-Hanh Nguyen-Le

comment: Accepted at International Joint Conference on Neural Networks 2026

☆ A Power-Weighted Noncentral Complex Gaussian Distribution

Toru Nakashika

☆ Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR

Shashi Kumar, Esaú Villatoro-Tello, Sergio Burdisso, Kadri Hacioglu, Thibault Bañeras-Roux, Hasindri Watawana, Dairazalia Sanchez-Cortes, Srikanth Madikeri, Petr Motlicek, Andreas Stolcke

Standard LLM-based speech recognition systems typically process utterances in isolation, limiting their ability to leverage conversational context. In this work, we study whether multimodal context from prior turns improves LLM-based ASR and how to represent that context efficiently. We find that, after supervised multi-turn training, conversational context mainly helps with the recognition of contextual entities. However, conditioning on raw context is expensive because the prior-turn audio token sequence grows rapidly with conversation length. To address this, we propose Abstract Compression, which replaces the audio portion of prior turns with a fixed number of learned latent tokens while retaining corresponding transcripts explicitly. On both in-domain and out-of-domain test sets, the compressed model recovers part of the gains of raw-context conditioning with a smaller prior-turn audio footprint. We also provide targeted analyses of the compression setup and its trade-offs.

comment: 11 pages

☆ Dual-branch Graph Domain Adaptation for Cross-scenario Multi-modal Emotion Recognition

Yuntao Shou, Jun Zhou, Tao Meng, Wei Ai, Keqin Li

Multimodal Emotion Recognition in Conversations (MERC) aims to predict speakers' emotional states in multi-turn dialogues through text, audio, and visual cues. In real-world settings, conversation scenarios differ significantly in speakers, topics, styles, and noise levels. Existing MERC methods generally neglect these cross-scenario variations, limiting their ability to transfer models trained on a source domain to unseen target domains. To address this issue, we propose a Dual-branch Graph Domain Adaptation framework (DGDA) for multimodal emotion recognition under cross-scenario conditions. We first construct an emotion interaction graph to characterize complex emotional dependencies among utterances. A dual-branch encoder, consisting of a hypergraph neural network (HGNN) and a path neural network (PathNN), is then designed to explicitly model multivariate relationships and implicitly capture global dependencies. To enable out-of-domain generalization, a domain adversarial discriminator is introduced to learn invariant representations across domains. Furthermore, a regularization loss is incorporated to suppress the negative influence of noisy labels. To the best of our knowledge, DGDA is the first MERC framework that jointly addresses domain shift and label noise. Theoretical analysis provides tighter generalization bounds, and extensive experiments on IEMOCAP and MELD demonstrate that DGDA consistently outperforms strong baselines and better adapts to cross-scenario conversations. Our code is available at https://github.com/Xudmm1239439/DGDA-Net.

comment: 29 pages

☆ Cinematic Audio Source Separation Using Visual Cues

Kang Zhang, Suyeon Lee, Arda Senocak, Joon Son Chung

comment: CVPR 2026. Project page: https://cass-flowmatching.github.io

♻ ☆ DiffAU: Diffusion-Based Ambisonics Upscaling

Amit Milstein, Nir Shlezinger, Boaz Rafaely

♻ ☆ Does Audio Deepfake Detection Generalize?

Nicolas M. Müller, Pavel Czempin, Franziska Dieckmann, Adam Froghyar, Konstantin Böttinger

comment: Interspeech 2022

♻ ☆ Hear What Matters! Text-conditioned Selective Video-to-Audio Generation

Junwon Lee, Juhan Nam, Jiyoung Lee

comment: accepted to CVPR 2026

♻ ☆ Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction ICASSP 2026

Téo Guichoux, Théodor Lemerle, Shivam Mehta, Jonas Beskow, Gustav Eje Henter, Laure Soulier, Catherine Pelachaud, Nicolas Obin

comment: Paper accepted at ICASSP 2026, 5 pages

♻ ☆ Acoustic Imaging for UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwanth Bethi, Saeed Afshar

2026-03-26

Sound 13

☆ CLAR: CIF-Localized Alignment for Retrieval-Augmented Speech LLM-Based Contextual ASR

Shangkun Huang, Huan Shen, Wei Zou, Yunzhang Chen

Speech LLM-based ASR often struggles with named entities and long-tail words due to strong internal language-model priors. Retrieval-augmented biasing can help, but its effectiveness depends on accurate hotword localization in full-utterance speech under weak supervision. We propose CLAR, a dual-encoder speech-text retriever that uses Continuous Integrate-and-Fire (CIF) to learn monotonic token-level alignments without timestamps. With length-aware localized matching, CLAR anchors short-entity acoustic cues and reduces representation dilution and attention drift. The retriever is trained with a multi-granularity objective combining global and local segment-level contrastive losses and a CIF quantity constraint. At inference, top-ranked hotwords are injected as contextual prompts for the Speech LLM, improving recognition without shallow fusion. Experiments show that CLAR significantly improves hotword retrieval and reduces both CER and B-WER against strong contextual ASR baselines.

comment: Submitted to Interspeech 2026

☆ CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluation

Huan Shen, Yingao Wang, Shangkun Huang, Wei Zou, Yunzhang Chen

comment: Submitted to Interspeech 2026

☆ Joint Learning Global-Local Speaker Classification to Enhance End-to-End Speaker Diarization and Recognition

Yuhang Dai, Haopeng Lin, Jiale Qian, Ruiqi Yan, Hao Meng, Hanke Xie, Hanlin Wen, Shunshun Yin, Ming Tao, Xie Chen, Lei Xie, Xinsheng Wang

comment: 5 pages, 2 figures, 2 tables

☆ SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment

Sahibzada Adil Shahzad, Ammarah Hashmi, Junichi Yamagishi, Yusuke Yasuda, Yu Tsao, Chia-Wen Lin, Yan-Tsung Peng, Hsin-Min Wang

Multimodal deepfakes can exhibit subtle visual artifacts and cross-modal inconsistencies, which remain challenging to detect, especially when detectors are trained primarily on curated synthetic forgeries. Such synthetic dependence can introduce dataset and generator bias, limiting scalability and robustness to unseen manipulations. We propose SAVe, a self-supervised audio-visual deepfake detection framework that learns entirely on authentic videos. SAVe generates on-the-fly, identity-preserving, region-aware self-blended pseudo-manipulations to emulate tampering artifacts, enabling the model to learn complementary visual cues across multiple facial granularities. To capture cross-modal evidence, SAVe also models lip-speech synchronization via an audio-visual alignment component that detects temporal misalignment patterns characteristic of audio-visual forgeries. Experiments on FakeAVCeleb and AV-LipSync-TIMIT demonstrate competitive in-domain performance and strong cross-dataset generalization, highlighting self-supervised learning as a scalable paradigm for multimodal deepfake detection.

☆ Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods

Xuanru Zhou, Yiwen Shao, Wei-Cheng Tseng, Dong Yu

Current audio pre-training seeks to learn unified representations for broad audio understanding tasks, but it remains fragmented and is fundamentally bottlenecked by its reliance on weak, noisy, and scale-limited labels. Drawing lessons from vision's foundational pre-training blueprint, we argue that the audio field must first establish its own large-scale, strong supervision framework. We introduce a new data-centric pipeline that leverages a high-fidelity captioner to create SOTA-quality captions and the first Unified Tag System (UTS) that bridges speech, music, and environmental sounds. We then conduct a systematic comparative study of different pre-training objectives on these strong source data. Our experiments suggest that data quality and coverage are the primary drivers of performance, while the choice of objective dictates downstream task specialization.

comment: Accepted to CVPR 2026

♻ ☆ Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation

Nghia Phan, Rong Jin, Gang Liu, Xiao Dong

Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire. At the same time, open-weight pre-trained models are currently more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use a pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on these pseudo-labels. In the second stage, the student is continually trained on ground-truth labels as they become available. To prevent catastrophic forgetting of the representations learned in the first stage, we apply selective knowledge distillation (KD) from the teacher as a regularizer. In our experiments, two models (BTC, 2E1D) were used as students. In stage 1, using only pseudo-labels, the BTC student achieves over 98% of the teacher's performance, while the 2E1D model achieves about 96% across seven standard mir_eval metrics. After a single training run for both students in stage 2, the resulting BTC student model surpasses the traditional supervised learning baseline by 2.5% and the original pre-trained teacher model by 1.55% on average across all metrics. The resulting 2E1D student model improves over the traditional supervised learning baseline by 2.67% on average and achieves almost the same performance as the teacher. Both cases show large gains on rare chord qualities.

comment: 9 pages, 6 figures, 3 tables

♻ ☆ ASVspoof 5: Evaluation of Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech

Xin Wang, Héctor Delgado, Nicholas Evans, Xuechen Liu, Tomi Kinnunen, Hemlata Tak, Kong Aik Lee, Ivan Kukanov, Md Sahidullah, Massimiliano Todisco, Junichi Yamagishi

ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake detection solutions. A significant change from previous challenge editions is a new crowdsourced database collected from a substantially greater number of speakers under diverse recording conditions, and a mix of cutting-edge and legacy generative speech technology. With the new database described elsewhere, we provide in this paper an overview of the ASVspoof 5 challenge results for the submissions of 53 participating teams. While many solutions perform well, performance degrades under adversarial attacks and the application of neural encoding/compression schemes. Together with a review of post-challenge results, we also report a study of calibration in addition to other principal challenges and outline a road-map for the future of ASVspoof.

comment: This work has been submitted to the IEEE TASLP for possible publication

♻ ☆ U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model

Louis Bahrman, Marius Rodrigues, Mathieu Fontaine, Gaël Richard

This paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to virtually unsupervised, relying solely on reverberant signals and an acoustic model for training. Most of the existing deep learning approaches typically require paired dry and reverberant data, which are difficult to obtain in practice. We develop instead a sequential learning strategy motivated by a maximum-likelihood formulation of the dereverberation problem, wherein acoustic parameters and dry signals are estimated from reverberant inputs using deep neural networks, guided by a reverberation matching loss. Our most data-efficient variant requires only 100 reverberation-parameter-labeled samples to outperform an unsupervised baseline, demonstrating the effectiveness and practicality of the proposed method in low-resource scenarios.

♻ ☆ Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level Dropin & Neuroplasticity Mechanisms

Yupei Li, Shuaijie Shao, Manuel Milling, Björn Schuller

Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements with the introduction of large models (LMs) like Wav2Vec. The success of large language models (LLMs) further demonstrates the benefits of scaling model parameters, but also highlights one bottleneck where performance gains are constrained by parameter counts. Simply stacking additional layers, as done in current LLMs, is computationally expensive and requires full retraining. Furthermore, existing low-rank adaptation methods are primarily applied to attention-based architectures, which limits their scope. Inspired by the neuronal plasticity observed in mammalian brains, we propose novel algorithms, dropin and further plasticity, that dynamically adjust the number of neurons in certain layers to flexibly modulate model parameters. We evaluate these algorithms on multiple architectures, including ResNet, Gated Recurrent Neural Networks, and Wav2Vec. Experimental results using the widely recognised ASVSpoof2019 LA, PA, and FakeorReal dataset demonstrate consistent improvements in computational efficiency with the dropin approach and a maximum of around 39% and 66% relative reduction in Equal Error Rate with the dropin and plasticity approach among these dataset, respectively. The code and supplementary material are available at Github link.

comment: Accepted at IJCNN 2026

♻ ☆ DashengTokenizer: One layer is enough for unified audio understanding and generation

Heinrich Dinkel, Xingwei Sun, Gang Li, Jiahao Mei, Yadong Niu, Jizhong Liu, Xiyang Li, Yifan Liao, Jiahao Zhou, Junbo Zhang, Jian Luan

This paper introduces DashengTokenizer, a continuous audio tokenizer engineered for joint use in both understanding and generation tasks. Unlike conventional approaches, which train acoustic tokenizers and subsequently integrate frozen semantic knowledge, our method inverts this paradigm: we leverage frozen semantic features and inject acoustic information. In linear evaluation across 22 diverse tasks, our method outperforms previous audio codec and audio encoder baselines by a significant margin while maintaining competitive audio reconstruction quality. Notably, we demonstrate that this acoustic injection improves performance for tasks such as speech emotion recognition, music understanding, and acoustic scene classification. We further evaluate the tokenizer's generative performance on text-to-audio (TTA), text-to-music (TTM), and speech enhancement (SE). Our approach surpasses standard variational autoencoder (VAE)-based methods on TTA and TTM tasks, while its effectiveness on SE underscores its capabilities as a general-purpose audio encoder. Finally, our results challenge the prevailing assumption that VAE-based architectures are a prerequisite for audio synthesis. Checkpoints are available at https://huggingface.co/mispeech/dashengtokenizer.

comment: Added ACAVCaps reference

♻ ☆ MiDashengLM: Efficient Audio Understanding with General Audio Captions ICASSP 2026

Heinrich Dinkel, Gang Li, Jizhong Liu, Jian Luan, Yadong Niu, Xingwei Sun, Tianzi Wang, Qiyang Xiao, Junbo Zhang, Jiahao Zhou

Current approaches for large audio language models (LALMs) often rely on closed data sources or proprietary models, limiting their generalization and accessibility. This paper introduces MiDashengLM, a novel open audio-language model designed for efficient and comprehensive audio understanding through the use of general audio captions using our novel ACAVCaps training dataset. MiDashengLM exclusively relies on publicly available pretraining and supervised fine-tuning (SFT) datasets, ensuring full transparency and reproducibility. At its core, MiDashengLM integrates Dasheng, an open-source audio encoder, specifically engineered to process diverse auditory information effectively. Unlike previous works primarily focused on Automatic Speech Recognition (ASR) based audio-text alignment, our strategy centers on general audio captions, fusing speech, sound and music information into one textual representation, enabling a holistic textual representation of complex audio scenes. Lastly, MiDashengLM provides an up to 4x speedup in terms of time-to-first-token (TTFT) and up to 20x higher throughput than comparable models. Checkpoints are available online at https://huggingface.co/mispeech/midashenglm-7b and https://github.com/xiaomi-research/dasheng-lm.

comment: Added ACAVCaps reference (ICASSP 2026)

♻ ☆ A Lightweight Two-Branch Architecture for Multi-instrument Transcription via Note-Level Contrastive Clustering

Ruigang Li, Yongxu Zhu

Existing multi-timbre transcription models struggle with generalization beyond pre-trained instruments, rigid source-count constraints, and high computational demands that hinder deployment on low-resource devices. We address these limitations with a lightweight model that extends a timbre-agnostic transcription backbone with a dedicated timbre encoder and performs deep clustering at the note level, enabling joint transcription and dynamic separation of arbitrary instruments given a specified number of instrument classes. Practical optimizations including spectral normalization, dilated convolutions, and contrastive clustering further improve efficiency and robustness. Despite its small size and fast inference, the model achieves competitive performance with heavier baselines in terms of transcription accuracy and separation quality, and shows promising generalization ability, making it highly suitable for real-world deployment in practical and resource-constrained settings.

♻ ☆ Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwant Bethy, Saeed Afshar

We introduce a U-net model for 360° acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth and elevation) into regions of active sound presence. Using delay-and-sum (DAS) beamforming on a custom 24-microphone array, we generate signals aligned with drone GPS telemetry to create binary supervision masks. A modified U-Net, trained on frequency-domain representations of these maps, learns to identify spatially distributed source regions while addressing class imbalance via the Tversky loss. Because the network operates on beamformed energy maps, the approach is inherently array-independent and can adapt to different microphone configurations without retraining from scratch. The segmentation outputs are post-processed by computing centroids over activated regions, enabling robust DoA estimates. Our dataset includes real-world open-field recordings of a DJI Air 3 drone, synchronized with 360° video and flight logs across multiple dates and locations. Experimental results show that U-net generalizes across environments, providing improved angular precision, offering a new paradigm for dense spatial audio understanding beyond traditional Sound Source Localization (SSL).

Audio and Speech Processing 7

☆ AdaLTM: Adaptive Layer-wise Task Vector Merging for Categorical Speech Emotion Recognition with ASR Knowledge Integration

Chia-Yu Lee, Huang-Cheng Chou, Tzu-Quan Lin, Yuanchao Li, Ya-Tse Wu, Shrikanth Narayanan, Chi-Chun Lee

Integrating Automatic Speech Recognition (ASR) into Speech Emotion Recognition (SER) enhances modeling by providing linguistic context. However, conventional feature fusion faces performance bottlenecks, and multi-task learning often suffers from optimization conflicts. While task vectors and model merging have addressed such conflicts in NLP and CV, their potential in speech tasks remains largely unexplored. In this work, we propose an Adaptive Layer-wise Task Vector Merging (AdaLTM) framework based on WavLM-Large. Instead of joint optimization, we extract task vectors from in-domain ASR and SER models fine-tuned on emotion datasets. These vectors are integrated into a frozen base model using layer-wise learnable coefficients. This strategy enables depth-aware balancing of linguistic and paralinguistic knowledge across transformer layers without gradient interference. Experiments on the MSP-Podcast demonstrate that the proposed approach effectively mitigates conflicts between ASR and SER.

comment: Submitted to Interspeech 2026

☆ UPV_RIR_DB: A Structured Room Impulse Response Database with Hierarchical Metadata and Acoustic Indicators

Jesús García-Gamborino, Laura Fuster, Daniel de la Prida, Luis A. Azpicueta-Ruiz, Gema Piñero

This paper presents UPV_RIR_DB, a structured database of measured room impulse responses (RIRs) designed to provide acoustic data with explicit spatial metadata and traceable acquisition parameters. The dataset currently contains 166 multichannel RIR files measured in three rooms of the Universitat Politècnica de València (UPV). Each multichannel RIR file contains impulse responses for multiple source-receiver pairs, with each pair covering a 25 cm2 area - the typical size of a personal sound zone. Considering the number of sources and receiver channels associated with each microphone modality, the database contains a total of 18,976 single impulse responses. A hierarchical organization is adopted in which directory structure and metadata jointly describe the measurement context. Each room includes a metadata file containing acquisition parameters, hardware description, spatial coordinates of zones and microphones, and acoustic indicators such as reverberation time. A central index links each RIR file with its experimental context, ensuring traceability and enabling reproducible analysis. The resulting database provides a consistent framework for storing, inspecting, and reusing real RIR measurements while preserving compatibility with both MATLAB- and JSON-based workflows. The UPV_RIR_DB dataset is publicly available through the open repository Zenodo.

comment: RIR Database available at ZENODO

☆ Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods

Xuanru Zhou, Yiwen Shao, Wei-Cheng Tseng, Dong Yu

comment: Accepted to CVPR 2026

♻ ☆ U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model

Louis Bahrman, Marius Rodrigues, Mathieu Fontaine, Gaël Richard

♻ ☆ DashengTokenizer: One layer is enough for unified audio understanding and generation

Heinrich Dinkel, Xingwei Sun, Gang Li, Jiahao Mei, Yadong Niu, Jizhong Liu, Xiyang Li, Yifan Liao, Jiahao Zhou, Junbo Zhang, Jian Luan

comment: Added ACAVCaps reference

♻ ☆ MiDashengLM: Efficient Audio Understanding with General Audio Captions ICASSP 2026

Heinrich Dinkel, Gang Li, Jizhong Liu, Jian Luan, Yadong Niu, Xingwei Sun, Tianzi Wang, Qiyang Xiao, Junbo Zhang, Jiahao Zhou

comment: Added ACAVCaps reference (ICASSP 2026)

♻ ☆ Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwant Bethy, Saeed Afshar

We introduce a U-net model for 360° acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth and elevation) into regions of active sound presence. Using delay-and-sum (DAS) beamforming on a custom 24-microphone array, we generate signals aligned with drone GPS telemetry to create binary supervision masks. A modified U-Net, trained on frequency-domain representations of these maps, learns to identify spatially distributed source regions while addressing class imbalance via the Tversky loss. Because the network operates on beamformed energy maps, the approach is inherently array-independent and can adapt to different microphone configurations without retraining from scratch. The segmentation outputs are post-processed by computing centroids over activated regions, enabling robust DoA estimates. Our dataset includes real-world open-field recordings of a DJI Air 3 drone, synchronized with 360° video and flight logs across multiple dates and locations. Experimental results show that U-net generalizes across environments, providing improved angular precision, offering a new paradigm for dense spatial audio understanding beyond traditional Sound Source Localization (SSL).

Computer Vision and Pattern Recognition 151

☆ ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Yawen Luo, Xiaoyu Shi, Junhao Zhuang, Yutian Chen, Quande Liu, Xintao Wang, Pengfei Wan, Tianfan Xue

Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables interactive storytelling and efficient on-the-fly frame generation. By reformulating the task as next-shot generation conditioned on historical context, ShotStream allows users to dynamically instruct ongoing narratives via streaming prompts. We achieve this by first fine-tuning a text-to-video model into a bidirectional next-shot generator, which is then distilled into a causal student via Distribution Matching Distillation. To overcome the challenges of inter-shot consistency and error accumulation inherent in autoregressive generation, we introduce two key innovations. First, a dual-cache memory mechanism preserves visual coherence: a global context cache retains conditional frames for inter-shot consistency, while a local context cache holds generated frames within the current shot for intra-shot consistency. And a RoPE discontinuity indicator is employed to explicitly distinguish the two caches to eliminate ambiguity. Second, to mitigate error accumulation, we propose a two-stage distillation strategy. This begins with intra-shot self-forcing conditioned on ground-truth historical shots and progressively extends to inter-shot self-forcing using self-generated histories, effectively bridging the train-test gap. Extensive experiments demonstrate that ShotStream generates coherent multi-shot videos with sub-second latency, achieving 16 FPS on a single GPU. It matches or exceeds the quality of slower bidirectional models, paving the way for real-time interactive storytelling. Training and inference code, as well as the models, are available on our

comment: Project Page: https://luo0207.github.io/ShotStream/ Code: https://github.com/KlingAIResearch/ShotStream

☆ Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

Yixing Lao, Xuyang Bai, Xiaoyang Wu, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao

Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity from rendering resolution. This approach enables high-fidelity 4K novel view synthesis without per-scene optimization, a capability previously out of reach for feed-forward methods, all while using significantly fewer Gaussian primitives. Project page: https://yxlao.github.io/lgtm/

☆ MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models

Bocheng Zou, Mu Cai, Mark Stanley, Dingfu Lu, Yong Jae Lee

Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recent advances allow these models to handle varying input sizes during training, inference typically remains restricted to a single, fixed scale. This prevalent single-scale paradigm overlooks a fundamental property of visual perception: varying resolutions offer complementary inductive biases, where low-resolution views excel at global semantic recognition and high-resolution views are essential for fine-grained refinement. In this work, we propose Multi-Resolution Fusion (MuRF), a simple yet universally effective strategy to harness this synergy at inference time. Instead of relying on a single view, MuRF constructs a unified representation by processing an image at multiple resolutions through a frozen VFM and fusing the resulting features. The universality of MuRF is its most compelling attribute. It is not tied to a specific architecture, serving instead as a fundamental, training-free enhancement to visual representation. We empirically validate this by applying MuRF to a broad spectrum of critical computer vision tasks across multiple distinct VFM families - primarily DINOv2, but also demonstrating successful generalization to contrastive models like SigLIP2.

☆ RefAlign: Representation Alignment for Reference-to-Video Generation

Lei Wang, YuXin Song, Ge Wu, Haocheng Feng, Hang Zhou, Jingdong Wang, Yaxing Wang, jian Yang

Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on. In practice, existing R2V methods typically introduce additional high-level semantic or cross-modal features alongside the VAE latent representation of the reference image and jointly feed them into the diffusion Transformer (DiT). These auxiliary representations provide semantic guidance and act as implicit alignment signals, which can partially alleviate pixel-level information leakage in the VAE latent space. However, they may still struggle to address copy--paste artifacts and multi-subject confusion caused by modality mismatch across heterogeneous encoder features. In this paper, we propose RefAlign, a representation alignment framework that explicitly aligns DiT reference-branch features to the semantic space of a visual foundation model (VFM). The core of RefAlign is a reference alignment loss that pulls the reference features and VFM features of the same subject closer to improve identity consistency, while pushing apart the corresponding features of different subjects to enhance semantic discriminability. This simple yet effective strategy is applied only during training, incurring no inference-time overhead, and achieves a better balance between text controllability and reference fidelity. Extensive experiments on the OpenS2V-Eval benchmark demonstrate that RefAlign outperforms current state-of-the-art methods in TotalScore, validating the effectiveness of explicit reference alignment for R2V tasks.

comment: 17 pages, 11 figures

☆ Vega: Learning to Drive with Natural Language Instructions

Sicheng Zuo, Yuxuan Li, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu

comment: Code is available at https://github.com/zuosc19/Vega

☆ Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving

Zehao Wang, Huaide Jiang, Shuaiwu Dong, Yuping Wang, Hang Qiu, Jiachen Li

Human driving behavior is inherently personal, which is shaped by long-term habits and influenced by short-term intentions. Individuals differ in how they accelerate, brake, merge, yield, and overtake across diverse situations. However, existing end-to-end autonomous driving systems either optimize for generic objectives or rely on fixed driving modes, lacking the ability to adapt to individual preferences or interpret natural language intent. To address this gap, we propose Drive My Way (DMW), a personalized Vision-Language-Action (VLA) driving framework that aligns with users' long-term driving habits and adapts to real-time user instructions. DMW learns a user embedding from our personalized driving dataset collected across multiple real drivers and conditions the policy on this embedding during planning, while natural language instructions provide additional short-term guidance. Closed-loop evaluation on the Bench2Drive benchmark demonstrates that DMW improves style instruction adaptation, and user studies show that its generated behaviors are recognizable as each driver's own style, highlighting personalization as a key capability for human-centered autonomous driving. Our data and code are available at https://dmw-cvpr.github.io/.

comment: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026); Project website: https://dmw-cvpr.github.io/

☆ PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow

Xincheng Shuai, Song Tang, Yutong Huang, Henghui Ding, Dacheng Tao

Graphic design is a creative and innovative process that plays a crucial role in applications such as e-commerce and advertising. However, developing an automated design system that can faithfully translate user intentions into editable design files remains an open challenge. Although recent studies have leveraged powerful text-to-image models and MLLMs to assist graphic design, they typically simplify professional workflows, resulting in limited flexibility and intuitiveness. To address these limitations, we propose PSDesigner, an automated graphic design system that emulates the creative workflow of human designers. Building upon multiple specialized components, PSDesigner collects theme-related assets based on user instructions, and autonomously infers and executes tool calls to manipulate design files, such as integrating new assets or refining inferior elements. To endow the system with strong tool-use capabilities, we construct a design dataset, CreativePSD, which contains a large amount of high-quality PSD design files annotated with operation traces across a wide range of design scenarios and artistic styles, enabling models to learn expert design procedures. Extensive experiments demonstrate that PSDesigner outperforms existing methods across diverse graphic design tasks, empowering non-specialists to conveniently create production-quality designs.

comment: CVPR 2026, Project Page: https://henghuiding.com/PSDesigner/

☆ MegaFlow: Zero-Shot Large Displacement Optical Flow

Dingxi Zhang, Fangjinhua Wang, Marc Pollefeys, Haofei Xu

Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement and zero-shot generalization scenarios. To overcome this, we introduce MegaFlow, a simple yet powerful model for zero-shot large displacement optical flow. Rather than relying on highly complex, task-specific architectural designs, MegaFlow adapts powerful pre-trained vision priors to produce temporally consistent motion fields. In particular, we formulate flow estimation as a global matching problem by leveraging pre-trained global Vision Transformer features, which naturally capture large displacements. This is followed by a few lightweight iterative refinements to further improve the sub-pixel accuracy. Extensive experiments demonstrate that MegaFlow achieves state-of-the-art zero-shot performance across multiple optical flow benchmarks. Moreover, our model also delivers highly competitive zero-shot performance on long-range point tracking benchmarks, demonstrating its robust transferability and suggesting a unified paradigm for generalizable motion estimation. Our project page is at: https://kristen-z.github.io/projects/megaflow.

comment: Project Page: https://kristen-z.github.io/projects/megaflow Code: https://github.com/cvg/megaflow

☆ How good was my shot? Quantifying Player Skill Level in Table Tennis

Akihiro Kubota, Tomoya Hasegawa, Ryo Kawahara, Ko Nishino

Gauging an individual's skill level is crucial, as it inherently shapes their behavior. Quantifying skill, however, is challenging because it is latent to the observed actions. To explore skill understanding in human behavior, we focus on dyadic sports -- specifically table tennis -- where skill manifests not just in complex movements, but in the subtle nuances of execution conditioned on game context. Our key idea is to learn a generative model of each player's tactical racket strokes and jointly embed them in a common latent space that encodes individual characteristics, including those pertaining to skill levels. By training these player models on a large-scale dataset of 3D-reconstructed professional matches and conditioning them on comprehensive game context -- including player positioning and opponent behaviors -- the models capture individual tactical identities within their latent space. We probe this learned player space and find that it reflects distinct play styles and attributes that collectively represent skill. By training a simple relative ranking network on these embeddings, we demonstrate that both relative and absolute skill predictions can be achieved. These results demonstrate that the learned player space effectively quantifies skill levels, providing a foundation for automated skill assessment in complex, interactive behaviors.

☆ Unleashing Guidance Without Classifiers for Human-Object Interaction Animation

Ziyin Wang, Sirui Xu, Chuan Guo, Bing Zhou, Jiangshan Gong, Jian Wang, Yu-Xiong Wang, Liang-Yan Gui

Generating realistic human-object interaction (HOI) animations remains challenging because it requires jointly modeling dynamic human actions and diverse object geometries. Prior diffusion-based approaches often rely on hand-crafted contact priors or human-imposed kinematic constraints to improve contact quality. We propose LIGHT, a data-driven alternative in which guidance emerges from the denoising pace itself, reducing dependence on manually designed priors. Building on diffusion forcing, we factor the representation into modality-specific components and assign individualized noise levels with asynchronous denoising schedules. In this paradigm, cleaner components guide noisier ones through cross-attention, yielding guidance without auxiliary classifiers. We find that this data-driven guidance is inherently contact-aware, and can be enhanced when training is augmented with a broad spectrum of synthetic object geometries, encouraging invariance of contact semantics to geometric diversity. Extensive experiments show that pace-induced guidance more effectively mirrors the benefits of contact priors than conventional classifier-free guidance, while achieving higher contact fidelity, more realistic HOI generation, and stronger generalization to unseen objects and tasks.

comment: Project Page: http://ziyinwang1.github.io/LIGHT

☆ SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding

Jiwook Han, Geo Ahn, Youngrae Kim, Jinwoo Choi

Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-grained temporal understanding, making task-specific fine-tuning indispensable. This fine-tuning causes models to memorize dataset-specific shortcuts rather than faithfully grounding in the actual visual content, leading to poor Out-of-Domain (OOD) generalization. Object-centric learning offers a promising remedy by decomposing scenes into entity-level representations, but existing approaches require re-running the entire multi-stage training pipeline from scratch. We propose SlotVTG, a framework that steers MLLMs toward object-centric, input-grounded visual reasoning at minimal cost. SlotVTG introduces a lightweight slot adapter that decomposes visual tokens into abstract slots via slot attention and reconstructs the original sequence, where objectness priors from a self-supervised vision model encourage semantically coherent slot formation. Cross-domain evaluation on standard VTG benchmarks demonstrates that our approach significantly improves OOD robustness while maintaining competitive In-Domain (ID) performance with minimal overhead.

comment: Accepted to GRAIL-V workshop at CVPR 2026

☆ BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation

Yan Li, Zezi Zeng, Ziwei Zhou, Xin Gao, Muzhao Tian, Yifan Yang, Mingxi Cheng, Qi Dai, Yuqing Yang, Lili Qiu, Zhendong Wang, Zhengyuan Yang, Xue Yang, Lijuan Wang, Ji Li, Chong Luo

Recent advances in image generation models have expanded their applications beyond aesthetic imagery toward practical visual content creation. However, existing benchmarks mainly focus on natural image synthesis and fail to systematically evaluate models under the structured and multi-constraint requirements of real-world commercial design tasks. In this work, we introduce BizGenEval, a systematic benchmark for commercial visual content generation. The benchmark spans five representative document types: slides, charts, webpages, posters, and scientific figures, and evaluates four key capability dimensions: text rendering, layout control, attribute binding, and knowledge-based reasoning, forming 20 diverse evaluation tasks. BizGenEval contains 400 carefully curated prompts and 8000 human-verified checklist questions to rigorously assess whether generated images satisfy complex visual and semantic constraints. We conduct large-scale benchmarking on 26 popular image generation systems, including state-of-the-art commercial APIs and leading open-source models. The results reveal substantial capability gaps between current generative models and the requirements of professional visual content creation. We hope BizGenEval serves as a standardized benchmark for real-world commercial visual content generation.

☆ PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

Xiaofeng Mao, Shaohao Rui, Kaining Ying, Bo Zheng, Chuanhao Li, Mingmin Chi, Kaipeng Zhang

Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that efficiently manages the generation history through a novel three-partition KV-cache strategy. Specifically, we categorize the historical context into three distinct types: (1) Sink tokens, which preserve early anchor frames at full resolution to maintain global semantics; (2) Mid tokens, which achieve a massive spatiotemporal compression (32x token reduction) via a dual-branch network fusing progressive 3D convolutions with low-resolution VAE re-encoding; and (3) Recent tokens, kept at full resolution to ensure local temporal coherence. To strictly bound the memory footprint without sacrificing quality, we introduce a dynamic top-$k$ context selection mechanism for the mid tokens, coupled with a continuous Temporal RoPE Adjustment that seamlessly re-aligns position gaps caused by dropped tokens with negligible overhead. Empowered by this principled hierarchical context compression, PackForcing can generate coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU. It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal extrapolation (5s to 120s), operating effectively either zero-shot or trained on merely 5-second clips. Extensive results on VBench demonstrate state-of-the-art temporal consistency (26.07) and dynamic degree (56.25), proving that short-video supervision is sufficient for high-quality, long-video synthesis. https://github.com/ShandaAI/PackForcing

☆ PixelSmile: Toward Fine-Grained Facial Expression Editing

Jiabin Hua, Hengyuan Xu, Aojie Li, Wei Cheng, Gang Yu, Xingjun Ma, Yu-Gang Jiang

Fine-grained facial expression editing has long been limited by intrinsic semantic overlap. To address this, we construct the Flex Facial Expression (FFE) dataset with continuous affective annotations and establish FFE-Bench to evaluate structural confusion, editing accuracy, linear controllability, and the trade-off between expression editing and identity preservation. We propose PixelSmile, a diffusion framework that disentangles expression semantics via fully symmetric joint training. PixelSmile combines intensity supervision with contrastive learning to produce stronger and more distinguishable expressions, achieving precise and stable linear expression control through textual latent interpolation. Extensive experiments demonstrate that PixelSmile achieves superior disentanglement and robust identity preservation, confirming its effectiveness for continuous, controllable, and fine-grained expression editing, while naturally supporting smooth expression blending.

comment: 21 Pages; Project Page: https://ammmob.github.io/PixelSmile/; Code: https://github.com/Ammmob/PixelSmile

☆ AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation

Chen Si, Yulin Liu, Bo Ai, Jianwen Xie, Rolandos Alexandros Potamias, Chuanxia Zheng, Hao Su

We present AnyHand, a large-scale synthetic dataset designed to advance the state of the art in 3D hand pose estimation from both RGB-only and RGB-D inputs. While recent works with foundation approaches have shown that an increase in the quantity and diversity of training data can markedly improve performance and robustness in hand pose estimation, existing real-world-collected datasets on this task are limited in coverage, and prior synthetic datasets rarely provide occlusions, arm details, and aligned depth together at scale. To address this bottleneck, our AnyHand contains 2.5M single-hand and 4.1M hand-object interaction RGB-D images, with rich geometric annotations. In the RGB-only setting, we show that extending the original training sets of existing baselines with AnyHand yields significant gains on multiple benchmarks (FreiHAND and HO-3D), even when keeping the architecture and training scheme fixed. More impressively, the model trained with AnyHand shows stronger generalization to the out-of-domain HO-Cap dataset, without any fine-tuning. We also contribute a lightweight depth fusion module that can be easily integrated into existing RGB-based models. Trained with AnyHand, the resulting RGB-D model achieves superior performance on the HO-3D benchmark, showing the benefits of depth integration and the effectiveness of our synthetic data.

☆ No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models

Hai X. Pham, David T. Hoffmann, Ricardo Guerrero, Brais Martinez

Contrastive vision-language (V&L) models remain a popular choice for various applications. However, several limitations have emerged, most notably the limited ability of V&L models to learn compositional representations. Prior methods often addressed this limitation by generating custom training data to obtain hard negative samples. Hard negatives have been shown to improve performance on compositionality tasks, but are often specific to a single benchmark, do not generalize, and can cause substantial degradation of basic V&L capabilities such as zero-shot or retrieval performance, rendering them impractical. In this work we follow a different approach. We identify two root causes that limit compositionality performance of V&Ls: 1) Long training captions do not require a compositional representation; and 2) The final global pooling in the text and image encoders lead to a complete loss of the necessary information to learn binding in the first place. As a remedy, we propose two simple solutions: 1) We obtain short concept centric caption parts using standard NLP software and align those with the image; and 2) We introduce a parameter-free cross-modal attention-pooling to obtain concept centric visual embeddings from the image encoder. With these two changes and simple auxiliary contrastive losses, we obtain SOTA performance on standard compositionality benchmarks, while maintaining or improving strong zero-shot and retrieval capabilities. This is achieved without increasing inference cost. We release the code for this work at https://github.com/SamsungLabs/concept_centric_clip.

comment: Accepted at CVPR 2026

☆ R-C2: Cycle-Consistent Reinforcement Learning Improves Multimodal Reasoning

Zirui Zhang, Haoyu Dong, Kexin Pei, Chengzhi Mao

Robust perception and reasoning require consistency across sensory modalities. Yet current multimodal models often violate this principle, yielding contradictory predictions for visual and textual representations of the same concept. Rather than masking these failures with standard voting mechanisms, which can amplify systematic biases, we show that cross-modal inconsistency provides a rich and natural signal for learning. We introduce RC2, a reinforcement learning framework that resolves internal conflicts by enforcing cross-modal cycle consistency. By requiring a model to perform backward inference, switch modalities, and reliably reconstruct the answer through forward inference, we obtain a dense, label-free reward. This cyclic constraint encourages the model to align its internal representations autonomously. Optimizing for this structure mitigates modality-specific errors and improves reasoning accuracy by up to 7.6 points. Our results suggest that advanced reasoning emerges not only from scaling data, but also from enforcing a structurally consistent understanding of the world.

☆ Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Kaijin Chen, Dingkang Liang, Xin Zhou, Yikang Ding, Xiaoqiang Liu, Pengfei Wan, Xiang Bai

Video world models have shown immense potential in simulating the physical world, yet existing memory mechanisms primarily treat environments as static canvases. When dynamic subjects hide out of sight and later re-emerge, current methods often struggle, leading to frozen, distorted, or vanishing subjects. To address this, we introduce Hybrid Memory, a novel paradigm requiring models to simultaneously act as precise archivists for static backgrounds and vigilant trackers for dynamic subjects, ensuring motion continuity during out-of-view intervals. To facilitate research in this direction, we construct HM-World, the first large-scale video dataset dedicated to hybrid memory. It features 59K high-fidelity clips with decoupled camera and subject trajectories, encompassing 17 diverse scenes, 49 distinct subjects, and meticulously designed exit-entry events to rigorously evaluate hybrid coherence. Furthermore, we propose HyDRA, a specialized memory architecture that compresses memory into tokens and utilizes a spatiotemporal relevance-driven retrieval mechanism. By selectively attending to relevant motion cues, HyDRA effectively preserves the identity and motion of hidden subjects. Extensive experiments on HM-World demonstrate that our method significantly outperforms state-of-the-art approaches in both dynamic subject consistency and overall generation quality.

☆ Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs

Vishal Narnaware, Animesh Gupta, Kevin Zhai, Zhenyi Wang, Mubarak Shah

Multimodal Diffusion Large Language Models (MDLLMs) achieve high-concurrency generation through parallel masked decoding, yet the architectures remain prone to multimodal hallucinations. This structural vulnerability stems from an algorithmic flaw: the decoder ranks candidate tokens based on textual likelihood without verifying localized visual support. We establish that this language-only ranking induces an objective mismatch, where language probability mass acts as a misspecified proxy for the intended multimodal task. Consequently, we reinterpret hallucination as a localized optimization error, a phenomenon where the decoder exploits language shortcuts to maximize a proxy score at the expense of visual grounding. To address this objective mismatch, we introduce VISAGE, a training-free decoding framework that calibrates the objective at inference time. VISAGE estimates the proxy discrepancy by quantifying the spatial entropy of cross-attention distributions. By enforcing a localization consensus across attention heads, the method penalizes spatially uniform distributions and re-ranks token commitments to favor visually grounded outcomes. We provide an analytical stability guarantee establishing that VISAGE maintains a bounded objective loss under estimation error. Evaluations across hallucination-sensitive and general-purpose benchmarks demonstrate the robustness of the framework, yielding relative gains of 8.59% on MMMU-val and 7.75% on HallusionBench.

☆ TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance

Quynh Phung, Long Mai, Cusuh Ham, Feng Liu, Jia-Bin Huang, Aniruddha Mahapatra

We study object motion path editing in videos, where the goal is to alter a target object's trajectory while preserving the original scene content. Unlike prior video editing methods that primarily manipulate appearance or rely on point-track-based trajectory control, which is often challenging for users to provide during inference, especially in videos with camera motion, we offer a practical, easy-to-use approach to controllable object-centric motion editing. We present Trace, a framework that enables users to design the desired trajectory in a single anchor frame and then synthesizes a temporally consistent edited video. Our approach addresses this task with a two-stage pipeline: a cross-view motion transformation module that maps first-frame path design to frame-aligned box trajectories under camera motion, and a motion-conditioned video re-synthesis module that follows these trajectories to regenerate the object while preserving the remaining content of the input video. Experiments on diverse real-world videos show that our method produces more coherent, realistic, and controllable motion edits than recent image-to-video and video-to-video methods.

comment: webpage: https://trace-motion.github.io/

☆ Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training

Jinbo Xing, Zeyinzi Jiang, Yuxiang Tuo, Chaojie Mao, Xiaotang Gai, Xi Chen, Jingfeng Zhang, Yulin Pan, Zhen Han, Jie Xiao, Keyu Yan, Chenwei Xie, Chongyang Zhong, Kai Zhu, Tong Shen, Lianghua Huang, Yu Liu, Yujiu Yang

Recent unified models have made unprecedented progress in both understanding and generation. However, while most of them accept multi-modal inputs, they typically produce only single-modality outputs. This challenge of producing interleaved content is mainly due to training data scarcity and the difficulty of modeling long-range cross-modal context. To address this issue, we decompose interleaved generation into textual planning and visual consistency modeling, and introduce a framework consisting of a planner and a visualizer. The planner produces dense textual descriptions for visual content, while the visualizer synthesizes images accordingly. Under this guidance, we construct large-scale textual-proxy interleaved data (where visual content is represented in text) to train the planner, and curate reference-guided image data to train the visualizer. These designs give rise to Wan-Weaver, which exhibits emergent interleaved generation ability with long-range textual coherence and visual consistency. Meanwhile, the integration of diverse understanding and generation data into planner training enables Wan-Weaver to achieve robust task reasoning and generation proficiency. To assess the model's capability in interleaved generation, we further construct a benchmark that spans a wide range of use cases across multiple dimensions. Extensive experiments demonstrate that, even without access to any real interleaved data, Wan-Weaver achieves superior performance over existing methods.

comment: CVPR 2026 Camera-ready, Webpage: https://doubiiu.github.io/projects/WanWeaver

☆ LEMMA: Laplacian pyramids for Efficient Marine SeMAntic Segmentation

Ishaan Gakhar, Laven Srivastava, Sankarshanaa Sagaram, Aditya Kasliwal, Ujjwal Verma

Semantic segmentation in marine environments is crucial for the autonomous navigation of unmanned surface vessels (USVs) and coastal Earth Observation events such as oil spills. However, existing methods, often relying on deep CNNs and transformer-based architectures, face challenges in deployment due to their high computational costs and resource-intensive nature. These limitations hinder the practicality of real-time, low-cost applications in real-world marine settings. To address this, we propose LEMMA, a lightweight semantic segmentation model designed specifically for accurate remote sensing segmentation under resource constraints. The proposed architecture leverages Laplacian Pyramids to enhance edge recognition, a critical component for effective feature extraction in complex marine environments for disaster response, environmental surveillance, and coastal monitoring. By integrating edge information early in the feature extraction process, LEMMA eliminates the need for computationally expensive feature map computations in deeper network layers, drastically reducing model size, complexity and inference time. LEMMA demonstrates state-of-the-art performance across datasets captured from diverse platforms while reducing trainable parameters and computational requirements by up to 71x, GFLOPs by up to 88.5\%, and inference time by up to 84.65\%, as compared to existing models. Experimental results highlight its effectiveness and real-world applicability, including 93.42\% IoU on the Oil Spill dataset and 98.97\% mIoU on Mastr1325.

comment: Accepted at the MaCVi Workshop, CVPR 2026

☆ Just Zoom In: Cross-View Geo-Localization via Autoregressive Zooming

Yunus Talha Erzurumlu, Jiyong Kwag, Alper Yilmaz

Cross-view geo-localization (CVGL) estimates a camera's location by matching a street-view image to geo-referenced overhead imagery, enabling GPS-denied localization and navigation. Existing methods almost universally formulate CVGL as an image-retrieval problem in a contrastively trained embedding space. This ties performance to large batches and hard negative mining, and it ignores both the geometric structure of maps and the coverage mismatch between street-view and overhead imagery. In particular, salient landmarks visible from the street view can fall outside a fixed satellite crop, making retrieval targets ambiguous and limiting explicit spatial inference over the map. We propose Just Zoom In, an alternative formulation that performs CVGL via autoregressive zooming over a city-scale overhead map. Starting from a coarse satellite view, the model takes a short sequence of zoom-in decisions to select a terminal satellite cell at a target resolution, without contrastive losses or hard negative mining. We further introduce a realistic benchmark with crowd-sourced street views and high-resolution satellite imagery that reflects real capture conditions. On this benchmark, Just Zoom In achieves state-of-the-art performance, improving Recall@1 within 50 m by 5.5% and Recall@1 within 100 m by 9.6% over the strongest contrastive-retrieval baseline. These results demonstrate the effectiveness of sequential coarse-to-fine spatial reasoning for cross-view geo-localization.

comment: 18 pages, 6 figures

☆ Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning

Jai Bardhan, Patrik Drozdik, Josef Sivic, Vladimir Petrik

Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks that are difficult to model with traditional physics engines. However, these models are optimized for short-term prediction and break down when deployed autoregressively: each predicted clip feeds back as context for the next, causing errors to compound and visual quality to rapidly degrade. We address this through the following contributions. First, we introduce a reinforcement learning (RL) post-training scheme that trains the world model on its own autoregressive rollouts rather than on ground-truth histories. We achieve this by adapting a recent contrastive RL objective for diffusion models to our setting and show that its convergence guarantees carry over exactly. Second, we design a training protocol that generates and compares multiple candidate variable-length futures from the same rollout state, reinforcing higher-fidelity predictions over lower-fidelity ones. Third, we develop efficient, multi-view visual fidelity rewards that combine complementary perceptual metrics across camera views and are aggregated at the clip level for dense, low-variance training signal. Fourth, we show that our approach establishes a new state-of-the-art for rollout fidelity on the DROID dataset, outperforming the strongest baseline on all metrics (e.g., LPIPS reduced by 14% on external cameras, SSIM improved by 9.1% on the wrist camera), winning 98% of paired comparisons, and achieving an 80% preference rate in a blind human study.

comment: 34 pages, 11 figures, 12 tables

☆ Can Users Specify Driving Speed? Bench2Drive-Speed: Benchmark and Baselines for Desired-Speed Conditioned Autonomous Driving

Yuqian Shao, Xiaosong Jia, Langechuan Liu, Junchi Yan

End-to-end autonomous driving (E2E-AD) has achieved remarkable progress. However, one practical and useful function has been long overlooked: users may wish to customize the desired speed of the policy or specify whether to allow the autonomous vehicle to overtake. To bridge this gap, we present Bench2Drive-Speed, a benchmark with metrics, dataset, and baselines for desired-speed conditioned autonomous driving. We introduce explicit inputs of users' desired target-speed and overtake/follow instructions to driving policy models. We design quantitative metrics, including Speed-Adherence Score and Overtake Score, to measure how faithfully policies follow user specifications, while remaining compatible with standard autonomous driving metrics. To enable training of speed-conditioned policies, one approach is to collect expert demonstrations that strictly follow speed requirements, an expensive and unscalable process in the real world. An alternative is to adapt existing regular driving data by treating the speed observed in future frames as the target speed for training. To investigate this, we construct CustomizedSpeedDataset, composed of 2,100 clips annotated with experts demonstrations, enabling systematic investigation of supervision strategies. Our experiments show that, under proper re-annotation, models trained on regular driving data perform comparably to on expert demonstrations, suggesting that speed supervision can be introduced without additional complex real-world data collection. Furthermore, we find that while target-speed following can be achieved without degrading regular driving performance, executing overtaking commands remains challenging due to the inherent difficulty of interactive behaviors. All code, datasets and baselines are available at https://github.com/Thinklab-SJTU/Bench2Drive-Speed

comment: Project page: https://thinklab-sjtu.github.io/Bench2Drive-Speed/

☆ Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance

Wenxuan Song, Jiayi Chen, Shuai Chen, Jingbo Wang, Pengxiang Ding, Han Zhao, Yikai Qin, Xinhu Zheng, Donglin Wang, Yan Wang, Haoang Li

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods with auxiliary training objectives can improve performance and reduce the number of convergence steps. However, they typically incur significant computational overhead due to the additional losses from auxiliary tasks. To simultaneously achieve the enhanced capabilities of auxiliary training with the simplicity of standard SFT, we decouple the two objectives of auxiliary task training within the parameter space, namely, enhancing general capabilities and fitting task-specific action distributions. To deliver this goal, we only need to train the model to converge on a small-scale task set using two distinct training strategies. The difference between the resulting model parameters can then be interpreted as capability vectors provided by auxiliary tasks. These vectors are then merged with pretrained parameters to form a capability-enhanced meta model. Moreover, when standard SFT is augmented with a lightweight orthogonal regularization loss, the merged model attains performance comparable to auxiliary finetuned baselines with reduced computational overhead. Experimental results demonstrate that this approach is highly effective across diverse robot tasks. Project page: https://chris1220313648.github.io/Fast-dVLA/

☆ Colon-Bench: An Agentic Workflow for Scalable Dense Lesion Annotation in Full-Procedure Colonoscopy Videos

Abdullah Hamdi, Changchun Yang, Xin Gao

Early screening via colonoscopy is critical for colon cancer prevention, yet developing robust AI systems for this domain is hindered by the lack of densely annotated, long-sequence video datasets. Existing datasets predominantly focus on single-class polyp detection and lack the rich spatial, temporal, and linguistic annotations required to evaluate modern Multimodal Large Language Models (MLLMs). To address this critical gap, we introduce Colon-Bench, generated via a novel multi-stage agentic workflow. Our pipeline seamlessly integrates temporal proposals, bounding-box tracking, AI-driven visual confirmation, and human-in-the-loop review to scalably annotate full-procedure videos. The resulting verified benchmark is unprecedented in scope, encompassing 528 videos, 14 distinct lesion categories (including polyps, ulcers, and bleeding), over 300,000 bounding boxes, 213,000 segmentation masks, and 133,000 words of clinical descriptions. We utilize Colon-Bench to rigorously evaluate state-of-the-art MLLMs across lesion classification, Open-Vocabulary Video Object Segmentation (OV-VOS), and video Visual Question Answering (VQA). The MLLM results demonstrate surprisingly high localization performance in medical domains compared to SAM-3. Finally, we analyze common VQA errors from MLLMs to introduce a novel "colon-skill" prompting strategy, improving zero-shot MLLM performance by up to 9.7% across most MLLMs. The dataset and the code are available at https://abdullahamdi.com/colon-bench .

comment: preprint

☆ Designing Any Imaging System from Natural Language: Agent-Constrained Composition over a Finite Primitive Basis

Chengshuai Yang

Designing a computational imaging system -- selecting operators, setting parameters, validating consistency -- requires weeks of specialist effort per modality, creating an expertise bottleneck that excludes the broader scientific community from prototyping imaging instruments. We introduce spec.md, a structured specification format, and three autonomous agents -- Plan, Judge, and Execute -- that translate a one-sentence natural-language description into a validated forward model with bounded reconstruction error. A design-to-real error theorem decomposes total reconstruction error into five independently bounded terms, each linked to a corrective action. On 6 real-data modalities spanning all 5 carrier families, the automated pipeline matches expert-library quality (98.1 +/- 4.2%). Ten novel designs -- composing primitives into chains from 3D to 5D -- demonstrate compositional reach beyond any single-modality tool.

comment: 28 pages, 7 figures, 8 tables, includes Supplementary Information (sections S1-S6)

☆ LanteRn: Latent Visual Structured Reasoning

André G. Viveiros, Nuno Gonçalves, Matthias Lindemann, André Martins

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks requiring fine-grained spatial and visual understanding. While recent approaches take steps toward thinking with images by invoking tools or generating intermediate images, they either rely on external modules, or incur unnecessary computation by reasoning directly in pixel space. In this paper, we introduce LanteRn, a framework that enables LMMs to interleave language with compact latent visual representations, allowing visual reasoning to occur directly in latent space. LanteRn augments a vision-language transformer with the ability to generate and attend to continuous visual thought embeddings during inference. We train the model in two stages: supervised fine-tuning to ground visual features in latent states, followed by reinforcement learning to align latent reasoning with task-level utility. We evaluate LanteRn on three perception-centric benchmarks (VisCoT, V*, and Blink), observing consistent improvements in visual grounding and fine-grained reasoning. These results suggest that internal latent representations provide a promising direction for more efficient multimodal reasoning.

☆ Demographic Fairness in Multimodal LLMs: A Benchmark of Gender and Ethnicity Bias in Face Verification

Ünsal Öztürk, Hatef Otroshi Shahreza, Sébastien Marcel

Multimodal Large Language Models (MLLMs) have recently been explored as face verification systems that determine whether two face images are of the same person. Unlike dedicated face recognition systems, MLLMs approach this task through visual prompting and rely on general visual and reasoning abilities. However, the demographic fairness of these models remains largely unexplored. In this paper, we present a benchmarking study that evaluates nine open-source MLLMs from six model families, ranging from 2B to 8B parameters, on the IJB-C and RFW face verification protocols across four ethnicity groups and two gender groups. We measure verification accuracy with the Equal Error Rate and True Match Rate at multiple operating points per demographic group, and we quantify demographic disparity with four FMR-based fairness metrics. Our results show that FaceLLM-8B, the only face-specialised model in our study, substantially outperforms general-purpose MLLMs on both benchmarks. The bias patterns we observe differ from those commonly reported for traditional face recognition, with different groups being most affected depending on the benchmark and the model. We also note that the most accurate models are not necessarily the fairest and that models with poor overall accuracy can appear fair simply because they produce uniformly high error rates across all demographic groups.

comment: Accepted in CVPR 2026 workshops

☆ DeepFAN, a transformer-based deep learning model for human-artificial intelligence collaborative assessment of incidental pulmonary nodules in CT scans: a multi-reader, multi-case trial

Zhenchen Zhu, Ge Hu, Weixiong Tan, Kai Gao, Chao Sun, Zhen Zhou, Kepei Xu, Wei Han, Meixia Shang, Xiaoming Qiu, Yiqing Tan, Jinhua Wang, Zhoumeng Ying, Li Peng, Wei Song, Lan Song, Zhengyu Jin, Nan Hong, Yizhou Yu

The widespread adoption of CT has notably increased the number of detected lung nodules. However, current deep learning methods for classifying benign and malignant nodules often fail to comprehensively integrate global and local features, and most of them have not been validated through clinical trials. To address this, we developed DeepFAN, a transformer-based model trained on over 10K pathology-confirmed nodules and further conducted a multi-reader, multi-case clinical trial to evaluate its efficacy in assisting junior radiologists. DeepFAN achieved diagnostic area under the curve (AUC) of 0.939 (95% CI 0.930-0.948) on an internal test set and 0.954 (95% CI 0.934-0.973) on the clinical trial dataset involving 400 cases across three independent medical institutions. Explainability analysis indicated higher contributions from global than local features. Twelve readers' average performance significantly improved by 10.9% (95% CI 8.3%-13.5%) in AUC, 10.0% (95% CI 8.9%-11.1%) in accuracy, 7.6% (95% CI 6.1%-9.2%) in sensitivity, and 12.6% (95% CI 10.9%-14.3%) in specificity (P<0.001 for all). Nodule-level inter-reader diagnostic consistency improved from fair to moderate (overall k: 0.313 vs. 0.421; P=0.019). In conclusion, DeepFAN effectively assisted junior radiologists and may help homogenize diagnostic quality and reduce unnecessary follow-up of indeterminate pulmonary nodules. Chinese Clinical Trial Registry: ChiCTR2400084624.

comment: 28 pages for main text and 37 pages for supplementary information, 7 figures in main text and 9 figures in supplementary information

☆ UNIC: Neural Garment Deformation Field for Real-time Clothed Character Animation

Chengfeng Zhao, Junbo Qi, Yulou Liu, Zhiyang Dou, Minchen Li, Taku Komura, Ziwei Liu, Wenping Wang, Yuan Liu

Simulating physically realistic garment deformations is an essential task for virtual immersive experience, which is often achieved by physics simulation methods. However, these methods are typically time-consuming, computationally demanding, and require costly hardware, which is not suitable for real-time applications. Recent learning-based methods tried to resolve this problem by training graph neural networks to learn the garment deformation on vertices, which, however, fail to capture the intricate deformation of complex garment meshes with complex topologies. In this paper, we introduce a novel neural deformation field-based method, named UNIC, to animate the garments of an avatar in real time, given the motion sequences. Our key idea is to learn the instance-specific neural deformation field to animate the garment meshes. Such an instance-specific learning scheme does not require UNIC to generalize to new garments but only to new motion sequences, which greatly reduces the difficulty in training and improves the deformation quality. Moreover, neural deformation fields map the 3D points to their deformation offsets, which not only avoids handling topologies of the complex garments but also injects a natural smoothness constraint in the deformation learning. Extensive experiments have been conducted on various kinds of garment meshes to demonstrate the effectiveness and efficiency of UNIC over baseline methods, making it potentially practical and useful in real-world interactive applications like video games.

comment: Project page: https://igl-hkust.github.io/UNIC/

☆ Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference ICLR 2026

Sk Miraj Ahmed, Xi Yu, Yunqi Li, Yuewei Lin, Wei Xu

Accurate biodiversity identification from large-scale field data is a foundational problem with direct impact on ecology, conservation, and environmental monitoring. In practice, the core task is taxonomic prediction - inferring order, family, genus, or species from imperfect inputs such as specimen images, DNA barcodes, or both. Existing multimodal methods often treat taxonomy as a flat label space and therefore fail to encode the hierarchical structure of biological classification, which is critical for robustness under noise and missing modalities. We present two end-to-end variants for hierarchy-aware multimodal learning: CLiBD-HiR, which introduces Hierarchical Information Regularization (HiR) to shape embedding geometry across taxonomic levels, yielding structured and noise-robust representations; and CLiBD-HiR-Fuse, which additionally trains a lightweight fusion predictor that supports image-only, DNA-only, or joint inference and is resilient to modality corruption. Across large-scale biodiversity benchmarks, our approach improves taxonomic classification accuracy by over 14 percent compared to strong multimodal baselines, with particularly large gains under partial and corrupted DNA conditions. These results highlight that explicitly encoding biological hierarchy, together with flexible fusion, is key for practical biodiversity foundation models.

comment: Accepted at the ICLR 2026 Workshop on Foundation Models for Science (FM4Science)

☆ GeoHeight-Bench: Towards Height-Aware Multimodal Reasoning in Remote Sensing

Xuran Hu, Zhitong Xiong, Zhongcheng Hong, Yifang Ban, Xiaoxiang Zhu, Wufan Zhao

Current Large Multimodal Models (LMMs) in Earth Observation typically neglect the critical "vertical" dimension, limiting their reasoning capabilities in complex remote sensing geometries and disaster scenarios where physical spatial structures often outweigh planar visual textures. To bridge this gap, we introduce a comprehensive evaluation framework dedicated to height-aware remote sensing understanding. First, to overcome the severe scarcity of annotated data, we develop a scalable, VLM-driven data generation pipeline utilizing systematic prompt engineering and metadata extraction. This pipeline constructs two complementary benchmarks: GeoHeight-Bench for relative height analysis, and a more challenging GeoHeight-Bench+ for holistic, terrain-aware reasoning. Furthermore, to validate the necessity of height perception, we propose GeoHeightChat, the first height-aware remote sensing LMM baseline. Serving as a strong proof of concept, our baseline demonstrates that synergizing visual semantics with implicitly injected height geometric features effectively mitigates the "vertical blind spot", successfully unlocking a new paradigm of interactive height reasoning in existing optical models.

comment: 18 pages, 4 figures

☆ Towards Comprehensive Real-Time Scene Understanding in Ophthalmic Surgery through Multimodal Image Fusion

Nikolo Rohrmoser, Ghazal Ghazaei, Michael Sommersperger, Nassir Navab

Purpose: The integration of multimodal imaging into operating rooms paves the way for comprehensive surgical scene understanding. In ophthalmic surgery, by now, two complementary imaging modalities are available: operating microscope (OPMI) imaging and real-time intraoperative optical coherence tomography (iOCT). This first work toward temporal OPMI and iOCT feature fusion demonstrates the potential of multimodal image processing for multi-head prediction through the example of precise instrument tracking in vitreoretinal surgery. Methods: We propose a multimodal, temporal, real-time capable network architecture to perform joint instrument detection, keypoint localization, and tool-tissue distance estimation. Our network design integrates a cross-attention fusion module to merge OPMI and iOCT image features, which are efficiently extracted via a YoloNAS and a CNN encoder, respectively. Furthermore, a region-based recurrent module leverages temporal coherence. Results: Our experiments demonstrate reliable instrument localization and keypoint detection (95.79% mAP50) and show that the incorporation of iOCT significantly improves tool-tissue distance estimation, while achieving real-time processing rates of 22.5 ms per frame. Especially for close distances to the retina (below 1 mm), the distance estimation accuracy improved from 284 $μm$ (OPMI only) to 33 $μm$ (multimodal). Conclusion: Feature fusion of multimodal imaging can enhance multi-task prediction accuracy compared to single-modality processing and real-time processing performance can be achieved through tailored network design. While our results demonstrate the potential of multi-modal processing for image-guided vitreoretinal surgery, they also underline key challenges that motivate future research toward more reliable, consistent, and comprehensive surgical scene understanding.

☆ PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos

Yihao Wang, Yang Miao, Wenshuai Zhao, Wenyan Yang, Zihan Wang, Joni Pajarinen, Luc Van Gool, Danda Pani Paudel, Juho Kannala, Xi Wang, Arno Solin

Articulation perception aims to recover the motion and structure of articulated objects (e.g., drawers and cupboards), and is fundamental to 3D scene understanding in robotics, simulation, and animation. Existing learning-based methods rely heavily on supervised training with high-quality 3D data and manual annotations, limiting scalability and diversity. To address this limitation, we propose PAWS, a method that directly extracts object articulations from hand-object interactions in large-scale in-the-wild egocentric videos. We evaluate our method on the public data sets, including HD-EPIC and Arti4D data sets, achieving significant improvements over baselines. We further demonstrate that the extracted articulations benefit downstream tasks, including fine-tuning 3D articulation prediction models and enabling robot manipulation. See the project website at https://aaltoml.github.io/PAWS/.

comment: 32 pages, 13 figures. Project page: https://aaltoml.github.io/PAWS/

☆ Insights on back marking for the automated identification of animals

David Brunner, Marie Bordes, Elisabeth Mayrhuber, Stephan M. Winkler, Viktoria Dorfer, Maciej Oczak

To date, there is little research on how to design back marks to best support individual-level monitoring of uniform looking species like pigs. With the recent surge of machine learning-based monitoring solutions, there is a particular need for guidelines on the design of marks that can be effectively recognised by such algorithms. This study provides valuable insights on effective back mark design, based on the analysis of a machine learning model, trained to distinguish pigs via their back marks. Specifically, a neural network of type ResNet-50 was trained to classify ten pigs with unique back marks. The analysis of the model's predictions highlights the significance of certain design choices, even in controlled settings. Most importantly, the set of back marks must be designed such that each mark remains unambiguous under conditions of motion blur, diverse view angles and occlusions, caused by animal behaviour. Further, the back mark design must consider data augmentation strategies commonly employed during model training, like colour, flip and crop augmentations. The generated insights can support individual-level monitoring in future studies and real-world applications by optimizing back mark design.

☆ BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning

Ning Ding, Keisuke Fujii, Toru Tamaki

Understanding tactical dynamics in badminton requires analyzing entire matches rather than isolated clips. However, existing badminton datasets mainly focus on short clips or task-specific annotations and rarely provide full-match data with dense multimodal annotations. This limitation makes it difficult to generate accurate shot captions and perform match-level analysis. To address this limitation, we introduce the first Badminton Full Match Dense (BFMD) dataset, with 19 broadcast matches (including both singles and doubles) covering over 20 hours of play, comprising 1,687 rallies and 16,751 hit events, each annotated with a shot caption. The dataset provides hierarchical annotations including match segments, rally events, and dense rally-level multimodal annotations such as shot types, shuttle trajectories, player pose keypoints, and shot captions. We develop a VideoMAE-based multimodal captioning framework with a Semantic Feedback mechanism that leverages shot semantics to guide caption generation and improve semantic consistency. Experimental results demonstrate that multimodal modeling and semantic feedback improve shot caption quality over RGB-only baselines. We further showcase the potential of BFMD by analyzing the temporal evolution of tactical patterns across full matches.

comment: CVSports2026 accepted

☆ Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training

Xiangyang Luo, Qingyu Li, Yuming Li, Guanbo Huang, Yongjie Zhu, Wenyu Qin, Meng Wang, Pengfei Wan, Shao-Lun Huang

comment: Accepted to CVPR 2026

☆ CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild

Alex Hoi Hang Chan, Neha Singhal, Onur Kocahan, Andrea Meltzer, Saverio Lubrano, Miyako H. Warrington, Michel Griesser, Fumihiro Kano, Hemal Naik

Long-term behavioral monitoring of individual animals is crucial for studying behavioral changes that occur over different time scales, especially for conservation and evolutionary biology. Computer vision methods have proven to benefit biodiversity monitoring, but automated behavior monitoring in wild populations remains challenging. This stems from the lack of datasets that cover a range of computer vision tasks necessary to extract biologically meaningful measurements of individual animals. Here, we introduce such a dataset (CHIRP) with a new method (CORVID) for individual re-identification of wild birds. The CHIRP (Combining beHaviour, Individual Re-identification and Postures) dataset is curated from a long-term population of wild Siberian jays studied in Swedish Lapland, supporting re-identification (re-id), action recognition, 2D keypoint estimation, object detection, and instance segmentation. In addition to traditional task-specific benchmarking, we introduce application-specific benchmarking with biologically relevant metrics (feeding rates, co-occurrence rates) to evaluate the performance of models in real-world use cases. Finally, we present CORVID (COlouR-based Video re-ID), a novel pipeline for individual identification of birds based on the segmentation and classification of colored leg rings, a widespread approach for visual identification of individual birds. CORVID offers a probability-based id tracking method by matching the detected combination of color rings with a database. We use application-specific benchmarking to show that CORVID outperforms state-of-the-art re-id methods. We hope this work offers the community a blueprint for curating real-world datasets from ethically approved biological studies to bridge the gap between computer vision research and biological applications.

comment: 8 pages, 4 figures

☆ Challenges in Hyperspectral Imaging for Autonomous Driving: The HSI-Drive Case

Koldo Basterretxea, Jon Gutiérrez-Zaballa, Javier Echanobe

The use of hyperspectral imaging (HSI) in autonomous driving (AD), while promising, faces many challenges related to the specifics and requirements of this application domain. On the one hand, non-controlled and variable lighting conditions, the wide depth-of-field ranges, and dynamic scenes with fast-moving objects. On the other hand, the requirements for real-time operation and the limited computational resources of embedded platforms. The combination of these factors determines both the criteria for selecting appropriate HSI technologies and the development of custom vision algorithms that leverage the spectral and spatial information obtained from the sensors. In this article, we analyse several techniques explored in the research of HSI-based vision systems with application to AD, using as an example results obtained from experiments using data from the most recent version of the HSI-Drive dataset.

☆ RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

Yufeng Yang, Xianfang Zeng, Zhangqi Jiang, Fukun Yin, Jianzhuang Liu, Wei Cheng, jinghong lan, Shiyu Liu, Yuqi Peng, Gang YU, Shifeng Chen

Image restoration under real-world degradations is critical for downstream tasks such as autonomous driving and object detection. However, existing restoration models are often limited by the scale and distribution of their training data, resulting in poor generalization to real-world scenarios. Recently, large-scale image editing models have shown strong generalization ability in restoration tasks, especially for closed-source models like Nano Banana Pro, which can restore images while preserving consistency. Nevertheless, achieving such performance with those large universal models requires substantial data and computational costs. To address this issue, we construct a large-scale dataset covering nine common real-world degradation types and train a state-of-the-art open-source model to narrow the gap with closed-source alternatives. Furthermore, we introduce RealIR-Bench, which contains 464 real-world degraded images and tailored evaluation metrics focusing on degradation removal and consistency preservation. Extensive experiments demonstrate our model ranks first among open-source methods, achieving state-of-the-art performance.

comment: 27 pages, 15 figures, Project homepage: https://yfyang007.github.io/RealRestorer/

☆ Knowledge-Guided Failure Prediction: Detecting When Object Detectors Miss Safety-Critical Objects

Jakob Paul Zimmermann, Gerrit Holzbach, David Lerch

Object detectors deployed in safety-critical environments can fail silently, e.g. missing pedestrians, workers, or other safety-critical objects without emitting any warning. Traditional Out Of Distribution (OOD) detection methods focus on identifying unfamiliar inputs, but do not directly predict functional failures of the detector itself. We introduce Knowledge Guided Failure Prediction (KGFP), a representation-based monitoring framework that treats missed safety-critical detections as anomalies to be detected at runtime. KGFP measures semantic misalignment between internal object detector features and visual foundation model embeddings using a dual-encoder architecture with an angular distance metric. A key property is that when either the detector is operating outside its competence or the visual foundation model itself encounters novel inputs, the two embeddings diverge, producing a high-angle signal that reliably flags unsafe images. We compare our novel KGFS method to baseline OOD detection methods. On COCO person detection, applying KGFP as a selective-prediction gate raises person recall among accepted images from 64.3% to 84.5% at 5% False Positive Rate (FPR), and maintains strong performance across six COCO-O visual domains, outperforming OOD baselines by large margins. Our code, models, and features are published at https://gitlab.cc-asp.fraunhofer.de/iosb_public/KGFP.

☆ AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments

Xuzhi Wang, Xinran Wu, Song Wang, Lingdong Kong, Ziping Zhao

Indoor monocular semantic scene completion (MSSC) is notably more challenging than its outdoor counterpart due to complex spatial layouts and severe occlusions. While transformers are well suited for modeling global dependencies, their high memory cost and difficulty in reconstructing fine-grained details have limited their use in indoor MSSC. To address these limitations, we introduce AdaSFormer, a serialized transformer framework tailored for indoor MSSC. Our model features three key designs: (1) an Adaptive Serialized Transformer with learnable shifts that dynamically adjust receptive fields; (2) a Center-Relative Positional Encoding that captures spatial information richness; and (3) a Convolution-Modulated Layer Normalization that bridges heterogeneous representations between convolutional and transformer features. Extensive experiments on NYUv2 and Occ-ScanNet demonstrate that AdaSFormer achieves state-of-the-art performance. The code is publicly available at: https://github.com/alanWXZ/AdaSFormer.

comment: Accepted at CVPR 2026

☆ GridVAD: Open-Set Video Anomaly Detection via Spatial Reasoning over Stratified Frame Grids

Mohamed Eltahir, Ahmed O. Ibrahim, Obada Siralkhatim, Tabarak Abdallah, Sondos Mohamed

Vision-Language Models (VLMs) are powerful open-set reasoners, yet their direct use as anomaly detectors in video surveillance is fragile: without calibrated anomaly priors, they alternate between missed detections and hallucinated false alarms. We argue the problem is not the VLM itself but how it is used. VLMs should function as anomaly proposers, generating open-set candidate descriptions that are then grounded and tracked by purpose-built spatial and temporal modules. We instantiate this propose-ground-propagate principle in GridVAD, a training-free pipeline that produces pixel-level anomaly masks without any domain-specific training. A VLM reasons over stratified grid representations of video clips to generate natural-language anomaly proposals. Self-Consistency Consolidation (SCC) filters hallucinations by retaining only proposals that recur across multiple independent samplings. Grounding DINO anchors each surviving proposal to a bounding box, and SAM2 propagates it as a dense mask through the anomaly interval. The per-clip VLM budget is fixed at M+1 calls regardless of video length, where M can be set according to the proposals needed. On UCSD Ped2, GridVAD achieves the highest Pixel-AUROC (77.59) among all compared methods, surpassing even the partially fine-tuned TAO (75.11) and outperforms other zero-shot approaches on object-level RBDC by over 5x. Ablations reveal that SCC provides a controllable precision-recall tradeoff: filtering improves all pixel level metrics at a modest cost in object-level recall. Efficiency experiments show GridVAD is 2.7x more call-efficient than uniform per-frame VLM querying while additionally producing dense segmentation masks.Code and qualitative video results are available at https://gridvad.github.io.

☆ CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration

Keming Ye, Zhou Zhao, Fan Wu, Shengyu Zhang

Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches. However, their computational intensity and sequential nature impede on-device deployment, causing disruptive latency. We address this via a cloud-device collaboration framework \textbf{CIAR}, which utilizes on-device self-verification to handle two key properties of visual synthesis: \textit{the vast token vocabulary} required for high-fidelity images and \textit{inherent spatial redundancy} which leads to extreme predictability in homogeneous regions, while object boundaries exhibit high uncertainty. Uniform verification wastes resources on such redundant tokens. Our solution centers on an on-device token uncertainty quantifier, which adopts continuous probability intervals to accelerate processing and make it feasible for large visual vocabularies instead of conventional discrete solution sets. Additionally, we incorporate a Interval-enhanced decoding module to further speed up decoding while maintaining visual fidelity and semantic consistency via a distribution alignment training strategy. Extensive experiments demonstrate that CIAR achieves a 2.18x speed-up and reduces cloud requests by 70\%, while preserving image quality compared to existing methods.

comment: 23 pages, 10 tables, 7 figures

☆ DC-Reg: Globally Optimal Point Cloud Registration via Tight Bounding with Difference of Convex Programming

Wei Lian, Fei Ma, Hang Pan, Zhesen Cui, Wangmeng Zuo

Achieving globally optimal point cloud registration under partial overlaps and large misalignments remains a fundamental challenge. While simultaneous transformation ($\boldsymbolθ$) and correspondence ($\mathbf{P}$) estimation has the advantage of being robust to nonrigid deformation, its non-convex coupled objective often leads to local minima for heuristic methods and prohibitive convergence times for existing global solvers due to loose lower bounds. To address this, we propose DC-Reg, a robust globally optimal framework that significantly tightens the Branch-and-Bound (BnB) search. Our core innovation is the derivation of a holistic concave underestimator for the coupled transformation-assignment objective, grounded in the Difference of Convex (DC) programming paradigm. Unlike prior works that rely on term-wise relaxations (e.g., McCormick envelopes) which neglect variable interplay, our holistic DC decomposition captures the joint structural interaction between $\boldsymbolθ$ and $\mathbf{P}$. This formulation enables the computation of remarkably tight lower bounds via efficient Linear Assignment Problems (LAP) evaluated at the vertices of the search boxes. We validate our framework on 2D similarity and 3D rigid registration, utilizing rotation-invariant features for the latter to achieve high efficiency without sacrificing optimality. Experimental results on synthetic data and the 3DMatch benchmark demonstrate that DC-Reg achieves significantly faster convergence and superior robustness to extreme noise and outliers compared to state-of-the-art global techniques.

☆ VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents

George Eskandar, Fengyi Shen, Mohammad Altillawi, Dong Chen, Yang Bai, Liudi Yang, Ziyuan Liu

Recent progress in video-to-video (V2V) translation has enabled realistic resimulation of embodied AI demonstrations, a capability that allows pretrained robot policies to be transferable to new environments without additional data collection. However, prior works can only operate on a single view at a time, while embodied AI tasks are commonly captured from multiple synchronized cameras to support policy learning. Naively applying single-view models independently to each camera leads to inconsistent appearance across views, and standard transformer architectures do not scale to multi-view settings due to the quadratic cost of cross-view attention. We present VideoWeaver, the first multimodal multi-view V2V translation framework. VideoWeaver is initially trained as a single-view flow-based V2V model. To achieve an extension to the multi-view regime, we propose to ground all views in a shared 4D latent space derived from a feed-forward spatial foundation model, namely, Pi3. This encourages view-consistent appearance even under wide baselines and dynamic camera motion. To scale beyond a fixed number of cameras, we train views at distinct diffusion timesteps, enabling the model to learn both joint and conditional view distributions. This in turn allows autoregressive synthesis of new viewpoints conditioned on existing ones. Experiments show superior or similar performance to the state-of-the-art on the single-view translation benchmarks and, for the first time, physically and stylistically consistent multi-view translations, including challenging egocentric and heterogeneous-camera setups central to world randomization for robot learning.

☆ HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models

Huizhi Liang, Yichao Shen, Yu Deng, Sicheng Xu, Zhiyuan Feng, Tong Zhang, Yaobo Liang, Jiaolong Yang

Achieving human-like spatial intelligence for vision-language models (VLMs) requires inferring 3D structures from 2D observations, recognizing object properties and relations in 3D space, and performing high-level spatial reasoning. In this paper, we propose a principled hierarchical framework that decomposes the learning of 3D spatial understanding in VLMs into four progressively complex levels, from geometric perception to abstract spatial reasoning. Guided by this framework, we construct an automated pipeline that processes approximately 5M images with over 45M objects to generate 3D spatial VQA pairs across diverse tasks and scenes for VLM supervised fine-tuning. We also develop an RGB-D VLM incorporating metric-scale point maps as auxiliary inputs to further enhance spatial understanding. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on multiple spatial understanding and reasoning benchmarks, surpassing specialized spatial models and large proprietary systems such as Gemini-2.5-pro and GPT-5. Moreover, our analysis reveals clear dependencies among hierarchical task levels, offering new insights into how multi-level task design facilitates the emergence of 3D spatial intelligence.

comment: Accepted by CVPR 2026. Project page: https://microsoft.github.io/HiSpatial

☆ LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior

Xinkai Wang, Chenyi Wang, Yifu Xu, Mingzhe Ye, Fu-Cheng Zhang, Jialin Tian, Xinyu Zhan, Lifeng Zhu, Cewu Lu, Lixin Yang

We introduce \textbf{LaMP}, a dual-expert Vision-Language-Action framework that embeds dense 3D scene flow as a latent motion prior for robotic manipulation. Existing VLA models regress actions directly from 2D semantic visual features, forcing them to learn complex 3D physical interactions implicitly. This implicit learning strategy degrades under unfamiliar spatial dynamics. LaMP addresses this limitation by aligning a flow-matching \emph{Motion Expert} with a policy-predicting \emph{Action Expert} through gated cross-attention. Specifically, the Motion Expert generates a one-step partially denoised 3D scene flow, and its hidden states condition the Action Expert without full multi-step reconstruction. We evaluate LaMP on the LIBERO, LIBERO-Plus, and SimplerEnv-WidowX simulation benchmarks as well as real-world experiments. LaMP consistently outperforms evaluated VLA baselines across LIBERO, LIBERO-Plus, and SimplerEnv-WidowX benchmarks, achieving the highest reported average success rates under the same training budgets. On LIBERO-Plus OOD perturbations, LaMP shows improved robustness with an average 9.7% gain over the strongest prior baseline. Our project page is available at https://summerwxk.github.io/lamp-project-page/.

☆ PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders

Niccolò Cavagnero, Narges Norouzi, Gijs Dubbelman, Daan de Geus

Vision Foundation Models (VFMs) pre-trained at scale enable a single frozen encoder to serve multiple downstream tasks simultaneously. Recent VFM-based encoder-only models for image and video segmentation, such as EoMT and VidEoMT, achieve competitive accuracy with remarkably low latency, yet they require finetuning the encoder, sacrificing the multi-task encoder sharing that makes VFMs practically attractive for large-scale deployment. To reconcile encoder-only simplicity and speed with frozen VFM features, we propose the Plain Mask Decoder (PMD), a fast Transformer-based segmentation decoder that operates on top of frozen VFM features. The resulting model, the Plain Mask Transformer (PMT), preserves the architectural simplicity and low latency of encoder-only designs while keeping the encoder representation unchanged and shareable. The design seamlessly applies to both image and video segmentation, inheriting the generality of the encoder-only framework. On standard image segmentation benchmarks, PMT matches the frozen-encoder state of the art while running up to ~3x faster. For video segmentation, it even performs on par with fully finetuned methods, while being up to 8x faster than state-of-the-art frozen-encoder models. Code: https://github.com/tue-mps/pmt.

comment: 8 pages, ECV 2026, CVPR Workshop

☆ FSGNet: A Frequency-Aware and Semantic Guidance Network for Infrared Small Target Detection

Yingmei Zhang, Wangtao Bao, Yong Yang, Weiguo Wan, Qin Xiao, Xueting Zou

Infrared small target detection (IRSTD) aims to identify and distinguish small targets from complex backgrounds. Leveraging the powerful multi-scale feature fusion capability of the U-Net architecture, IRSTD has achieved significant progress. However, U-Net suffers from semantic degradation when transferring high-level features from deep to shallow layers, limiting the precise localization of small targets. To address this issue, this paper proposes FSGNet, a lightweight and effective detection framework incorporating frequency-aware and semantic guidance mechanisms. Specifically, a multi-directional interactive attention module is proposed throughout the encoder to capture fine-grained and directional features, enhancing the network's sensitivity to small, low-contrast targets. To suppress background interference propagated through skip connections, a multi-scale frequency-aware module leverages Fast Fourier transform to filter out target-similar clutter while preserving salient target structures. At the deepest layer, a global pooling module captures high-level semantic information, which is subsequently upsampled and propagated to each decoder stage through the global semantic guidance flows, ensuring semantic consistency and precise localization across scales. Extensive experiments on four public IRSTD datasets demonstrate that FSGNet achieves superior detection performance and maintains high efficiency, highlighting its practical applicability and robustness. The codes will be released on https://github.com/Wangtao-Bao/FSGNet.

☆ Multimodal Dataset Distillation via Phased Teacher Models ICLR 2026

Shengbin Guo, Hang Zhao, Senqiao Yang, Chenyang Jiang, Yuhang Cheng, Xiangru Peng, Rui Shao, Zhuotao Tian

Multimodal dataset distillation aims to construct compact synthetic datasets that enable efficient compression and knowledge transfer from large-scale image-text data. However, existing approaches often fail to capture the complex, dynamically evolving knowledge embedded in the later training stages of teacher models. This limitation leads to degraded student performance and compromises the quality of the distilled data. To address critical challenges such as pronounced cross-stage performance gaps and unstable teacher trajectories, we propose Phased Teacher Model with Shortcut Trajectory (PTM-ST) -- a novel phased distillation framework. PTM-ST leverages stage-aware teacher modeling and a shortcut-based trajectory construction strategy to accurately fit the teacher's learning dynamics across distinct training phases. This enhances both the stability and expressiveness of the distillation process. Through theoretical analysis and comprehensive experiments, we show that PTM-ST significantly mitigates optimization oscillations and inter-phase knowledge gaps, while also reducing storage overhead. Our method consistently surpasses state-of-the-art baselines on Flickr30k and COCO, achieving up to 13.5% absolute improvement and an average gain of 9.53% on Flickr30k. Code: https://github.com/Previsior/PTM-ST.

comment: Accepted to ICLR 2026

☆ CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation

Jeannie Chung, Hanna Jang, Ingyeong Yang, Uiwon Hwang, Jaehyung Sim

CLIP aligns image and text embeddings via contrastive learning and demonstrates strong zero-shot generalization. Its large-scale architecture requires substantial computational and memory resources, motivating the distillation of its capabilities into lightweight student models. However, existing CLIP distillation methods do not explicitly model multi-directional relational dependencies between teacher and student embeddings, limiting the student's ability to preserve the structural relationships encoded by the teacher. To address this, we propose a relational knowledge distillation framework that introduces two novel methods, Vertical Relational Distillation (VRD) and Cross Relational Distillation (XRD). VRD enforces consistency of teacher-student distillation strength across modalities at the distribution level, while XRD imposes bidirectional symmetry on cross-modal teacher-student similarity distributions. By jointly modeling multi-directional relational structures, CLIP-RD promotes faithful alignment of the student embedding geometry with that of the teacher, outperforming existing methods by 0.8%p.

☆ Integrating Deep RL and Bayesian Inference for ObjectNav in Mobile Robotics

João Castelo-Branco, José Santos-Victor, Alexandre Bernardino

Autonomous object search is challenging for mobile robots operating in indoor environments due to partial observability, perceptual uncertainty, and the need to trade off exploration and navigation efficiency. Classical probabilistic approaches explicitly represent uncertainty but typically rely on handcrafted action-selection heuristics, while deep reinforcement learning enables adaptive policies but often suffers from slow convergence and limited interpretability. This paper proposes a hybrid object-search framework that integrates Bayesian inference with deep reinforcement learning. The method maintains a spatial belief map over target locations, updated online through Bayesian inference from calibrated object detections, and trains a reinforcement learning policy to select navigation actions directly from this probabilistic representation. The approach is evaluated in realistic indoor simulation using Habitat 3.0 and compared against developed baseline strategies. Across two indoor environments, the proposed method improves success rate while reducing search effort. Overall, the results support the value of combining Bayesian belief estimation with learned action selection to achieve more efficient and reliable objectsearch behavior under partial observability.

comment: Accepted and to be published in the ICARSC 2026 26th IEEE International Conference on Autonomous Robot Systems and Competitions

☆ InstanceAnimator: Multi-Instance Sketch Video Colorization

Yinhan Zhang, Yue Ma, Bingyuan Wang, Kunyu Feng, Yeying Jin, Qifeng Chen, Anyi Rao, Zeyu Wang

We propose InstanceAnimator, a novel Diffusion Transformer framework for multi-instance sketch video colorization. Existing methods suffer from three core limitations: inflexible user control due to heavy reliance on single reference frames, poor instance controllability leading to misalignment in multi-character scenarios, and degraded detail fidelity in fine-grained regions. To address these challenges, we introduce three corresponding innovations. First, a Canvas Guidance Condition eliminates workflow fragmentation by allowing free placement of reference elements and background, enabling unprecedented user flexibility. Second, an Instance Matching Mechanism resolves misalignment by integrating instance features with the sketches, ensuring precise control over multiple characters. Third, an Adaptive Decoupled Control Module enhances detail fidelity by injecting semantic features from characters, backgrounds, and text conditions into the diffusion process. Extensive experiments demonstrate that InstanceAnimator achieves superior multi-instance colorization with enhanced user control, high visual quality, and strong instance consistency.

☆ Image Rotation Angle Estimation: Comparing Circular-Aware Methods

Maximilian Woehrer

Automatic image rotation estimation is a key preprocessing step in many vision pipelines. This task is challenging because angles have circular topology, creating boundary discontinuities that hinder standard regression methods. We present a comprehensive study of five circular-aware methods for global orientation estimation: direct angle regression with circular loss, classification via angular binning, unit-vector regression, phase-shifting coder, and circular Gaussian distribution. Using transfer learning from ImageNet-pretrained models, we systematically evaluate these methods across sixteen modern architectures by adapting their output heads for rotation-specific predictions. Our results show that probabilistic methods, particularly the circular Gaussian distribution, are the most robust across architectures, while classification achieves the best accuracy on well-matched backbones but suffers training instabilities on others. The best configuration (classification with EfficientViT-B3) achieves a mean absolute error (MAE) of 1.23° (mean across five independent runs) on the DRC-D dataset, while the circular Gaussian distribution with MambaOut Base achieves a virtually identical 1.24° with greater robustness across backbones. Training and evaluating our top-performing method-architecture combinations on COCO 2014, the best configuration reaches 3.71° MAE, improving substantially over prior work, with further improvement to 2.84° on the larger COCO 2017 dataset.

comment: 7 pages, 3 figures, 2 tables. Under review at Pattern Recognition Letters

☆ HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT

Yongsung Kim, Wooseok Song, Jaihyun Lew, Hun Hwangbo, Jaehoon Lee, Sungroh Yoon

Visual Geometry Grounded Transformer (VGGT) has advanced 3D vision, yet its global attention layers suffer from quadratic computational costs that hinder scalability. Several sparsification-based acceleration techniques have been proposed to alleviate this issue, but they often suffer from substantial accuracy degradation. We hypothesize that the accuracy degradation stems from the heterogeneity in head-wise sparsification sensitivity, as the existing methods apply a uniform sparsity pattern across all heads. Motivated by this hypothesis, we present a two-stage sparsification pipeline that effectively quantifies and exploits headwise sparsification sensitivity. In the first stage, we measure head-wise sparsification sensitivity using a novel metric, the Head Sensitivity Score (HeSS), which approximates the Hessian with respect to two distinct error terms on a small calibration set. In the inference stage, we perform HeSS-Guided Sparsification, leveraging the pre-computed HeSS to reallocate the total attention budget-assigning denser attention to sensitive heads and sparser attention to more robust ones. We demonstrate that HeSS effectively captures head-wise sparsification sensitivity and empirically confirm that attention heads in the global attention layers exhibit heterogeneous sensitivity characteristics. Extensive experiments further show that our method effectively mitigates performance degradation under high sparsity, demonstrating strong robustness across varying sparsification levels. Code is available at https://github.com/libary753/HeSS.

comment: Accepted to CVPR 2026

☆ MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data

Zhekai Chen, Yuqing Wang, Manyuan Zhang, Xihui Liu

Generating images conditioned on multiple visual references is critical for real-world applications such as multi-subject composition, narrative illustration, and novel view synthesis, yet current models suffer from severe performance degradation as the number of input references grows. We identify the root cause as a fundamental data bottleneck: existing datasets are dominated by single- or few-reference pairs and lack the structured, long-context supervision needed to learn dense inter-reference dependencies. To address this, we introduce MacroData, a large-scale dataset of 400K samples, each containing up to 10 reference images, systematically organized across four complementary dimensions -- Customization, Illustration, Spatial reasoning, and Temporal dynamics -- to provide comprehensive coverage of the multi-reference generation space. Recognizing the concurrent absence of standardized evaluation protocols, we further propose MacroBench, a benchmark of 4,000 samples that assesses generative coherence across graded task dimensions and input scales. Extensive experiments show that fine-tuning on MacroData yields substantial improvements in multi-reference generation, and ablation studies further reveal synergistic benefits of cross-task co-training and effective strategies for handling long-context complexity. The dataset and benchmark will be publicly released.

comment: Project Page: https://macro400k.github.io/

☆ Adaptive Learned Image Compression with Graph Neural Networks

Yunuo Chen, Bing He, Zezheng Lyu, Hongwei Hu, Qunshan Gu, Yuan Tian, Guo Lu

Efficient image compression relies on modeling both local and global redundancy. Most state-of-the-art (SOTA) learned image compression (LIC) methods are based on CNNs or Transformers, which are inherently rigid. Standard CNN kernels and window-based attention mechanisms impose fixed receptive fields and static connectivity patterns, which potentially couple non-redundant pixels simply due to their proximity in Euclidean space. This rigidity limits the model's ability to adaptively capture spatially varying redundancy across the image, particularly at the global level. To overcome these limitations, we propose a content-adaptive image compression framework based on Graph Neural Networks (GNNs). Specifically, our approach constructs dual-scale graphs that enable flexible, data-driven receptive fields. Furthermore, we introduce adaptive connectivity by dynamically adjusting the number of neighbors for each node based on local content complexity. These innovations empower our Graph-based Learned Image Compression (GLIC) model to effectively model diverse redundancy patterns across images, leading to more efficient and adaptive compression. Experiments demonstrate that GLIC achieves state-of-the-art performance, achieving BD-rate reductions of 19.29%, 21.69%, and 18.71% relative to VTM-9.1 on Kodak, Tecnick, and CLIC, respectively. Code will be released at https://github.com/UnoC-727/GLIC.

comment: Accepted by CVPR 2026

☆ Towards Controllable Low-Light Image Enhancement: A Continuous Multi-illumination Dataset and Efficient State Space Framework

Hongru Han, Tingrui Guo, Liming Zhang, Yan Su, Qiwen Xu, Zhuohua Ye

Low-light image enhancement (LLIE) has traditionally been formulated as a deterministic mapping. However, this paradigm often struggles to account for the ill-posed nature of the task, where unknown ambient conditions and sensor parameters create a multimodal solution space. Consequently, state-of-the-art methods frequently encounter luminance discrepancies between predictions and labels, often necessitating "gt-mean" post-processing to align output luminance for evaluation. To address this fundamental limitation, we propose a transition toward Controllable Low-light Enhancement (CLE), explicitly reformulating the task as a well-posed conditional problem. To this end, we introduce CLE-RWKV, a holistic framework supported by Light100, a new benchmark featuring continuous real-world illumination transitions. To resolve the conflict between luminance control and chromatic fidelity, a noise-decoupled supervision strategy in the HVI color space is employed, effectively separating illumination modulation from texture restoration. Architecturally, to adapt efficient State Space Models (SSMs) for dense prediction, we leverage a Space-to-Depth (S2D) strategy. By folding spatial neighborhoods into channel dimensions, this design allows the model to recover local inductive biases and effectively bridge the "scanning gap" inherent in flattened visual sequences without sacrificing linear complexity. Experiments across seven benchmarks demonstrate that our approach achieves competitive performance and robust controllability, providing a real-world multi-illumination alternative that significantly reduces the reliance on gt-mean post-processing.

comment: 10 pages, 8 figures

☆ V2U4Real: A Real-world Large-scale Dataset for Vehicle-to-UAV Cooperative Perception

Weijia Li, Haoen Xiang, Tianxu Wang, Shuaibing Wu, Qiming Xia, Cheng Wang, Chenglu Wen

Modern autonomous vehicle perception systems are often constrained by occlusions, blind spots, and limited sensing range. While existing cooperative perception paradigms, such as Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I), have demonstrated their effectiveness in mitigating these challenges, they remain limited to ground-level collaboration and cannot fully address large-scale occlusions or long-range perception in complex environments. To advance research in cross-view cooperative perception, we present V2U4Real, the first large-scale real-world multi-modal dataset for Vehicle-to-UAV (V2U) cooperative object perception. V2U4Real is collected by a ground vehicle and a UAV equipped with multi-view LiDARs and RGB cameras. The dataset covers urban streets, university campuses, and rural roads under diverse traffic scenarios, comprising over 56K LiDAR frames, 56K multi-view camera images, and 700K annotated 3D bounding boxes across four classes. To support a wide range of research tasks, we establish benchmarks for single-agent 3D object detection, cooperative 3D object detection, and object tracking. Comprehensive evaluations of several state-of-the-art models demonstrate the effectiveness of V2U cooperation in enhancing perception robustness and long-range awareness. The V2U4Real dataset and codebase is available at https://github.com/VjiaLi/V2U4Real.

comment: Accepted by CVPR2026

☆ EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval

Yuhan Chen, Pengwen Dai, Chuan Wang, Dayan Wu, Xiaochun Cao

comment: Accepted at CVPR 2026

☆ ViewSplat: View-Adaptive Dynamic Gaussian Splatting for Feed-Forward Synthesis

Moonyeon Jeong, Seunggi Min, Suhyeon Lee, Hongje Seong

We present ViewSplat, a view-adaptive 3D Gaussian splatting network for novel view synthesis from unposed images. While recent feed-forward 3D Gaussian splatting has significantly accelerated 3D scene reconstruction by bypassing per-scene optimization, a fundamental fidelity gap remains. We attribute this bottleneck to the limited capacity of single-step feed-forward networks to regress static Gaussian primitives that satisfy all viewpoints. To address this limitation, we shift the paradigm from static primitive regression to view-adaptive dynamic splatting. Instead of a rigid Gaussian representation, our pipeline learns a view-adaptable latent representation. Specifically, ViewSplat initially predicts base Gaussian primitives alongside the weights of dynamic MLPs. During rendering, these MLPs take target view coordinates as input and predict view-dependent residual updates for each Gaussian attribute (i.e., 3D position, scale, rotation, opacity, and color). This mechanism, which we term view-adaptive dynamic splatting, allows each primitive to rectify initial estimation errors, effectively capturing high-fidelity appearances. Extensive experiments demonstrate that ViewSplat achieves state-of-the-art fidelity while maintaining fast inference (17 FPS) and real-time rendering (154 FPS).

comment: 24 pages, 10 figures

☆ Towards Practical Lossless Neural Compression for LiDAR Point Clouds

Pengpeng Yu, Haoran Li, Runqing Jiang, Dingquan Li, Jing Wang, Liang Lin, Yulan Guo

LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of existing methods. To address this challenge, we propose a compact representation for efficient predictive lossless coding. Our framework comprises two lightweight modules. First, the Geometry Re-Densification Module iteratively densifies encoded sparse geometry, extracts features at a dense scale, and then sparsifies the features for predictive coding. This module avoids costly computation on highly sparse details while maintaining a lightweight prediction head. Second, the Cross-scale Feature Propagation Module leverages occupancy cues from multiple resolution levels to guide hierarchical feature propagation, enabling information sharing across scales and reducing redundant feature extraction. Additionally, we introduce an integer-only inference pipeline to enable bit-exact cross-platform consistency, which avoids the entropy-coding collapse observed in existing neural compression methods and further accelerates coding. Experiments demonstrate competitive compression performance at real-time speed. Code will be released upon acceptance. Code is available at https://github.com/pengpeng-yu/FastPCC.

☆ Hyperspectral Trajectory Image for Multi-Month Trajectory Anomaly Detection

Md Awsafur Rahman, Chandrakanth Gudavalli, Hardik Prajapati, B. S. Manjunath

Trajectory anomaly detection underpins applications from fraud detection to urban mobility analysis. Dense GPS methods preserve fine-grained evidence such as abnormal speeds and short-duration events, but their quadratic cost makes multi-month analysis intractable; consequently, no existing approach detects anomalies over multi-month dense GPS trajectories. The field instead relies on scalable sparse stay-point methods that discard this evidence, forcing separate architectures for each regime and preventing knowledge transfer. We argue this bottleneck is unnecessary: human trajectories, dense or sparse, share a natural two-dimensional cyclic structure along within-day and across-day axes. We therefore propose TITAnD (Trajectory Image Transformer for Anomaly Detection), which reformulates trajectory anomaly detection as a vision problem by representing trajectories as a Hyperspectral Trajectory Image (HTI): a day x time-of-day grid whose channels encode spatial, semantic, temporal, and kinematic information from either modality, unifying both under a single representation. Under this formulation, agent-level detection reduces to image classification and temporal localization to semantic segmentation. To model this representation, we introduce the Cyclic Factorized Transformer (CFT), which factorizes attention along the two temporal axes, encoding the cyclic inductive bias of human routines, while reducing attention cost by orders of magnitude and enabling dense multi-month anomaly detection for the first time. Empirically, TITAnD achieves the best AUC-PR across sparse and dense benchmarks, surpassing vision models like UNet while being 11-75x faster than the Transformer with comparable memory, demonstrating that vision reformulation and structure-aware modeling are jointly essential. Code will be made public soon.

☆ Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models

Yabin Zhang, Maya Varma, Yunhe Gao, Jean-Benoit Delbrouck, Jiaming Liu, Chong Wang, Curtis Langlotz

Out-of-distribution (OOD) detection aims to identify samples that deviate from in-distribution (ID). One popular pipeline addresses this by introducing negative labels distant from ID classes and detecting OOD based on their distance to these labels. However, such labels may present poor activation on OOD samples, failing to capture the OOD characteristics. To address this, we propose \underline{T}est-time \underline{A}ctivated \underline{N}egative \underline{L}abels (TANL) by dynamically evaluating activation levels across the corpus dataset and mining candidate labels with high activation responses during the testing process. Specifically, TANL identifies high-confidence test images online and accumulates their assignment probabilities over the corpus to construct a label activation metric. Such a metric leverages historical test samples to adaptively align with the test distribution, enabling the selection of distribution-adaptive activated negative labels. By further exploring the activation information within the current testing batch, we introduce a more fine-grained, batch-adaptive variant. To fully utilize label activation knowledge, we propose an activation-aware score function that emphasizes negative labels with stronger activations, boosting performance and enhancing its robustness to the label number. Our TANL is training-free, test-efficient, and grounded in theoretical justification. Experiments on diverse backbones and wide task settings validate its effectiveness. Notably, on the large-scale ImageNet benchmark, TANL significantly reduces the FPR95 from 17.5\% to 9.8\%. Codes are available at \href{https://github.com/YBZh/OpenOOD-VLM}{YBZh/OpenOOD-VLM}.

comment: CVPR 2026 main track, Codes are available at https://github.com/YBZh/OpenOOD-VLM

☆ Semantic-Aware Prefix Learning for Token-Efficient Image Generation

Qingfeng Li, Haoxian Zhang, Xu He, Songlin Tang, Zhixue Fang, Xiaoqiang Liu, Pengfei Wan Guoqi Li

Visual tokenizers play a central role in latent image generation by bridging high-dimensional images and tractable generative modeling. However, most existing tokenizers are still trained with reconstruction-dominated objectives, which often yield latent representations that are only weakly grounded in high-level semantics. Recent approaches improve semantic alignment, but typically treat semantic signals as auxiliary regularization rather than making them functionally necessary for representation learning. We propose SMAP, a SeMantic-Aware Prefix tokenizer that injects class-level semantic conditions into a query-based 1D tokenization framework. To make semantics indispensable during training, SMAP introduces a tail token dropping strategy, which forces semantic conditions and early latent prefixes to bear increasing responsibility under progressively reduced token budgets. To verify that the resulting latent space is useful for generation rather than reconstruction alone, we further introduce CARD, a hybrid Causal AutoRegressive--Diffusion generator. Extensive experiments on ImageNet show that SMAP consistently improves reconstruction quality across discrete and continuous tokenization settings, and that its semantically grounded latent space yields strong downstream generation performance under compact token budgets.

☆ FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics

Taejin Jeong, Joohyeok Kim, Jinyeong Kim, Chanyoung Kim, Seong Jae Hwang

Spatial Transcriptomics (ST) provides spatially-resolved gene expression, offering crucial insights into tissue architecture and complex diseases. However, its prohibitive cost limits widespread adoption, leading to significant attention on inferring spatial gene expression from readily available whole slide images. While graph neural networks have been proposed to model interactions between tissue regions, their reliance on pre-defined sparse graphs prevents them from considering potentially interacting spot pairs, resulting in a structural limitation in capturing complex biological relationships. To address this, we propose FEAST (Fully connected Expressive Attention for Spatial Transcriptomics), an attention-based framework that models the tissue as a fully connected graph, enabling the consideration of all pairwise interactions. To better reflect biological interactions, we introduce negative-aware attention, which models both excitatory and inhibitory interactions, capturing essential negative relationships that standard attention often overlooks. Furthermore, to mitigate the information loss from truncated or ignored context in standard spot image extraction, we introduce an off-grid sampling strategy that gathers additional images from intermediate regions, allowing the model to capture a richer morphological context. Experiments on public ST datasets show that FEAST surpasses state-of-the-art methods in gene expression prediction while providing biologically plausible attention maps that clarify positive and negative interactions. Our code is available at https://github.com/starforTJ/ FEAST.

☆ Efficient Preemptive Robustification with Image Sharpening

Jiaming Liang, Chi-Man Pun

Despite their great success, deep neural networks rely on high-dimensional, non-robust representations, making them vulnerable to imperceptible perturbations, even in transfer scenarios. To address this, both training-time defenses (e.g., adversarial training and robust architecture design) and post-attack defenses (e.g., input purification and adversarial detection) have been extensively studied. Recently, a limited body of work has preliminarily explored a pre-attack defense paradigm, termed preemptive robustification, which introduces subtle modifications to benign samples prior to attack to proactively resist adversarial perturbations. Unfortunately, their practical applicability remains questionable due to several limitations, including (1) reliance on well-trained classifiers as surrogates to provide robustness priors, (2) substantial computational overhead arising from iterative optimization or trained generators for robustification, and (3) limited interpretability of the optimization- or generation-based robustification processes. Inspired by recent studies revealing a positive correlation between texture intensity and the robustness of benign samples, we show that image sharpening alone can efficiently robustify images. To the best of our knowledge, this is the first surrogate-free, optimization-free, generator-free, and human-interpretable robustification approach. Extensive experiments demonstrate that sharpening yields remarkable robustness gains with low computational cost, especially in transfer scenarios.

☆ A Unified Spatial Alignment Framework for Highly Transferable Transformation-Based Attacks on Spatially Structured Tasks

Jiaming Liang, Chi-Man Pun

Transformation-based adversarial attacks (TAAs) demonstrate strong transferability when deceiving classification models. However, existing TAAs often perform unsatisfactorily or even fail when applied to structured tasks such as semantic segmentation and object detection. Encouragingly, recent studies that categorize transformations into non-spatial and spatial transformations inspire us to address this challenge. We find that for non-structured tasks, labels are spatially non-structured, and thus TAAs are not required to adjust labels when applying spatial transformations. In contrast, for structured tasks, labels are spatially structured, and failing to transform labels synchronously with inputs can cause spatial misalignment and yield erroneous gradients. To address these issues, we propose a novel unified Spatial Alignment Framework (SAF) for highly transferable TAAs on spatially structured tasks, where the TAAs spatially transform labels synchronously with the input using the proposed Spatial Alignment (SA) algorithm. Extensive experiments demonstrate the crucial role of our SAF for TAAs on structured tasks. Specifically, in non-targeted attacks, our SAF degrades the average mIoU on Cityscapes from 24.50 to 11.34, and on Kvasir-SEG from 49.91 to 31.80, while reducing the average mAP of COCO from 17.89 to 5.25.

☆ An Image Dataset of Common Skin Diseases of Bangladesh and Benchmarking Performance with Machine Learning Models

Sazzad Hossain, Saiful Islam, Muhammad Ibrahim, Md. Rasel Ahmed, Md Shuayb, Ahmedul Kabir

Skin diseases are a major public health concern worldwide, and their detection is often challenging without access to dermatological expertise. In countries like Bangladesh, which is highly populated, the number of qualified skin specialists and diagnostic instruments is insufficient to meet the demand. Due to the lack of proper detection and treatment of skin diseases, that may lead to severe health consequences including death. Common properties of skin diseases are, changing the color, texture, and pattern of skin and in this era of artificial intelligence and machine learning, we are able to detect skin diseases by using image processing and computer vision techniques. In response to this challenge, we develop a publicly available dataset focused on common skin disease detection using machine learning techniques. We focus on five prevalent skin diseases in Bangladesh: Contact Dermatitis, Vitiligo, Eczema, Scabies, and Tinea Ringworm. The dataset consists of 1612 images (of which, 250 are distinct while others are augmented), collected directly from patients at the outpatient department of Faridpur Medical College, Faridpur, Bangladesh. The data comprises of 302, 381, 301, 316, and 312 images of Dermatitis, Eczema, Scabies, Tinea Ringworm, and Vitiligo, respectively. Although the data are collected regionally, the selected diseases are common across many countries especially in South Asia, making the dataset potentially valuable for global applications in machine learning-based dermatology. We also apply several machine learning and deep learning models on the dataset and report classification performance. We expect that this research would garner attention from machine learning and deep learning researchers and practitioners working in the field of automated disease diagnosis.

comment: 14 pages

☆ Training-free Detection and 6D Pose Estimation of Unseen Surgical Instruments

Jonas Hein, Lilian Calvet, Matthias Seibold, Siyu Tang, Marc Pollefeys, Philipp Fürnstahl

Purpose: Accurate detection and 6D pose estimation of surgical instruments are crucial for many computer-assisted interventions. However, supervised methods lack flexibility for new or unseen tools and require extensive annotated data. This work introduces a training-free pipeline for accurate multi-view 6D pose estimation of unseen surgical instruments, which only requires a textured CAD model as prior knowledge. Methods: Our pipeline consists of two main stages. First, for detection, we generate object mask proposals in each view and score their similarity to rendered templates using a pre-trained feature extractor. Detections are matched across views, triangulated into 3D instance candidates, and filtered using multi-view geometric consistency. Second, for pose estimation, a set of pose hypotheses is iteratively refined and scored using feature-metric scores with cross-view attention. The best hypothesis undergoes a final refinement using a novel multi-view, occlusion-aware contour registration, which minimizes reprojection errors of unoccluded contour points. Results: The proposed method was rigorously evaluated on real-world surgical data from the MVPSP dataset. The method achieves millimeter-accurate pose estimates that are on par with supervised methods under controlled conditions, while maintaining full generalization to unseen instruments. These results demonstrate the feasibility of training-free, marker-less detection and tracking in surgical scenes, and highlight the unique challenges in surgical environments. Conclusion: We present a novel and flexible pipeline that effectively combines state-of-the-art foundational models, multi-view geometry, and contour-based refinement for high-accuracy 6D pose estimation of surgical instruments without task-specific training. This approach enables robust instrument tracking and scene understanding in dynamic clinical environments.

comment: Accepted at IJCARS: IPCAI 2026

☆ SDD-YOLO: A Small-Target Detection Framework for Ground-to-Air Anti-UAV Surveillance with Edge-Efficient Deployment

Pengyu Chen, Haotian Sa, Yiwei Hu, Yuhan Cheng, Junbo Wang

Detecting small unmanned aerial vehicles (UAVs) from a ground-to-air (G2A) perspective presents significant challenges, including extremely low pixel occupancy, cluttered aerial backgrounds, and strict real-time constraints. Existing YOLO-based detectors are primarily optimized for general object detection and often lack adequate feature resolution for sub-pixel targets, while introducing complexities during deployment. In this paper, we propose SDD-YOLO, a small-target detection framework tailored for G2A anti-UAV surveillance. To capture fine-grained spatial details critical for micro-targets, SDD-YOLO introduces a P2 high-resolution detection head operating at 4 times downsampling. Furthermore, we integrate the recent architectural advancements from YOLO26, including a DFL-free, NMS-free architecture for streamlined inference, and the MuSGD hybrid training strategy with ProgLoss and STAL, which substantially mitigates gradient oscillation on sparse small-target signals. To support our evaluation, we construct DroneSOD-30K, a large-scale G2A dataset comprising approximately 30,000 annotated images covering diverse meteorological conditions. Experiments demonstrate that SDD-YOLO-n achieves a mAP@0.5 of 86.0% on DroneSOD-30K, surpassing the YOLOv5n baseline by 7.8 percentage points. Extensive inference analysis shows our model attains 226 FPS on an NVIDIA RTX 5090 and 35 FPS on an Intel Xeon CPU, demonstrating exceptional efficiency for future edge deployment.

☆ Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction

Jiahao Tian, Chenxi Song, Wei Cheng, Chi Zhang

Generating long videos using pre-trained video diffusion models, which are typically trained on short clips, presents a significant challenge. Directly applying these models for long-video inference often leads to a notable degradation in visual quality. This paper identifies that this issue primarily stems from two out-of-distribution (O.O.D) problems: frame-level relative position O.O.D and context-length O.O.D. To address these challenges, we propose FreeLOC, a novel training-free, layer-adaptive framework that introduces two core techniques: Video-based Relative Position Re-encoding (VRPR) for frame-level relative position O.O.D, a multi-granularity strategy that hierarchically re-encodes temporal relative positions to align with the model's pre-trained distribution, and Tiered Sparse Attention (TSA) for context-length O.O.D, which preserves both local detail and long-range dependencies by structuring attention density across different temporal scales. Crucially, we introduce a layer-adaptive probing mechanism that identifies the sensitivity of each transformer layer to these O.O.D issues, allowing for the selective and efficient application of our methods. Extensive experiments demonstrate that our approach significantly outperforms existing training-free methods, achieving state-of-the-art results in both temporal consistency and visual quality. Code is available at https://github.com/Westlake-AGI-Lab/FreeLOC.

comment: Accepted to CVPR 2026. Code: https://github.com/Westlake-AGI-Lab/FreeLOC

☆ Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection

Ruichao Yang, Wei Gao, Xiaobin Zhu, Jing Ma, Hongzhan Lin, Ziyang Luo, Bo-Wen Zhang, Xu-Cheng Yin

Multimodal misinformation poses an escalating challenge that often evades traditional detectors, which are opaque black boxes and fragile against new manipulation tactics. We present Probabilistic Concept Graph Reasoning (PCGR), an interpretable and evolvable framework that reframes multimodal misinformation detection (MMD) as structured and concept-based reasoning. PCGR follows a build-then-infer paradigm, which first constructs a graph of human-understandable concept nodes, including novel high-level concepts automatically discovered and validated by multimodal large language models (MLLMs), and then applies hierarchical attention over this concept graph to infer claim veracity. This design produces interpretable reasoning chains linking evidence to conclusions. Experiments demonstrate that PCGR achieves state-of-the-art MMD accuracy and robustness to emerging manipulation types, outperforming prior methods in both coarse detection and fine-grained manipulation recognition.

comment: Accepted by CVPR 2026

☆ CIV-DG: Conditional Instrumental Variables for Domain Generalization in Medical Imaging

Shaojin Bai, Yuting Su, Weizhi Nie

Cross-site generalizability in medical AI is fundamentally compromised by selection bias, a structural mechanism where patient demographics (e.g., age, severity) non-randomly dictate hospital assignment. Conventional Domain Generalization (DG) paradigms, which predominantly target image-level distribution shifts, fail to address the resulting spurious correlations between site-specific variations and diagnostic labels. To surmount this identifiability barrier, we propose CIV-DG, a causal framework that leverages Conditional Instrumental Variables to disentangle pathological semantics from scanner-induced artifacts. By relaxing the strict random assignment assumption of standard IV methods, CIV-DG accommodates complex clinical scenarios where hospital selection is endogenously driven by patient demographics. We instantiate this theory via a Deep Generalized Method of Moments (DeepGMM) architecture, employing a conditional critic to minimize moment violations and enforce instrument-error orthogonality within demographic strata. Extensive experiments on the Camelyon17 benchmark and large-scale Chest X-Ray datasets demonstrate that CIV-DG significantly outperforms leading baselines, validating the efficacy of conditional causal mechanisms in resolving structural confounding for robust medical AI.

comment: 10 pages, 2 figures

☆ TacSIm: A Dataset and Benchmark for Football Tactical Style Imitation

Peng Wen, Yuting Wang, Qiurui Wang

Current football imitation research primarily aims to opti mize reward-based objectives, such as goals scored or win rate proxies, paying less attention to accurately replicat ing real-world team tactical behaviors. We introduce Tac SIm, a large-scale dataset and benchmark for Tactical Style Imitation in football. TacSIm imitates the acitons of all 11 players in one team in the given broadcast footage of Pre mier League matches under a single broadcast view. Under a offensive or defensive broadcast footage, TacSIm projects the beginning positions and actions of all 22 players from both sides onto a standard pitch coordinate system. Tac SIm offers an explicit style imitation task and evaluation protocols. Tactics style imitation is measured by using spatial occupancy similarity and movement vector similarity in defined time, supporting the evaluation of spatial and tem poral similarities for one team. We run multiple baseline methods in a unified virtual environment to generate full team behaviors, enabling both quantitative and visual as sessment of tactical coordination. By using unified data and metrics from broadcast to simulation, TacSIm estab lishes a rigorous benchmark for measuring and modeling style-aligned tactical imitation task in football.

comment: Accepted to CVPR 2026

☆ CardioDiT: Latent Diffusion Transformers for 4D Cardiac MRI Synthesis

Marvin Seyfarth, Sarah Kaye Müller, Arman Ghanaat, Isabelle Ayx, Fabian Fastenrath, Philipp Wild, Alexander Hertel, Theano Papavassiliu, Salman Ul Hassan Dar, Sandy Engelhardt

Latent diffusion models (LDMs) have recently achieved strong performance in 3D medical image synthesis. However, modalities like cine cardiac MRI (CMR), representing a temporally synchronized 3D volume across the cardiac cycle, add an additional dimension that most generative approaches do not model directly. Instead, they factorize space and time or enforce temporal consistency through auxiliary mechanisms such as anatomical masks. Such strategies introduce structural biases that may limit global context integration and lead to subtle spatiotemporal discontinuities or physiologically inconsistent cardiac dynamics. We investigate whether a unified 4D generative model can learn continuous cardiac dynamics without architectural factorization. We propose CardioDiT, a fully 4D latent diffusion framework for short-axis cine CMR synthesis based on diffusion transformers. A spatiotemporal VQ-VAE encodes 2D+t slices into compact latents, which a diffusion transformer then models jointly as complete 3D+t volumes, coupling space and time throughout the generative process. We evaluate CardioDiT on public CMR datasets and a larger private cohort, comparing it to baselines with progressively stronger spatiotemporal coupling. Results show improved inter-slice consistency, temporally coherent motion, and realistic cardiac function distributions, suggesting that explicit 4D modeling with a diffusion transformer provides a principled foundation for spatiotemporal cardiac image synthesis. Code and models trained on public data are available at https://github.com/Cardio-AI/cardiodit.

☆ AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References

Jiahao Wang, Hualian Sheng, Sijia Cai, Yuxiao Yang, Weizhan Zhang, Caixia Yan, Bing Deng, Jieping Ye

Identity-preserving video generation offers powerful tools for creative expression, allowing users to customize videos featuring their beloved characters. However, prevailing methods are typically designed and optimized for a single identity reference. This underlying assumption restricts creative flexibility by inadequately accommodating diverse real-world input formats. Relying on a single source also constitutes an ill-posed scenario, causing an inherently ambiguous setting that makes it difficult for the model to faithfully reproduce an identity across novel contexts. To address these issues, we present AnyID, an ultra-fidelity identity-preservation video generation framework that features two core contributions. First, we introduce a scalable omni-referenced architecture that effectively unifies heterogeneous identity inputs (e.g., faces, portraits, and videos) into a cohesive representation. Second, we propose a primary-referenced generation paradigm, which designates one reference as a canonical anchor and uses a novel differential prompt to enable precise, attribute-level controllability. We conduct training on a large-scale, meticulously curated dataset to ensure robustness and high fidelity, and then perform a final fine-tuning stage using reinforcement learning. This process leverages a preference dataset constructed from human evaluations, where annotators performed pairwise comparisons of videos based on two key criteria: identity fidelity and prompt controllability. Extensive evaluations validate that AnyID achieves ultra-high identity fidelity as well as superior attribute-level controllability across different task settings.

☆ VolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers

Marvin Seyfarth, Salman Ul Hassan Dar, Yannik Frisch, Philipp Wild, Norbert Frey, Florian André, Sandy Engelhardt

Diffusion models have become a leading approach for high-fidelity medical image synthesis. However, most existing methods for 3D medical image generation rely on convolutional U-Net backbones within latent diffusion frameworks. While effective, these architectures impose strong locality biases and limited receptive fields, which may constrain scalability, global context integration, and flexible conditioning. In this work, we introduce VolDiT, the first purely transformer-based 3D Diffusion Transformer for volumetric medical image synthesis. Our approach extends diffusion transformers to native 3D data through volumetric patch embeddings and global self-attention operating directly over 3D tokens. To enable structured control, we propose a timestep-gated control adapter that maps segmentation masks into learnable control tokens that modulate transformer layers during denoising. This token-level conditioning mechanism allows precise spatial guidance while preserving the modeling advantages of transformer architectures. We evaluate our model on high-resolution 3D medical image synthesis tasks and compare it to state-of-the-art 3D latent diffusion models based on U-Nets. Results demonstrate improved global coherence, superior generative fidelity, and enhanced controllability. Our findings suggest that fully transformerbased diffusion models provide a flexible foundation for volumetric medical image synthesis. The code and models trained on public data are available at https://github.com/Cardio-AI/voldit.

☆ Bilingual Text-to-Motion Generation: A New Benchmark and Baselines

Wanjiang Weng, Xiaofeng Tan, Xiangbo Shu, Guo-Sen Xie, Pan Zhou, Hongsong Wang

Text-to-motion generation holds significant potential for cross-linguistic applications, yet it is hindered by the lack of bilingual datasets and the poor cross-lingual semantic understanding of existing language models. To address these gaps, we introduce BiHumanML3D, the first bilingual text-to-motion benchmark, constructed via LLM-assisted annotation and rigorous manual correction. Furthermore, we propose a simple yet effective baseline, Bilingual Motion Diffusion (BiMD), featuring Cross-Lingual Alignment (CLA). CLA explicitly aligns semantic representations across languages, creating a robust conditional space that enables high-quality motion generation from bilingual inputs, including zero-shot code-switching scenarios. Extensive experiments demonstrate that BiMD with CLA achieves an FID of 0.045 vs. 0.169 and R@3 of 82.8\% vs. 80.8\%, significantly outperforms monolingual diffusion models and translation baselines on BiHumanML3D, underscoring the critical necessity and reliability of our dataset and the effectiveness of our alignment strategy for cross-lingual motion synthesis. The dataset and code are released at \href{https://wengwanjiang.github.io/BilingualT2M-page}{https://wengwanjiang.github.io/BilingualT2M-page}

comment: 11 pages, 7 figures

☆ AG-EgoPose: Leveraging Action-Guided Motion and Kinematic Joint Encoding for Egocentric 3D Pose Estimation

Md Mushfiqur Azam, John Quarles, Kevin Desai

Egocentric 3D human pose estimation remains challenging due to severe perspective distortion, limited body visibility, and complex camera motion inherent in first-person viewpoints. Existing methods typically rely on single-frame analysis or limited temporal fusion, which fails to effectively leverage the rich motion context available in egocentric videos. We introduce AG-EgoPose, a novel dual-stream framework that integrates short- and long-range motion context with fine-grained spatial cues for robust pose estimation from fisheye camera input. Our framework features two parallel streams: A spatial stream uses a weight-sharing ResNet-18 encoder-decoder to generate 2D joint heatmaps and corresponding joint-specific spatial feature tokens. Simultaneously, a temporal stream uses a ResNet-50 backbone to extract visual features, which are then processed by an action recognition backbone to capture the motion dynamics. These complementary representations are fused and refined in a transformer decoder with learnable joint tokens, which allows for the joint-level integration of spatial and temporal evidence while maintaining anatomical constraints. Experiments on real-world datasets demonstrate that AG-EgoPose achieves state-of-the-art performance in both quantitative and qualitative metrics. Code is available at: https://github.com/Mushfiq5647/AG-EgoPose.

☆ Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling

Shiji Zhao, Shukun Xiong, Maoxun Yuan, Yao Huang, Ranjie Duan, Qing Guo, Jiansheng Chen, Haibin Duan, Xingxing Wei

In complex environments, infrared object detection exhibits broad applicability and stability across diverse scenarios. However, infrared object detection is vulnerable to both common corruptions and adversarial examples, leading to potential security risks. To improve the robustness of infrared object detection, current methods mostly adopt a data-driven ideology, which only superficially drives the network to fit the training data without specifically considering the unique characteristics of infrared images, resulting in limited robustness. In this paper, we revisit infrared physical knowledge and find that relative thermal radiation relations between different classes can be regarded as a reliable knowledge source under the complex scenarios of adversarial examples and common corruptions. Thus, we theoretically model thermal radiation relations based on the rank order of gray values for different classes, and further quantify the stability of various inter-class thermal radiation relations. Based on the above theoretical framework, we propose Knowledge-Guided Adversarial Training (KGAT) for infrared object detection, in which infrared physical knowledge is embedded into the adversarial training process, and the predicted results are optimized to be consistent with the actual physical laws. Extensive experiments on three infrared datasets and six mainstream infrared object detection models demonstrate that KGAT effectively enhances both clean accuracy and robustness against adversarial attacks and common corruptions.

comment: Accepted for publication in the International Journal of Computer Vision (IJCV)

☆ ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis

Xike Zhang, Maoyuan Ye, Juhua Liu, Bo Du

Previous works based on Segment Anything Model (SAM) have achieved promising performance in unified scene text detection and layout analysis. However, the typical reliance on pixel-level text segmentation for sampling thousands of foreground points as prompts leads to unsatisfied inference latency and limited data utilization. To address above issues, we propose ET-SAM, an Efficient framework with two decoders for unified scene Text detection and layout analysis based on SAM. Technically, we customize a lightweight point decoder that produces word heatmaps for achieving a few foreground points, thereby eliminating excessive point prompts and accelerating inference. Without the dependence on pixel-level segmentation, we further design a joint training strategy to leverage existing data with heterogeneous text-level annotations. Specifically, the datasets with multi-level, word-level only, and line-level only annotations are combined in parallel as a unified training set. For these datasets, we introduce three corresponding sets of learnable task prompts in both the point decoder and hierarchical mask decoder to mitigate discrepancies across datasets.Extensive experiments demonstrate that, compared to the previous SAM-based architecture, ET-SAM achieves about 3$\times$ inference acceleration while obtaining competitive performance on HierText, and improves an average of 11.0% F-score on Total-Text, CTW1500, and ICDAR15.

comment: 20 pages, 8 figures, 8 tables. Submitted to ECCV 2026

☆ Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds

Bin Yang, Mohamed Abdelsamad, Miao Zhang, Alexandru Paul Condurache

comment: The paper was accepted by CVPR2026

☆ SportSkills: Physical Skill Learning from Sports Instructional Videos

Kumar Ashutosh, Chi Hsuan Wu, Kristen Grauman

Current large-scale video datasets focus on general human activity, but lack depth of coverage on fine-grained activities needed to address physical skill learning. We introduce SportSkills, the first large-scale sports dataset geared towards physical skill learning with in-the-wild video. SportSkills has more than 360k instructional videos containing more than 630k visual demonstrations paired with instructional narrations explaining the know-how behind the actions from 55 varied sports. Through a suite of experiments, we show that SportSkills unlocks the ability to understand fine-grained differences between physical actions. Our representation achieves gains of up to 4x with the same model trained on traditional activity-centric datasets. Crucially, building on SportSkills, we introduce the first large-scale task formulation of mistake-conditioned instructional video retrieval, bridging representation learning and actionable feedback generation (e.g., "here's my execution of a skill; which video clip should I watch to improve it?"). Formal evaluations by professional coaches show our retrieval approach significantly advances the ability of video models to personalize visual instructions for a user query.

comment: Technical report

☆ A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection

SuYeon Kim, Wongyu Lee, MyeongAh Cho

3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data. While a unified model improves scalability by learning across multiple categories, it often suffers from Inter-Category Entanglement (ICE)-where latent features from different categories overlap, causing the model to adopt incorrect semantic priors during reconstruction and ultimately yielding unreliable anomaly scores. To address this issue, we propose the Semantically Disentangled Unified Model for 3D Anomaly Detection, which reconstructs features conditioned on disentangled semantic representations. Our framework consists of three key components: (i) Coarse-to-Fine Global Tokenization for forming instance-level semantic identity, (ii) Category-Conditioned Contrastive Learning for disentangling category semantics, and (iii) a Geometry-Guided Decoder for semantically consistent reconstruction. Extensive experiments on Real3D-AD and Anomaly-ShapeNet demonstrate that our method achieves state-of-the-art for both unified and category-specific models, improving object-level AUROC by 2.8% and 9.1%, respectively, while enhancing the reliability of unified 3D anomaly detection.

comment: Accepted by CVPR 2026

☆ Vision Hopfield Memory Networks

Jianfeng Wang, Amine M'Charrak, Luk Koska, Xiangtao Wang, Daniel Petriceanu, Mykyta Smyrnov, Ruizhi Wang, Michael Bumbar, Luca Pinchetti, Thomas Lukasiewicz

Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, enabling unified modeling across images, text, and beyond. Despite their empirical success, these architectures remain far from the computational principles of the human brain, often demanding enormous amounts of training data while offering limited interpretability. In this work, we propose the Vision Hopfield Memory Network (V-HMN), a brain-inspired foundation backbone that integrates hierarchical memory mechanisms with iterative refinement updates. Specifically, V-HMN incorporates local Hopfield modules that provide associative memory dynamics at the image patch level, global Hopfield modules that function as episodic memory for contextual modulation, and a predictive-coding-inspired refinement rule for iterative error correction. By organizing these memory-based modules hierarchically, V-HMN captures both local and global dynamics in a unified framework. Memory retrieval exposes the relationship between inputs and stored patterns, making decisions more interpretable, while the reuse of stored patterns improves data efficiency. This brain-inspired design therefore enhances interpretability and data efficiency beyond existing self-attention- or state-space-based approaches. We conducted extensive experiments on public computer vision benchmarks, and V-HMN achieved competitive results against widely adopted backbone architectures, while offering better interpretability, higher data efficiency, and stronger biological plausibility. These findings highlight the potential of V-HMN to serve as a next-generation vision foundation model, while also providing a generalizable blueprint for multimodal backbones in domains such as text and audio, thereby bridging brain-inspired computation with large-scale machine learning.

☆ Photon: Speedup Volume Understanding with Efficient Multimodal Large Language Models ICLR 2026

Chengyu Fang, Heng Guo, Zheng Jiang, Chunming He, Xiu Li, Minfeng Xu

Multimodal large language models are promising for clinical visual question answering tasks, but scaling to 3D imaging is hindered by high computational costs. Prior methods often rely on 2D slices or fixed-length token compression, disrupting volumetric continuity and obscuring subtle findings. We present Photon, a framework that represents 3D medical volumes with token sequences of variable length. Photon introduces instruction-conditioned token scheduling and surrogate gradient propagation to adaptively reduce tokens during both training and inference, which lowers computational cost while mitigating the attention dilution caused by redundant tokens. It incorporates a custom backpropagation rule with gradient restoration to enable differentiable optimization despite discrete token drop. To stabilize token compression and ensure reliable use of visual evidence, Photon further applies regularization objectives that mitigate language-only bias and improve reliability. Experiments on diverse medical visual question answering tasks show that Photon achieves state-of-the-art accuracy while reducing resource usage and accelerating both training and inference.

comment: Accepted by ICLR 2026

☆ Learning to Rank Caption Chains for Video-Text Alignment

Ansel Blume, Burak Uzkent, Shalini Chaudhuri, Garin Kessler

Direct preference optimization (DPO) is an effective technique to train language models to generate preferred over dispreferred responses. However, this binary "winner-takes-all" approach is suboptimal for vision-language models whose response quality is highly dependent on visual content. In particular, a response may still be faithful to the visual inputs even if it is less preferable than an alternative. The standard Bradley-Terry DPO formulation lacks this nuance, upweighting winning responses without sufficient regard for whether the "losing" response still maintains high visual fidelity. In this work, we investigate ranking optimization as an alternative that more precisely situates responses' faithfulness to visual inputs. We focus on video-text alignment using detailed video captions, proposing a method to generate challenging, totally ordered caption chains at scale through repeated caption degradation. Our results show ranking optimization outperforms binary DPO for long-form content generation and assessment, and importantly, we find that these approaches require finetuning of the vision encoder to be effective, challenging the view of DPO as purely a language-reweighting process.

☆ FD$^2$: A Dedicated Framework for Fine-Grained Dataset Distillation

Hongxu Ma, Guang Li, Shijie Wang, Dongzhan Zhou, Baoli Sun, Takahiro Ogawa, Miki Haseyama, Zhihui Wang

Dataset distillation (DD) compresses a large training set into a small synthetic set, reducing storage and training cost, and has shown strong results on general benchmarks. Decoupled DD further improves efficiency by splitting the pipeline into pretraining, sample distillation, and soft-label generation. However, existing decoupled methods largely rely on coarse class-label supervision and optimize samples within each class in a nearly identical manner. On fine-grained datasets, this often yields distilled samples that (i) retain large intra-class variation with subtle inter-class differences and (ii) become overly similar within the same class, limiting localized discriminative cues and hurting recognition. To solve the above-mentioned problems, we propose FD$^{2}$, a dedicated framework for Fine-grained Dataset Distillation. FD$^{2}$ localizes discriminative regions and constructs fine-grained representations for distillation. During pretraining, counterfactual attention learning aggregates discriminative representations to update class prototypes. During distillation, a fine-grained characteristic constraint aligns each sample with its class prototype while repelling others, and a similarity constraint diversifies attention across same-class samples. Experiments on multiple fine-grained and general datasets show that FD$^{2}$ integrates seamlessly with decoupled DD and improves performance in most settings, indicating strong transferability.

☆ SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment

Sahibzada Adil Shahzad, Ammarah Hashmi, Junichi Yamagishi, Yusuke Yasuda, Yu Tsao, Chia-Wen Lin, Yan-Tsung Peng, Hsin-Min Wang

☆ EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions

Taegyoon Yoon, Yegyu Han, Seojin Ji, Jaewoo Park, Sojeong Kim, Taein Kwon, Hyung-Sin Kim

Smart glass is emerging as an useful device since it provides plenty of insights under hands-busy, eyes-on-task situations. To understand the context of the wearer, 6D object pose estimation in egocentric view is becoming essential. However, existing 6D object pose estimation benchmarks fail to capture the challenges of real-world egocentric applications, which are often dominated by severe motion blur, dynamic illumination, and visual obstructions. This discrepancy creates a significant gap between controlled lab data and chaotic real-world application. To bridge this gap, we introduce EgoXtreme, a new large-scale 6D pose estimation dataset captured entirely from an egocentric perspective. EgoXtreme features three challenging scenarios - industrial maintenance, sports, and emergency rescue - designed to introduce severe perceptual ambiguities through extreme lighting, heavy motion blur, and smoke. Evaluations of state-of-the-art generalizable pose estimators on EgoXtreme indicate that their generalization fails to hold in extreme conditions, especially under low light. We further demonstrate that simply applying image restoration (e.g., deblurring) offers no positive improvement for extreme conditions. While performance gain has appeared in tracking-based approach, implying using temporal information in fast-motion scenarios is meaningful. We conclude that EgoXtreme is an essential resource for developing and evaluating the next generation of pose estimation models robust enough for real-world egocentric vision. The dataset and code are available at https://taegyoun88.github.io/EgoXtreme/

comment: Camera ready version for CVPR 2026, appendix included

☆ Robust Principal Component Completion

Yinjian Wang, Wei Li, Yuanyuan Gui, James E. Fowler, Gemine Vivone

Robust principal component analysis (RPCA) seeks a low-rank component and a sparse component from their summation. Yet, in many applications of interest, the sparse foreground actually replaces, or occludes, elements from the low-rank background. To address this mismatch, a new framework is proposed in which the sparse component is identified indirectly through determining its support. This approach, called robust principal component completion (RPCC), is solved via variational Bayesian inference applied to a fully probabilistic Bayesian sparse tensor factorization. Convergence to a hard classifier for the support is shown, thereby eliminating the post-hoc thresholding required of most prior RPCA-driven approaches. Experimental results reveal that the proposed approach delivers near-optimal estimates on synthetic data as well as robust foreground-extraction and anomaly-detection performance on real color video and hyperspectral datasets, respectively. Source implementation and Appendices are available at https://github.com/WongYinJ/BCP-RPCC.

☆ Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentation

Yaowen Chang, Zhen Cao, Xu Zheng, Xiaoxin Mi, Zhen Dong

Panoramic semantic segmentation is pivotal for comprehensive 360° scene understanding in critical applications like autonomous driving and virtual reality. However, progress in this domain is constrained by two key challenges: the severe geometric distortions inherent in panoramic projections and the prohibitive cost of dense annotation. While Unsupervised Domain Adaptation (UDA) from label-rich pinhole-camera datasets offers a viable alternative, many real-world tasks impose a stricter source-free (SFUDA) constraint where source data is inaccessible for privacy or proprietary reasons. This constraint significantly amplifies the core problems of domain shift, leading to unreliable pseudo-labels and dramatic performance degradation, particularly for minority classes. To overcome these limitations, we propose the DAPASS framework. DAPASS introduces two synergistic modules to robustly transfer knowledge without source data. First, our Panoramic Confidence-Guided Denoising (PCGD) module generates high-fidelity, class-balanced pseudo-labels by enforcing perturbation consistency and incorporating neighborhood-level confidence to filter noise. Second, a Contextual Resolution Adversarial Module (CRAM) explicitly addresses scale variance and distortion by adversarially aligning fine-grained details from high-resolution crops with global semantics from low-resolution contexts. DAPASS achieves state-of-the-art performances on outdoor (Cityscapes-to-DensePASS) and indoor (Stanford2D3D) benchmarks, yielding 55.04% (+2.05%) and 70.38% (+1.54%) mIoU, respectively.

comment: Accepted to CVPR26

☆ PixelSmile: Toward Fine-Grained Facial Expression Editing

Jiabin Hua, Hengyuan Xu, Aojie Li, Wei Cheng, Gang Yu, Xingjun Ma, Yu-Gang Jiang

comment: 21 Pages; Project Page: https://ammmob.github.io/PixelSmile/ Code: https://github.com/Ammmob/PixelSmile

♻ ☆ Hyper-Connections for Adaptive Multi-Modal MRI Brain Tumor Segmentation

Lokendra Kumar, Shubham Aggarwal

We present the first study of Hyper-Connections (HC) for volumetric multi-modal brain tumor segmentation, integrating them as a drop-in replacement for fixed residual connections across five architectures: nnU-Net, SwinUNETR, VT-UNet, U-Net, and U-Netpp. Dynamic HC consistently improves all 3D models on the BraTS 2021 dataset, yielding up to +1.03 percent mean Dice gain with negligible parameter overhead. Gains are most pronounced in the Enhancing Tumor sub-region, reflecting improved fine-grained boundary delineation. Modality ablation further reveals that HC-equipped models develop sharper sensitivity toward clinically dominant sequences, specifically T1ce for Tumor Core and Enhancing Tumor, and FLAIR for Whole Tumor, a behavior absent in fixed-connection baselines and consistent across all architectures. In 2D settings, improvements are smaller and configuration-sensitive, suggesting that volumetric spatial context amplifies the benefit of adaptive aggregation. These results establish HC as a simple, efficient, and broadly applicable mechanism for multi-modal feature fusion in medical image segmentation.

comment: 29 pages,6 tables,17 figures

♻ ☆ The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition

Yuwen Tan, Yuan Qing, Boqing Gong

This paper reveals that many open-source large language models (LLMs) lack hierarchical knowledge about our visual world, unaware of even well-established biology taxonomies. This shortcoming makes LLMs a bottleneck for vision LLMs' hierarchical visual recognition (e.g., recognizing Anemone Fish but not Vertebrate). We arrive at these findings using about one million four-choice visual question answering (VQA) tasks constructed from six taxonomies and four image datasets. Interestingly, finetuning a vision LLM using our VQA tasks reaffirms LLMs' bottleneck effect because the VQA tasks improve the LLMs' hierarchical consistency more than the vision LLMs'. We conjecture that one cannot make open-source vision LLMs understand visual concepts hierarchically until LLMs possess corresponding taxonomy knowledge.

comment: Accepted to CVPR 2026. Project page and code: https://yuanqing-ai.github.io/llm-hierarchy/

♻ ☆ Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment

Roy Amoyal, Oren Freifeld, Chaim Baskin

We present Gaussian Splatting Alignment (GSA), a novel method for aligning two independent 3D Gaussian Splatting (3DGS) models via a similarity transformation (rotation, translation, and scale), even when they are of different objects in the same category (e.g., different cars). In contrast, existing methods can only align 3DGS models of the same object (e.g., the same car) and often must be given true scale as input, while we estimate it successfully. GSA leverages viewpoint-guided spherical map features to obtain robust correspondences and introduces a two-step optimization framework that aligns 3DGS models while keeping them fixed. First, we apply an iterative feature-guided absolute orientation solver as our coarse registration, which is robust to poor initialization (e.g., 180 degrees misalignment or a 10x scale gap). Next, we use a fine registration step that enforces multi-view feature consistency, inspired by inverse radiance-field formulations. The first step already achieves state-of-the-art performance, and the second further improves results. In the same-object case, GSA outperforms prior works, often by a large margin, even when the other methods are given the true scale. In the harder case of different objects in the same category, GSA vastly surpasses them, providing the first effective solution for category-level 3DGS registration and unlocking new applications. Project webpage: https://bgu-cs-vil.github.io/GSA-project/

comment: Accepted to CVPR 2026

♻ ☆ 3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds

Ryousuke Yamada, Kohsuke Ide, Yoshihiro Fukuhara, Hirokatsu Kataoka, Gilles Puy, Andrei Bursuc, Yuki M. Asano

Despite recent progress in 3D self-supervised learning, collecting large-scale 3D scene scans remains expensive and labor-intensive. In this work, we investigate whether 3D representations can be learned from unlabeled videos recorded without any real 3D sensors. We present Laplacian-Aware Multi-level 3D Clustering with Sinkhorn-Knopp (LAM3C), a self-supervised framework that learns from video-generated point clouds reconstructed from unlabeled videos. We first introduce RoomTours, a video-generated point cloud dataset constructed by collecting room-walkthrough videos from the web (e.g., real-estate tours) and generating 49,219 scenes using an off-the-shelf feed-forward reconstruction model. We also propose a noise-regularized loss that stabilizes representation learning by enforcing local geometric smoothness and ensuring feature stability under noisy point clouds. Remarkably, without using any real 3D scans, LAM3C achieves better performance than previous self-supervised methods on indoor semantic and instance segmentation. These results suggest that unlabeled videos represent an abundant source of data for 3D self-supervised learning. Our source code is available at https://ryosuke-yamada.github.io/lam3c/.

comment: Accepted to CVPR 2026. Project page: https://ryosuke-yamada.github.io/lam3c/

♻ ☆ ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference

Ali Hojjat, Janek Haberer, Soren Pirk, Olaf Landsiedel

ViTs deliver SOTA performance, yet their fixed computational budget prevents scalable deployment across heterogeneous hardware. Recent Matryoshka-style Transformer architectures mitigate this by embedding nested subnetworks within a single model to enable scalable inference. However, these models allocate the same amount of compute to all inputs, regardless of their complexity, which leads to inefficiencies. To address this, we introduce ThinkingViT, a nested ViT architecture that employs progressive thinking stages to dynamically adjust inference computation based on input difficulty. ThinkingViT first activates a small subset of the most important attention heads to produce an initial prediction. If the prediction confidence exceeds a predefined threshold, inference terminates early. Otherwise, within the same backbone, it activates a larger subset of attention heads and conducts a new forward pass. This process continues iteratively until the model reaches the predefined confidence level or exhausts its maximum capacity. To boost the performance of subsequent rounds, we introduce a Token Recycling approach that fuses the input embeddings with the embeddings from the previous stage. Experiments show that ThinkingViT surpasses nested baselines by up to 2.0 percentage points (p.p.) in accuracy at the same throughput and by up to 2.9 p.p. at equal GMACs on ImageNet-1K. We show that the backbone-preserving design of ThinkingViT allows it to serve as a plug-in upgrade for ViTs in downstream tasks such as semantic segmentation. We also demonstrate that ThinkingViT transfers effectively to other architectures such as Swin Transformers. The source code is available at https://github.com/ds-kiel/ThinkingViT.

comment: Accepted at CVPR'26, please cite the conference version

♻ ☆ Seeking Physics in Diffusion Noise

Chujun Tang, Lei Zhong, Fangqiang Ding

Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate denoising representations of a pretrained Diffusion Transformer (DiT) and find that physically plausible and implausible videos are partially separable in mid-layer feature space across noise levels. This separability cannot be fully attributed to visual quality or generator identity, suggesting recoverable physics-related cues in frozen DiT features. Leveraging this observation, we introduce progressive trajectory selection, an inference-time strategy that scores parallel denoising trajectories at a few intermediate checkpoints using a lightweight physics verifier trained on frozen features, and prunes low-scoring candidates early. Extensive experiments on PhyGenBench demonstrate that our method improves physical consistency while reducing inference cost, achieving comparable results to Best-of-K sampling with substantially fewer denoising steps.

comment: 32 pages, 8 figures, 10 tables

♻ ☆ GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis

Xuqin Wang, Tao Wu, Yanfeng Zhang, Lu Liu, Mingwei Sun, Yongliang Wang, Niclas Zeller, Daniel Cremers

Recent advances in generative modeling have substantially enhanced novel view synthesis, yet maintaining consistency across viewpoints remains challenging. Diffusion-based models rely on stochastic noise-to-data transitions, which obscure deterministic structures and yield inconsistent view predictions. We advocate a Data-to-Data Flow Matching framework that learns deterministic transformations between paired views, enhancing view-consistent synthesis through explicit data coupling. Building on this, we propose Probability Density Geodesic Flow Matching (PDG-FM), which aligns interpolation trajectories with density-based geodesics of a data manifold. To enable tractable geodesic estimation, we employ a teacher-student framework that distills density-based geodesic interpolants into an efficient ambient-space predictor. Empirically, our method surpasses diffusion-based baselines on Objaverse and GSO30 datasets, demonstrating improved structural coherence and smoother transitions across views. These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.

comment: Accepted by CVPR 2026; Project Page see https://xuqinwang.github.io/geodesicNVS.github.io/

♻ ☆ MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding

Yuhao Su, Anwesa Choudhuri, Zhongpai Gao, Benjamin Planche, Van Nguyen Nguyen, Meng Zheng, Yuhan Shen, Arun Innanje, Terrence Chen, Ehsan Elhamifar, Ziyan Wu

Large vision-language models struggle with medical video understanding, where spatial precision, temporal reasoning, and clinical semantics are critical. To address this, we first introduce \textbf{MedVidBench}, a large-scale benchmark of 531,850 video-instruction pairs across 8 medical sources spanning video, segment, and frame-level tasks, curated through a rigorous quality assurance pipeline with expert-guided prompting and dual-model validation. While supervised fine-tuning on MedVidBench yields noticeable gains, standard Reinforcement Learning (RL) fails due to imbalanced reward scales across datasets, which destabilizes optimization and leads to training collapse. To overcome this, we introduce \textbf{MedGRPO}, a novel RL framework for balanced multi-dataset training with two key innovations: (1) \emph{cross-dataset reward normalization} that maps each dataset's median performance to a common reward value, ensuring fair optimization regardless of difficulty, and (2) a \emph{medical LLM judge} that evaluates caption quality on five clinical dimensions through comparative similarity scoring. Supervised fine-tuning Qwen2.5-VL-7B on MedVidBench substantially outperforms GPT-4.1 and Gemini-2.5-Flash across all tasks, demonstrating MedVidBench's efficacy, while our MedGRPO framework further improves upon the SFT baseline across grounding and captioning tasks. Our work establishes a foundational benchmark and robust training methodology for advancing vision-language models in medical domains. Our project website is available at https://yuhaosu.github.io/MedGRPO/.

comment: Accepted at CVPR 2026

♻ ☆ HIFICL: High-Fidelity In-Context Learning for Multimodal Tasks

Xiaoyu Li, Yuhang Liu, Zheng Luo, Xuanshuo Kang, Fangqi Lou, Xiaohua Wu, Zihan Xiong

In-Context Learning (ICL) is a significant paradigm for Large Multimodal Models (LMMs), using a few in-context demonstrations (ICDs) for new task adaptation. However, its performance is sensitive to demonstration configurations and computationally expensive. Mathematically, the influence of these demonstrations can be decomposed into a dynamic mixture of the standard attention output and the context values. Current approximation methods simplify this process by learning a "shift vector". Inspired by the exact decomposition, we introduce High-Fidelity In-Context Learning (HIFICL) to more faithfully model the ICL mechanism. HIFICL consists of three key components: 1) a set of "virtual key-value pairs" to act as a learnable context, 2) a low-rank factorization for stable and regularized training, and 3) a simple end-to-end training objective. From another perspective, this mechanism constitutes a form of context-aware Parameter-Efficient Fine-Tuning (PEFT). Extensive experiments show that HiFICL consistently outperforms existing approximation methods on several multimodal benchmarks. The code is available at https://github.com/bbbandari/HiFICL.

comment: Accepted to CVPR 2026. Code available at https://github.com/bbbandari/HiFICL

♻ ☆ Closing the Navigation Compliance Gap in End-to-end Autonomous Driving

Hanfeng Wu, Marlon Steiner, Michael Schmidt, Alvaro Marcos-Ramiro, Christoph Stiller

Trajectory-scoring planners achieve high navigation compliance when following the expert's original command, yet they struggle at intersections when presented with alternative commands; over 30 percent of such commands are ignored. We attribute this navigation compliance gap to two root causes: (1) existing metrics like Ego Progress do not explicitly measure navigation adherence, diluting the gap between on-route and off-route trajectories; and (2) current datasets pair each scenario with a single command, preventing models from learning command-dependent behavior. We address the metric gap by introducing the binary Navigation Compliance metric (NAVI) and the derived Controllability Measure (CM), and the data gap with the NavControl dataset, 14,918 intersection scenarios augmented with all feasible alternative commands and routing annotations, yielding over 34,000 direction samples. Building on these, we propose NaviHydra, a trajectory-scoring planner incorporating NAVI distillation and Bird's Eye View (BEV)-based trajectory gathering for context-position-aware trajectory feature extraction. NaviHydra achieves 92.7 PDM score on NAVSIM navtest split and 77.5 CM on NavControl test split. Training with NavControl improves controllability across diverse architectures, confirming it as a broadly effective augmentation for navigation compliance.

♻ ☆ Verifier Threshold: An Efficient Test-Time Scaling Approach for Image Generation ICLR 2026

Vignesh Sundaresha, Akash Haridas, Vikram Appia, Lav R. Varshney

Image generation has emerged as a mainstream application of large generative models. Just as test-time compute and reasoning have improved language model capabilities, similar benefits have been observed for image generation models. In particular, searching over noise samples for diffusion and flow models has been shown to scale well with test-time compute. While recent works explore allocating non-uniform inference-compute budgets across denoising steps, existing approaches rely on greedy heuristics and often allocate the compute budget ineffectively. In this work, we study this problem and propose a simple fix. We propose Verifier-Threshold, which automatically reallocates test-time compute and delivers substantial efficiency improvements. For the same performance on the GenEval benchmark, we achieve a 2-4x reduction in computational time over the state-of-the-art method.

comment: ICLR 2026 ReALM-Gen and DeLTa

♻ ☆ 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction

Takeshi Noda, Yu-Shen Liu, Zhizhong Han

Rendering 3D surfaces has been revolutionized within the modeling of radiance fields through either 3DGS or NeRF. Although 3DGS has shown advantages over NeRF in terms of rendering quality or speed, there is still room for improvement in recovering high fidelity surfaces through 3DGS. To resolve this issue, we propose a self-constrained prior to constrain the learning of 3D Gaussians, aiming for more accurate depth rendering. Our self-constrained prior is derived from a TSDF grid that is obtained by fusing the depth maps rendered with current 3D Gaussians. The prior measures a distance field around the estimated surface, offering a band centered at the surface for imposing more specific constraints on 3D Gaussians, such as removing Gaussians outside the band, moving Gaussians closer to the surface, and encouraging larger or smaller opacity in a geometry-aware manner. More importantly, our prior can be regularly updated by the most recent depth images which are usually more accurate and complete. In addition, the prior can also progressively narrow the band to tighten the imposed constraints. We justify our idea and report our superiority over the state-of-the-art methods in evaluations on widely used benchmarks.

comment: Accepted by CVPR 2026. Project page: https://takeshie.github.io/GSPrior

♻ ☆ CompBench: Benchmarking Complex Instruction-guided Image Editing

Bohan Jia, Wenxuan Huang, Yuntian Tang, Junbo Qiao, Jincheng Liao, Shaosheng Cao, Fei Zhao, Zhaopeng Feng, Zhouhong Gu, Zhenfei Yin, Lei Bai, Wanli Ouyang, Lin Chen, Fei Zhao, Yao Hu, Zihan Wang, Yuan Xie, Shaohui Lin

While real-world applications increasingly demand intricate scene manipulation, existing instruction-guided image editing benchmarks often oversimplify task complexity and lack comprehensive, fine-grained instructions. To bridge this gap, we introduce CompBench, a large-scale benchmark specifically designed for complex instruction-guided image editing. CompBench features challenging editing scenarios that incorporate fine-grained instruction following, spatial and contextual reasoning, thereby enabling comprehensive evaluation of image editing models' precise manipulation capabilities. To construct CompBench, we propose an MLLM-human collaborative framework with tailored task pipelines. Furthermore, we propose an instruction decoupling strategy that disentangles editing intents into four key dimensions: location, appearance, dynamics, and objects, ensuring closer alignment between instructions and complex editing requirements. Extensive evaluations reveal that CompBench exposes fundamental limitations of current image editing models and provides critical insights for the development of next-generation instruction-guided image editing systems. Our project page is available at https://comp-bench.github.io/.

♻ ☆ Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs

Houston H. Zhang, Tao Zhang, Baoze Lin, Yuanqi Xue, Yincheng Zhu, Huan Liu, Li Gu, Linfeng Ye, Ziqiang Wang, Xinxin Zuo, Yang Wang, Yuanhao Yu, Zhixiang Chi

User interface to code (UI2Code) aims to generate executable code that can faithfully reconstruct a given input UI. Prior work focuses largely on web pages and mobile screens, leaving app widgets underexplored. Unlike web or mobile UIs with rich hierarchical context, widgets are compact, context-free micro-interfaces that summarize key information through dense layouts and iconography under strict spatial constraints. Moreover, while (image, code) pairs are widely available for web or mobile UIs, widget designs are proprietary and lack accessible markup. We formalize this setting as the Widget-to-Code (Widget2Code) and introduce an image-only widget benchmark with fine-grained, multi-dimensional evaluation metrics. Benchmarking shows that although generalized multimodal large language models (MLLMs) outperform specialized UI2Code methods, they still produce unreliable and visually inconsistent code. To address these limitations, we develop a baseline that jointly advances perceptual understanding and structured code generation. At the perceptual level, we follow widget design principles to assemble atomic components into complete layouts, equipped with icon retrieval and reusable visualization modules. At the system level, we design an end-to-end infrastructure, WidgetFactory, which includes a framework-agnostic widget-tailored domain-specific language (WidgetDSL) and a compiler that translates it into multiple front-end implementations (e.g., React, HTML/CSS). An adaptive rendering module further refines spatial dimensions to satisfy compactness constraints. Together, these contributions substantially enhance visual fidelity, establishing a strong baseline and unified infrastructure for future Widget2Code research.

comment: CVPR 2026, Code: https://github.com/Djanghao/widget2code

♻ ☆ Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting AAAI 2026

Giacomo Frisoni, Lorenzo Molfetta, Mattia Buzzoni, Gianluca Moro

Recent advances in training-free visual prompting, such as Set-of-Mark, have emerged as a promising direction for enhancing the grounding capabilities of multimodal language models (MLMs). These techniques operate by partitioning the input image into object regions and annotating them with marks, predominantly boxes with numeric identifiers, before feeding the augmented image to the MLM. However, these approaches treat marked objects as isolated entities, failing to capture the relationships between them. On these premises, we propose Graph-of-Mark (GoM), the first pixel-level visual prompting technique that overlays scene graphs onto the input image for spatial reasoning tasks. We evaluate GoM across 3 open-source MLMs and 4 different datasets, conducting extensive ablations on drawn components and investigating the impact of auxiliary graph descriptions in the text prompt. Our results demonstrate that GoM consistently improves the zero-shot capability of MLMs in interpreting object positions and relative directions, improving base accuracy in visual question answering and localization up to 11 percentage points.

comment: Please cite the definitive, copyrighted, and peer-reviewed version of this article published in AAAI 2026, edited by Sven Koenig et al., AAAI Press, Vol. 40, No. 36, Technical Track, pp. 30726-30734, 2026. DOI: https://doi.org/10.1609/aaai.v40i36.40329

♻ ☆ RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation

Kai Zhu, Zhenyu Cui, Zehua Zang, Jiahuan Zhou

Recently, state space models have demonstrated efficient video segmentation through linear-complexity state space compression. However, Video Semantic Segmentation (VSS) requires pixel-level spatiotemporal modeling capabilities to maintain temporal consistency in segmentation of semantic objects. While state space models can preserve common semantic information during state space compression, the fixed-size state space inevitably forgets specific information, which limits the models' capability for pixel-level segmentation. To tackle the above issue, we proposed a Refining Specifics State Space Model approach (RS-SSM) for video semantic segmentation, which performs complementary refining of forgotten spatiotemporal specifics. Specifically, a Channel-wise Amplitude Perceptron (CwAP) is designed to extract and align the distribution characteristics of specific information in the state space. Besides, a Forgetting Gate Information Refiner (FGIR) is proposed to adaptively invert and refine the forgetting gate matrix in the state space model based on the specific information distribution. Consequently, our RS-SSM leverages the inverted forgetting gate to complementarily refine the specific information forgotten during state space compression, thereby enhancing the model's capability for spatiotemporal pixel-level segmentation. Extensive experiments on four VSS benchmarks demonstrate that our RS-SSM achieves state-of-the-art performance while maintaining high computational efficiency. The code is available at https://github.com/zhoujiahuan1991/CVPR2026-RS-SSM.

comment: Accepted by CVPR 2026

♻ ☆ Mario: Multimodal Graph Reasoning with Large Language Models

Yuanfu Sun, Kang Li, Pengkang Guo, Jiajin Liu, Qiaoyu Tan

Recent advances in large language models (LLMs) have opened new avenues for multimodal reasoning. Yet, most existing methods still rely on pretrained vision-language models (VLMs) to encode image-text pairs in isolation, ignoring the relational structure that real-world multimodal data naturally form. This motivates reasoning on multimodal graphs (MMGs), where each node has textual and visual attributes and edges provide structural cues. Enabling LLM-based reasoning on such heterogeneous multimodal signals while preserving graph topology introduces two key challenges: resolving weak cross-modal consistency and handling heterogeneous modality preference. To address this, we propose Mario, a unified framework that simultaneously resolves the two above challenges and enables effective LLM-based reasoning over MMGs. Mario consists of two innovative stages. Firstly, a graph-conditioned VLM design that jointly refines textual and visual features through fine-grained cross-modal contrastive learning guided by graph topology. Secondly, a modality-adaptive graph instruction tuning mechanism that organizes aligned multimodal features into graph-aware instruction views and employs a learnable router to surface, for each node and its neighborhood, the most informative modality configuration to the LLM. Extensive experiments across diverse MMG benchmarks demonstrate that Mario consistently outperforms state-of-the-art graph models in both supervised and zero-shot scenarios for node classification and link prediction. The code will be made available at https://github.com/sunyuanfu/Mario.

comment: CVPR 2026

♻ ☆ MoLingo: Motion-Language Alignment for Text-to-Motion Generation

Yannan He, Garvita Tiwari, Xiaohan Zhang, Pankaj Bora, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll

We introduce MoLingo, a text-to-motion (T2M) model that generates realistic, lifelike human motion by denoising in a continuous latent space. Recent works perform latent space diffusion, either on the whole latent at once or auto-regressively over multiple latents. In this paper, we study how to make diffusion on continuous motion latents work best. We focus on two questions: (1) how to build a semantically aligned latent space so diffusion becomes more effective, and (2) how to best inject text conditioning so the motion follows the description closely. We propose a semantic-aligned motion encoder trained with frame-level text labels so that latents with similar text meaning stay close, which makes the latent space more diffusion-friendly. We also compare single-token conditioning with a multi-token cross-attention scheme and find that cross-attention gives better motion realism and text-motion alignment. With semantically aligned latents, auto-regressive generation, and cross-attention text conditioning, our model sets a new state of the art in human motion generation on standard metrics and in a user study. We will release our code and models for further research and downstream usage.

comment: Accepted by CVPR 2026. Project page: https://hynann.github.io/molingo/MoLingo.html

♻ ☆ One Dimensional CNN ECG Mamba for Multilabel Abnormality Classification in 12 Lead ECG

Huawei Jiang, Husna Mutahira, Gan Huang, Mannan Saeed Muhammad

Accurate detection of cardiac abnormalities from electrocardiogram recordings is regarded as essential for clinical diagnostics and decision support. Traditional deep learning models such as residual networks and transformer architectures have been applied successfully to this task, but their performance has been limited when long sequential signals are processed. Recently, state space models have been introduced as an efficient alternative. In this study, a hybrid framework named One Dimensional Convolutional Neural Network Electrocardiogram Mamba is introduced, in which convolutional feature extraction is combined with Mamba, a selective state space model designed for effective sequence modeling. The model is built upon Vision Mamba, a bidirectional variant through which the representation of temporal dependencies in electrocardiogram data is enhanced. Comprehensive experiments on the PhysioNet Computing in Cardiology Challenges of 2020 and 2021 were conducted, and superior performance compared with existing methods was achieved. Specifically, the proposed model achieved substantially higher AUPRC and AUROC scores than those reported by the best previously published algorithms on twelve lead electrocardiograms. These results demonstrate the potential of Mamba-based architectures to advance reliable ECG classification. This capability supports early diagnosis and personalized treatment, while enhancing accessibility in telemedicine and resource-constrained healthcare systems.

comment: 6 Pages, 2 figures

♻ ☆ Corruption-Aware Training of Latent Video Diffusion Models for Robust Text-to-Video Generation ICLR 2026

Chika Maduabuchi, Hao Chen, Yujin Han, Jindong Wang

Latent Video Diffusion Models (LVDMs) have achieved state-of-the-art generative quality for image and video generation; however, they remain brittle under noisy conditioning, where small perturbations in text or multimodal embeddings can cascade over timesteps and cause semantic drift. Existing corruption strategies from image diffusion (Gaussian, Uniform) fail in video settings because static noise disrupts temporal fidelity. In this paper, we propose CAT-LVDM, a corruption-aware training framework with structured, data-aligned noise injection tailored for video diffusion. Our two operators, Batch-Centered Noise Injection (BCNI) and Spectrum-Aware Contextual Noise (SACN), align perturbations with batch semantics or spectral dynamics to preserve coherence. CAT-LVDM yields substantial gains: BCNI reduces FVD by 31.9 percent on WebVid-2M, MSR-VTT, and MSVD, while SACN improves UCF-101 by 12.3 percent, outperforming Gaussian, Uniform, and even large diffusion baselines like DEMO (2.3B) and Lavie (3B) despite training on 5x less data. Ablations confirm the unique value of low-rank, data-aligned noise, and theory establishes why these operators tighten robustness and generalization bounds. CAT-LVDM thus sets a new framework for robust video diffusion, and our experiments show that it can also be extended to autoregressive generation and multimodal video understanding LLMs. Code, models, and samples are available at https://github.com/chikap421/catlvdm

comment: ICLR 2026 ReALM-GEN

♻ ☆ Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors

Chuanqing Zhuang, Xin Lu, Zehui Deng, Zhengda Lu, Yiqun Wang, Junqi Diao, Jun Xiao

Omnidirectional 3D Gaussian Splatting with panoramas is a key technique for 3D scene representation, and existing methods typically rely on slow SfM to provide camera poses and sparse points priors. In this work, we propose a pose-free omnidirectional 3DGS method, named PFGS360, that reconstructs 3D Gaussians from unposed omnidirectional videos. To achieve accurate camera pose estimation, we first construct a spherical consistency-aware pose estimation module, which recovers poses by establishing consistent 2D-3D correspondences between the reconstructed Gaussians and the unposed images using Gaussians' internal depth priors. Besides, to enhance the fidelity of novel view synthesis, we introduce a depth-inlier-aware densification module to extract depth inliers and Gaussian outliers with consistent monocular depth priors, enabling efficient Gaussian densification and achieving photorealistic novel view synthesis. The experiments show significant outperformance over existing pose-free and pose-aware 3DGS methods on both real-world and synthetic 360-degree videos. Code is available at https://github.com/zcq15/PFGS360.

♻ ☆ WiT: Waypoint Diffusion Transformers via Trajectory Conflict Navigation

Hainuo Wang, Mingjia Li, Xiaojie Guo

While recent Flow Matching models avoid the reconstruction bottlenecks of latent autoencoders by operating directly in pixel space, the lack of semantic continuity in the pixel manifold severely intertwines optimal transport paths. This induces severe trajectory conflicts near intersections, yielding sub-optimal solutions. Rather than bypassing this issue via information-lossy latent representations, we directly untangle the pixel-space trajectories by proposing Waypoint Diffusion Transformers (WiT). WiT factorizes the continuous vector field via intermediate semantic waypoints projected from pre-trained vision models. It effectively disentangles the generation trajectories by breaking the optimal transport into prior-to-waypoint and waypoint-to-pixel segments. Specifically, during the iterative denoising process, a lightweight generator dynamically infers these intermediate waypoints from the current noisy state. They then continuously condition the primary diffusion transformer via the Just-Pixel AdaLN mechanism, steering the evolution towards the next state, ultimately yielding the final RGB pixels. Evaluated on ImageNet 256x256, WiT beats strong pixel-space baselines, accelerating JiT training convergence by 2.2x. Code will be publicly released at https://github.com/hainuo-wang/WiT.git.

♻ ☆ MindSet: Vision. A toolbox for testing DNNs on key psychological experiments

Valerio Biscione, Milton L. Montero, Marin Dujmovic, Gaurav Malhotra, Dong Yin, Guillermo Puebla, Federico Adolfi, Rachel F. Heaton, John E. Hummel, Benjamin D. Evans, Karim Habashy, Jeffrey S. Bowers

Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses to naturalistic images that have not been manipulated to test hypotheses regarding how DNNs or humans perceive and identify objects. Here we introduce the toolbox \textit{MindSet: Vision}, consisting of a collection of image datasets and related scripts designed to test DNNs on 30 psychological findings. In all experimental conditions, the stimuli are systematically manipulated to test specific hypotheses regarding human visual perception and object recognition. In addition to providing pre-generated datasets of images, we provide code to regenerate these datasets, offering many configurable parameters which greatly extend the dataset versatility for different research contexts, and code to facilitate the testing of DNNs on these image datasets using three different methods (similarity judgments, out-of-distribution classification, and decoder method), accessible via https://github.com/MindSetVision/MindSetVision. To illustrate the challenges these datasets pose for developing better DNN models of human vision, we test several models on range of datasets included in the toolbox.

comment: 34 pages, 12 figures. Updated version with additional model evaluations

♻ ☆ Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation

Sule Bai, Yong Liu, Yifei Han, Haoji Zhang, Yansong Tang, Jie Zhou, Jiwen Lu

Recent advancements in pre-trained vision-language models like CLIP have enabled the task of open-vocabulary segmentation. CLIP demonstrates impressive zero-shot capabilities in various downstream tasks that require holistic image understanding. However, due to the image-level contrastive learning and fully global feature interaction, ViT-based CLIP struggles to capture local details, resulting in poor performance in segmentation tasks. Our analysis of ViT-based CLIP reveals that anomaly tokens emerge during the forward process, attracting disproportionate attention from normal patch tokens and thereby diminishing spatial awareness. To address this issue, we propose Self-Calibrated CLIP (SC-CLIP), a training-free method that calibrates CLIP to generate finer representations while preserving its original generalization ability-without introducing new parameters or relying on additional backbones. Specifically, we mitigate the negative impact of anomaly tokens from two complementary perspectives. First, we explicitly identify the anomaly tokens and replace them based on local context. Second, we reduce their influence on normal tokens by enhancing feature discriminability and attention correlation, leveraging the inherent semantic consistency within CLIP's mid-level features. In addition, we introduce a two-pass strategy that effectively integrates multi-level features to enrich local details under the training-free setting. Together, these strategies enhance CLIP's feature representations with improved granularity and semantic coherence. Experimental results demonstrate the effectiveness of SC-CLIP, achieving state-of-the-art results across all datasets and surpassing previous methods by 9.5%. Notably, SC-CLIP boosts the performance of vanilla CLIP ViT-L/14 by 6.8 times. Our source code is available at https://github.com/SuleBai/SC-CLIP.

comment: Accepted by IEEE TIP

♻ ☆ CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval

Haoran Wang, Dongliang He, Wenhao Wu, Boyang Xia, Min Yang, Fu Li, Yunlong Yu, Zhong Ji, Errui Ding, Jingdong Wang

Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning is restricted by manually weighting negative pairs as well as unawareness of external knowledge. In this paper, we propose our novel Coupled Diversity-Sensitive Momentum Constrastive Learning (CODER) for improving cross-modal representation. Firstly, a novel diversity-sensitive contrastive learning (DCL) architecture is invented. We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting. Furthermore, two branches are designed in CODER. One learns instance-level embeddings from image/text, and it also generates pseudo online clustering labels for its input image/text based on their embeddings. Meanwhile, the other branch learns to query from commonsense knowledge graph to form concept-level descriptors for both modalities. Afterwards, both branches leverage DCL to align the cross-modal embedding spaces while an extra pseudo clustering label prediction loss is utilized to promote concept-level representation learning for the second branch. Extensive experiments conducted on two popular benchmarks, i.e. MSCOCO and Flicker30K, validate CODER remarkably outperforms the state-of-the-art approaches. Our code is available at: https://github.com/BruceW91/CODER.

comment: Accepted by ECCV 2022

♻ ☆ MOGeo: Beyond One-to-One Cross-View Object Geo-localization

Bo Lv, Qingwang Zhang, Le Wu, Yuanyuan Li, Yingying Zhu

Cross-View Object Geo-Localization (CVOGL) aims to locate an object of interest in a query image within a corresponding satellite image. Existing methods typically assume that the query image contains only a single object, which does not align with the complex, multi-object geo-localization requirements in real-world applications, making them unsuitable for practical scenarios. To bridge the gap between the realistic setting and existing task, we propose a new task, called Cross-View Multi-Object Geo-Localization (CVMOGL). To advance the CVMOGL task, we first construct a benchmark, CMLocation, which includes two datasets: CMLocation-V1 and CMLocation-V2. Furthermore, we propose a novel cross-view multi-object geo-localization method, MOGeo, and benchmark it against existing state-of-the-art methods. Extensive experiments are conducted under various application scenarios to validate the effectiveness of our method. The results demonstrate that cross-view object geo-localization in the more realistic setting remains a challenging problem, encouraging further research in this area.

♻ ☆ ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors

Haodong Yu, Yabo Zhang, Donglin Di, Ruyi Zhang, Wangmeng Zuo

While diffusion models excel at generating images with conventional dimensions, pushing them to synthesize ultra-high-resolution imagery at extreme aspect ratios (EAR) often triggers catastrophic structural failures, such as object repetition and spatial fragmentation. This limitation fundamentally stems from a lack of robust spatial priors, as static text-to-image models are primarily trained on image distributions with conventional dimensions. To overcome this bottleneck, we present ScrollScape, a novel framework that reformulates EAR image synthesis into a continuous video generation process through two core innovations. By mapping the spatial expansion of a massive canvas to the temporal evolution of video frames, ScrollScape leverages the inherent temporal consistency of video models as a powerful global constraint to ensure long-range structural integrity. Specifically, Scanning Positional Encoding (ScanPE) distributes global coordinates across frames to act as a flexible moving camera, while Scrolling Super-Resolution (ScrollSR) leverages video super-resolution priors to circumvent memory bottlenecks, efficiently scaling outputs to an unprecedented 32K resolution. Fine-tuned on a curated 3K multi-ratio image dataset, ScrollScape effectively aligns pre-trained video priors with the EAR generation task. Extensive evaluations demonstrate that it significantly outperforms existing image-diffusion baselines by eliminating severe localized artifacts. Consequently, our method overcomes inherent structural bottlenecks to ensure exceptional global coherence and visual fidelity across diverse domains at extreme scales.

♻ ☆ Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model

Yuan Wang, Borui Liao, Huijuan Huang, Jinda Lu, Ouxiang Li, Kuien Liu, Meng Wang, Xiang Wang

Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality, and text alignment, they often overlook key structural distortions, such as abnormal object appearances and interactions, which can degrade the overall quality of the generative video. To address this gap, we introduce REACT, a frame-level reward model designed specifically for structural distortions evaluation in generative videos. REACT assigns point-wise scores and attribution labels by reasoning over video frames, focusing on recognizing distortions. To support this, we construct a large-scale human preference dataset, annotated based on our proposed taxonomy of structural distortions, and generate additional data using a efficient Chain-of-Thought (CoT) synthesis pipeline. REACT is trained with a two-stage framework: (1) supervised fine-tuning with masked loss for domain knowledge injection, followed by (2) reinforcement learning with Group Relative Policy Optimization (GRPO) and pairwise rewards to enhance reasoning capability and align output scores with human preferences. During inference, a dynamic sampling mechanism is introduced to focus on frames most likely to exhibit distortion. We also present REACT-Bench, a benchmark for generative video distortion evaluation. Experimental results demonstrate that REACT complements existing reward models in assessing structutal distortion, achieving both accurate quantitative evaluations and interpretable attribution analysis.

♻ ☆ Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting

Peiyu Xu, Xin Sun, Krishna Mullia, Raymond Fei, Iliyan Georgiev, Shuang Zhao

Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization -- rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction -- but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises. We present a differentiable, sorting-free stochastic formulation for ray-traced 3DGS -- the first framework that uses stochastic ray tracing to both reconstruct and render standard and relightable 3DGS scenes. At its core is an unbiased Monte Carlo estimator for pixel-color gradients that evaluates only a small sampled subset of Gaussians per ray, bypassing the need for sorting. For standard 3DGS, our method matches the reconstruction quality and speed of rasterization-based 3DGS while substantially outperforming sorting-based ray tracing. For relightable 3DGS, the same stochastic estimator drives per-Gaussian shading with fully ray-traced shadow rays, delivering notably higher reconstruction fidelity than prior work.

comment: Project Page: https://xupaya.github.io/stoch3DGS/

♻ ☆ OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval

Zhiwei Chen, Yupeng Hu, Zixu Li, Zhiheng Fu, Xuemeng Song, Liqiang Nie

Composed Image Retrieval (CIR) represents a novel retrieval paradigm that is capable of expressing users' intricate retrieval requirements flexibly. It enables the user to give a multimodal query, comprising a reference image and a modification text, and subsequently retrieve the target image. Notwithstanding the considerable advances made by prevailing methodologies, CIR remains in its nascent stages due to two limitations: 1) inhomogeneity between dominant and noisy portions in visual data is ignored, leading to query feature degradation, and 2) the priority of textual data in the image modification process is overlooked, which leads to a visual focus bias. To address these two limitations, this work presents a focus mapping-based feature extractor, which consists of two modules: dominant portion segmentation and dual focus mapping. It is designed to identify significant dominant portions in images and guide the extraction of visual and textual data features, thereby reducing the impact of noise interference. Subsequently, we propose a textually guided focus revision module, which can utilize the modification requirements implied in the text to perform adaptive focus revision on the reference image, thereby enhancing the perception of the modification focus on the composed features. The aforementioned modules collectively constitute the segmentatiOn-based Focus shiFt reviSion nETwork (\mbox{OFFSET}), and comprehensive experiments on four benchmark datasets substantiate the superiority of our proposed method. The codes and data are available on https://zivchen-ty.github.io/OFFSET.github.io/

♻ ☆ SSI-DM: Singularity Skipping Inversion of Diffusion Models

Chen Min, Enze Jiang, Jishen Peng, Zheng Ma

Inverting real images into the noise space is essential for editing tasks using diffusion models, yet existing methods produce non-Gaussian noise with poor editability due to the inaccuracy in early noising steps. We identify the root cause: a mathematical singularity that renders inversion fundamentally ill-posed. We propose Singularity Skipping Inversion of Diffusion Models (SSI-DM), which bypasses this singular region by adding small noise before standard inversion. This simple approach produces inverted noise with natural Gaussian properties while maintaining reconstruction fidelity. As a plug-and-play technique compatible with general diffusion models, our method achieves superior performance on public image datasets for reconstruction and interpolation tasks, providing a principled and efficient solution to diffusion model inversion.

comment: A complete revision is needed

♻ ☆ TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

Jun Zhang, Teng Wang, Yuying Ge, Yixiao Ge, Xinhao Li, Ying Shan, Limin Wang

This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models (MLLMs) excel at various video understanding tasks, the recipes for optimizing them for VTG remain under-explored. In this paper, we present TimeLens, a systematic investigation into building MLLMs with strong VTG ability, along two primary dimensions: data quality and algorithmic design. We first expose critical quality issues in existing VTG benchmarks and introduce TimeLens-Bench, comprising meticulously re-annotated versions of three popular benchmarks with strict quality criteria. Our analysis reveals dramatic model re-rankings compared to legacy benchmarks, confirming the unreliability of prior evaluation standards. We also address noisy training data through an automated re-annotation pipeline, yielding TimeLens-100K, a large-scale, high-quality training dataset. Building on our data foundation, we conduct in-depth explorations of algorithmic design principles, yielding a series of meaningful insights and effective yet efficient practices. These include interleaved textual encoding for time representation, a thinking-free reinforcement learning with verifiable rewards (RLVR) approach as the training paradigm, and carefully designed recipes for RLVR training. These efforts culminate in TimeLens models, a family of MLLMs with state-of-the-art VTG performance among open-source models and even surpass proprietary models such as GPT-5 and Gemini-2.5-Flash. All codes, data, and models will be released to facilitate future research.

comment: CVPR 2026. Website: https://timelens-arc-lab.github.io/

♻ ☆ AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation

Dahyeon Kye, Changhyun Roh, Sukhun Ko, Chanho Eom, Jihyong Oh

Video Frame Interpolation (VFI) is a core low-level vision task that synthesizes intermediate frames between existing ones while ensuring spatial and temporal coherence. Over the past decades, VFI methodologies have evolved from classical motion compensation-based approach to a wide spectrum of deep learning-based approaches, including kernel-, flow-, hybrid-, phase-, GAN-, Transformer-, Mamba-, and most recently, diffusion-based models. We introduce AceVFI, a comprehensive and up-to-date review of the VFI field, covering over 250 representative papers. We systematically categorize VFI methods based on their core design principles and architectural characteristics. Further, we classify them into two major learning paradigms: Center-Time Frame Interpolation (CTFI) and Arbitrary-Time Frame Interpolation (ATFI). We analyze key challenges in VFI, including large motion, occlusion, lighting variation, and non-linear motion. In addition, we review standard datasets, loss functions, evaluation metrics. We also explore VFI applications in other domains and highlight future research directions. This survey aims to serve as a valuable reference for researchers and practitioners seeking a thorough understanding of the modern VFI landscape.

comment: Accepted to IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). Please visit our project page at https://github.com/CMLab-Korea/Awesome-Video-Frame-Interpolation

♻ ☆ Unified Primitive Proxies for Structured Shape Completion

Zhaiyu Chen, Yuqing Wang, Xiao Xiang Zhu

Structured shape completion recovers missing geometry as primitives rather than as unstructured points, which enables primitive-based surface reconstruction. Instead of following the prevailing cascade, we rethink how primitives and points should interact, and find it more effective to decode primitives in a dedicated pathway that attends to shared shape features. Following this principle, we present UniCo, which in a single feed-forward pass predicts a set of primitives with complete geometry, semantics, and inlier membership. To drive this unified representation, we introduce primitive proxies, learnable queries that are contextualized to produce assembly-ready outputs. To ensure consistent optimization, our training strategy couples primitives and points with online target updates. Across synthetic and real-world benchmarks with four independent assembly solvers, UniCo consistently outperforms recent baselines, lowering Chamfer distance by up to 50% and improving normal consistency by up to 7%. These results establish an attractive recipe for structured 3D understanding from incomplete data. Project page: https://unico-completion.github.io.

comment: CVPR 2026

♻ ☆ Diffusion Forcing for Multi-Agent Interaction Sequence Modeling

Vongani H. Maluleke, Kie Horiuchi, Lea Wilken, Evonne Ng, Jitendra Malik, Angjoo Kanazawa

Understanding and generating multi-person interactions is a fundamental challenge with broad implications for robotics and social computing. While humans naturally coordinate in groups, modeling such interactions remains difficult due to long temporal horizons, strong inter-agent dependencies, and variable group sizes. Existing motion generation methods are largely task-specific and do not generalize to flexible multi-agent generation. We introduce MAGNet (Multi-Agent Generative Network), a unified autoregressive diffusion framework for multi-agent motion generation that supports a wide range of interaction tasks through flexible conditioning and sampling. MAGNet performs dyadic and polyadic prediction, partner inpainting, partner prediction, and agentic generation all within a single model, and can autoregressively generate ultra-long sequences spanning hundreds of motion steps. We explicitly model inter-agent coupling during autoregressive denoising, enabling coherent coordination across agents. As a result, MAGNet captures both tightly synchronized activities (e.g., dancing, boxing) and loosely structured social interactions. Our approach performs on par with specialized methods on dyadic benchmarks while naturally extending to polyadic scenarios involving three or more interacting people. Please watch the supplemental video, where the temporal dynamics and spatial coordination of generated interactions are best appreciated. Project page: https://von31.github.io/MAGNet/

comment: Project page: https://von31.github.io/MAGNet/ ; Code: https://github.com/Von31/MAGNet-code

♻ ☆ ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning

Bangya Liu, Xinyu Gong, Zelin Zhao, Ziyang Song, Yulei Lu, Suhui Wu, Jun Zhang, Suman Banerjee, Hao Zhang

Human-object interaction (HOI) video generation has garnered increasing attention due to its promising applications in digital humans, e-commerce, advertising, and robotics imitation learning. However, existing methods face two critical limitations: (1) a lack of effective mechanisms to inject multi-view information of the object into the model, leading to poor cross-view consistency, and (2) heavy reliance on fine-grained hand mesh annotations for modeling interaction occlusions. To address these challenges, we introduce ByteLoom, a Diffusion Transformer (DiT)-based framework that generates realistic HOI videos with geometrically consistent object illustration, using simplified human conditioning and 3D object inputs. We first propose an RCM-cache mechanism that leverages Relative Coordinate Maps (RCM) as a universal representation to maintain object's geometry consistency and precisely control 6-DoF object transformations in the meantime. To compensate HOI dataset scarcity and leverage existing datasets, we further design a training curriculum that enhances model capabilities in a progressive style and relaxes the demand of hand mesh. Extensive experiments demonstrate that our method faithfully preserves human identity and the object's multi-view geometry, while maintaining smooth motion and object manipulation.

♻ ☆ Gastric-X: A Multimodal Multi-Phase Benchmark Dataset for Advancing Vision-Language Models in Gastric Cancer Analysis

Sheng Lu, Hao Chen, Rui Yin, Juyan Ba, Yu Zhang, Yuanzhe Li

Recent vision-language models (VLMs) have shown strong generalization and multimodal reasoning abilities in natural domains. However, their application to medical diagnosis remains limited by the lack of comprehensive and structured datasets that capture real clinical workflows. To advance the development of VLMs for clinical applications, particularly in gastric cancer, we introduce Gastric-X, a large-scale multimodal benchmark for gastric cancer analysis providing 1.7K cases. Each case in Gastric-X includes paired resting and dynamic CT scans, endoscopic image, a set of structured biochemical indicators, expert-authored diagnostic notes, and bounding box annotations of tumor regions, reflecting realistic clinical conditions. We systematically examine the capability of recent VLMs on five core tasks: Visual Question Answering (VQA), report generation, cross-modal retrieval, disease classification, and lesion localization. These tasks simulate critical stages of clinical workflow, from visual understanding and reasoning to multimodal decision support. Through this evaluation, we aim not only to assess model performance but also to probe the nature of VLM understanding: Can current VLMs meaningfully correlate biochemical signals with spatial tumor features and textual reports? We envision Gastric-X as a step toward aligning machine intelligence with the cognitive and evidential reasoning processes of physicians, and as a resource to inspire the development of next-generation medical VLMs.

comment: Computer Vision and Pattern Recognition 2026

♻ ☆ StreamingClaw Technical Report

Jiawei Chen, Zhe Chen, Chaoqun Du, Maokui He, Wei He, Hengtao Li, Qizhen Li, Zide Liu, Hao Ma, Xuhao Pan, Chang Ren, Xudong Rao, Xintian Shen, Chenfeng Wang, Tao Wei, Chengjun Yu, Pengfei Yu, Shengyu Yao, Chunpeng Zhou, Kun Zhan, Lihao Zheng, Pan Zhou, Xuhan Zhu, Yufei Zheng

Emerging applications such as embodied intelligence, AI hardware, autonomous driving, and intelligent cockpits rely on a real-time perception-decision-action closed loop, posing stringent challenges for streaming video understanding. However, current agents mostly suffer from fragmented capabilities, such as supporting only offline video understanding, lacking long-term multimodal memory mechanisms, or struggling to achieve real-time reasoning and proactive interaction under streaming input. These shortcomings have become a key bottleneck for preventing agents from sustaining perception, making real-time decisions, and executing closed-loop actions in complex real-world environments, constraining their deployment and potential in dynamic, open physical worlds. To alleviate these issues, we propose StreamingClaw, a unified agent framework for streaming video understanding and embodied intelligence. Beyond maintaining full compatibility with the OpenClaw framework, it natively supports real-time, multimodal streaming interactions. StreamingClaw integrates five core capabilities: (1) It supports real-time streaming reasoning. (2) It supports reasoning about future events and proactive interaction under the online evolution of interaction objectives. (3) It supports multimodal long-term memory storage, hierarchical memory evolution, efficient memory retrieval, and memory sharing across multiple agents. (4) It supports a closed loop of perception-decision-action. In addition to conventional tools and skills, it also provides streaming tools and action-centric skills tailored for real-world physical environments. (5) It is compatible with the OpenClaw framework, allowing it to leverage the resources and support of the open-source community.

comment: Under Progress

♻ ☆ DiP: Taming Diffusion Models in Pixel Space

Zhennan Chen, Junwei Zhu, Xu Chen, Jiangning Zhang, Xiaobin Hu, Hanzhen Zhao, Chengjie Wang, Jian Yang, Ying Tai

Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In contrast, existing pixel space models bypass VAEs but are computationally prohibitive for high-resolution synthesis. To resolve this dilemma, we propose DiP, an efficient pixel space diffusion framework. DiP decouples generation into a global and a local stage: a Diffusion Transformer (DiT) backbone operates on large patches for efficient global structure construction, while a co-trained lightweight Patch Detailer Head leverages contextual features to restore fine-grained local details. This synergistic design achieves computational efficiency comparable to LDMs without relying on a VAE. DiP is accomplished with up to 10$\times$ faster inference speeds than previous method while increasing the total number of parameters by only 0.3%, and achieves an 1.79 FID score on ImageNet 256$\times$256.

comment: Accepted by CVPR 2026

♻ ☆ Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation

Nassim Ali Ousalah, Peyman Rostami, Vincent Gaudillière, Emmanuel Koumandakis, Anis Kacem, Enjie Ghorbel, Djamila Aouada

In this paper, we address the problem of 6-DoF object pose estimation from a single RGB image. Indirect methods that typically predict intermediate 2D keypoints, followed by a Perspective-n-Point solver, have shown great performance. Direct approaches, which regress the pose in an end-to-end manner, are usually computationally more efficient but less accurate. However, direct pose regression heads rely on globally pooled features, ignoring spatial second-order statistics despite their informativeness in pose prediction. They also predict, in most cases, discontinuous pose representations that lack robustness. Herein, we therefore propose a covariance-pooled representation that encodes convolutional feature distributions as a symmetric positive definite (SPD) matrix. Moreover, we propose a novel pose encoding in the form of an SPD matrix via its Cholesky decomposition. Pose is then regressed in an end-to-end manner with a manifold-aware network head, taking into account the Riemannian geometry of SPD matrices. Experiments and ablations consistently demonstrate the relevance of second-order pooling and continuous representations for direct pose regression, including under partial occlusion.

comment: Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

♻ ☆ Group Editing: Edit Multiple Images in One Go

Yue Ma, Xinyu Wang, Qianli Ma, Qinghe Wang, Mingzhe Zheng, Xiangpeng Yang, Hao Li, Chongbo Zhao, Jixuan Ying, Harry Yang, Hongyu Liu, Qifeng Chen

In this paper, we tackle the problem of performing consistent and unified modifications across a set of related images. This task is particularly challenging because these images may vary significantly in pose, viewpoint, and spatial layout. Achieving coherent edits requires establishing reliable correspondences across the images, so that modifications can be applied accurately to semantically aligned regions. To address this, we propose GroupEditing, a novel framework that builds both explicit and implicit relationships among images within a group. On the explicit side, we extract geometric correspondences using VGGT, which provides spatial alignment based on visual features. On the implicit side, we reformulate the image group as a pseudo-video and leverage the temporal coherence priors learned by pre-trained video models to capture latent relationships. To effectively fuse these two types of correspondences, we inject the explicit geometric cues from VGGT into the video model through a novel fusion mechanism. To support large-scale training, we construct GroupEditData, a new dataset containing high-quality masks and detailed captions for numerous image groups. Furthermore, to ensure identity preservation during editing, we introduce an alignment-enhanced RoPE module, which improves the model's ability to maintain consistent appearance across multiple images. Finally, we present GroupEditBench, a dedicated benchmark designed to evaluate the effectiveness of group-level image editing. Extensive experiments demonstrate that GroupEditing significantly outperforms existing methods in terms of visual quality, cross-view consistency, and semantic alignment.

comment: Accepted by CVPR 2026, Project page: https://group-editing.github.io/, Github: https://github.com/mayuelala/GroupEditing

♻ ☆ Monocular Normal Estimation via Shading Sequence Estimation ICLR 2026

Zongrui Li, Xinhua Ma, Minghui Hu, Yunqing Zhao, Yingchen Yu, Qian Zheng, Chang Liu, Xudong Jiang, Song Bai

Monocular normal estimation aims to estimate the normal map from a single RGB image of an object under arbitrary lights. Existing methods rely on deep models to directly predict normal maps. However, they often suffer from 3D misalignment: while the estimated normal maps may appear to have a correct appearance, the reconstructed surfaces often fail to align with the geometric details. We argue that this misalignment stems from the current paradigm: the model struggles to distinguish and reconstruct varying geometry represented in normal maps, as the differences in underlying geometry are reflected only through relatively subtle color variations. To address this issue, we propose a new paradigm that reformulates normal estimation as shading sequence estimation, where shading sequences are more sensitive to various geometric information. Building on this paradigm, we present RoSE, a method that leverages image-to-video generative models to predict shading sequences. The predicted shading sequences are then converted into normal maps by solving a simple ordinary least-squares problem. To enhance robustness and better handle complex objects, RoSE is trained on a synthetic dataset, MultiShade, with diverse shapes, materials, and light conditions. Experiments demonstrate that RoSE achieves state-of-the-art performance on real-world benchmark datasets for object-based monocular normal estimation.

comment: ICLR 2026 (Oral), Project page: https://xinhua694.github.io/RoSE.github.io/

♻ ☆ See the Text: From Tokenization to Visual Reading

Ling Xing, Rui Yan, Alex Jinpeng Wang, Zechao Li, Jinhui Tang

People see text. Humans read by recognizing words as visual objects, including their shapes, layouts, and patterns, before connecting them to meaning, which enables us to handle typos, distorted fonts, and various scripts effectively. Modern large language models (LLMs), however, rely on subword tokenization, fragmenting text into pieces from a fixed vocabulary. While effective for high-resource languages, this approach over-segments low-resource languages, yielding long, linguistically meaningless sequences and inflating computation. In this work, we challenge this entrenched paradigm and move toward a vision-centric alternative. Our method, SeeTok, renders text as images (visual-text) and leverages pretrained multimodal LLMs to interpret them, reusing strong OCR and text-vision alignment abilities learned from large-scale multimodal training. Across three different language tasks, SeeTok matches or surpasses subword tokenizers while requiring 4.43 times fewer tokens and reducing FLOPs by 70.5%, with additional gains in cross-lingual generalization, robustness to typographic noise, and linguistic hierarchy. SeeTok signals a shift from symbolic tokenization to human-like visual reading, and takes a step toward more natural and cognitively inspired language models.

♻ ☆ Multimodal classification of Radiation-Induced Contrast Enhancements and tumor recurrence using deep learning

Robin Peretzke, Marlin Hanstein, Maximilian Fischer, Lars Badhi Wessel, Obada Alhalabi, Sebastian Regnery, Andreas Kudak, Maximilian Deng, Tanja Eichkorn, Philipp Hoegen Saßmannshausen, Fabian Allmendinger, Jan-Hendrik Bolten, Philipp Schröter, Christine Jungk, Jürgen Peter Debus, Peter Neher, Laila König, Klaus Maier-Hein

The differentiation between tumor recurrence and radiation-induced contrast enhancements in post-treatment glioblastoma patients remains a major clinical challenge. Existing approaches rely on clinically sparsely available diffusion MRI or do not consider radiation maps, which are gaining increasing interest in the tumor board for this differentiation. We introduce RICE-NET, a multimodal 3D deep learning model that integrates longitudinal MRI data with radiotherapy dose distributions for automated lesion classification using conventional T1-weighted MRI data. Using a cohort of 92 patients, the model achieved an F1 score of 0.92 on an independent test set. During extensive ablation experiments, we quantified the contribution of each timepoint and modality and showed that reliable classification largely depends on the radiation map. Occlusion-based interpretability analyses further confirmed the model's focus on clinically relevant regions. These findings highlight the potential of multimodal deep learning to enhance diagnostic accuracy and support clinical decision-making in neuro-oncology.

♻ ☆ Diffusion Probe: Generated Image Result Prediction Using CNN Probes

Benlei Cui, Bukun Huang, Zhizeng Ye, Xuemei Dong, Tuo Chen, Hui Xue, Dingkang Yang, Longtao Huang, Jingqun Tang, Haiwen Hong

Text-to-image (T2I) diffusion models lack an efficient mechanism for early quality assessment, leading to costly trial-and-error in multi-generation scenarios such as prompt iteration, agent-based generation, and flow-grpo. We reveal a strong correlation between early diffusion cross-attention distributions and final image quality. Based on this finding, we introduce Diffusion Probe, a framework that leverages internal cross-attention maps as predictive signals. We design a lightweight predictor that maps statistical properties of early-stage cross-attention extracted from initial denoising steps to the final image's overall quality. This enables accurate forecasting of image quality across diverse evaluation metrics long before full synthesis is complete. We validate Diffusion Probe across a wide range of settings. On multiple T2I models, across early denoising windows, resolutions, and quality metrics, it achieves strong correlation (PCC > 0.7) and high classification performance (AUC-ROC > 0.9). Its reliability translates into practical gains. By enabling early quality-aware decisions in workflows such as prompt optimization, seed selection, and accelerated RL training, the probe supports more targeted sampling and avoids computation on low-potential generations. This reduces computational overhead while improving final output quality.Diffusion Probe is model-agnostic, efficient, and broadly applicable, offering a practical solution for improving T2I generation efficiency through early quality prediction.

comment: CVPR 2026

♻ ☆ Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols

Xianchao Zeng, Xinyu Zhou, Youcheng Li, Jiayou Shi, Tianle Li, Liangming Chen, Lei Ren, Yong-Lu Li

Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic manipulation, yet they remain limited in failure diagnosis and learning from failures. Additionally, existing failure datasets are mostly generated programmatically in simulation, which limits their generalization to the real world. In light of these, we introduce ViFailback, a framework designed to diagnose robotic manipulation failures and provide both textual and visual correction guidance. Our framework utilizes explicit visual symbols to enhance annotation efficiency. We further release the ViFailback dataset, a large-scale collection of 58,126 Visual Question Answering (VQA) pairs along with their corresponding 5,202 real-world manipulation trajectories. Based on the dataset, we establish ViFailback-Bench, a benchmark of 11 fine-grained VQA tasks designed to assess the failure diagnosis and correction abilities of Vision-Language Models (VLMs), featuring ViFailback-Bench Lite for closed-ended and ViFailback-Bench Hard for open-ended evaluation. To demonstrate the effectiveness of our framework, we built the ViFailback-8B VLM, which not only achieves significant overall performance improvement on ViFailback-Bench but also generates visual symbols for corrective action guidance. Finally, by integrating ViFailback-8B with a VLA model, we conduct real-world robotic experiments demonstrating its ability to assist the VLA model in recovering from failures. Project Website: https://x1nyuzhou.github.io/vifailback.github.io/

comment: Accepted by CVPR 2026. Project Website: https://x1nyuzhou.github.io/vifailback.github.io/

♻ ☆ Foundry: Distilling 3D Foundation Models for the Edge

Guillaume Letellier, Siddharth Srivastava, Frédéric Jurie, Gaurav Sharma

Foundation models pre-trained with self-supervised learning (SSL) on large-scale datasets have become powerful general-purpose feature extractors. However, their immense size and computational cost make them prohibitive for deployment on edge devices such as robots and AR/VR headsets. Existing compression techniques like standard knowledge distillation create efficient 'specialist' models but sacrifice the crucial, downstream-agnostic generality that makes foundation models so valuable. In this paper, we introduce Foundation Model Distillation (FMD), a new paradigm for compressing large SSL models into compact, efficient, and faithful proxies that retain their general-purpose representational power. We present Foundry, the first implementation of FMD for 3D point clouds. Our approach, Foundry, trains a student to learn a compressed set of SuperTokens that reconstruct the teacher's token-level representations, capturing a compact basis of its latent space. A single distilled model maintains strong transferability across diverse downstream tasks-classification, part segmentation, and few-shot scenarios-approaching full foundation-model performance while using significantly fewer tokens and FLOPs, making such models more practical for deployment on resourceconstrained hardware.

comment: Accepted at CVPR 2026

♻ ☆ RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations

I-Hsiang Chen, Yu-Wei Liu, Tse-Yu Wu, Yu-Chien Chiang, Jen-Chien Yang, Wei-Ting Chen

Vision-based Retrieval-Augmented Generation (VisRAG) leverages vision-language models (VLMs) to jointly retrieve relevant visual documents and generate grounded answers based on multimodal evidence. However, existing VisRAG models degrade in performance when visual inputs suffer from distortions such as blur, noise, low light, or shadow, where semantic and degradation factors become entangled within pretrained visual encoders, leading to errors in both retrieval and generation stages. To address this limitation, we introduce RobustVisRAG, a causality-guided dual-path framework that improves VisRAG robustness while preserving efficiency and zero-shot generalization. RobustVisRAG uses a non-causal path to capture degradation signals through unidirectional attention and a causal path to learn purified semantics guided by these signals. Together with the proposed Non-Causal Distortion Modeling and Causal Semantic Alignment objectives, the framework enforces a clear separation between semantics and degradations, enabling stable retrieval and generation under challenging visual conditions. To evaluate robustness under realistic conditions, we introduce the Distortion-VisRAG dataset, a large-scale benchmark containing both synthetic and real-world degraded documents across seven domains, with 12 synthetic and 5 real distortion types that comprehensively reflect practical visual degradations. Experimental results show that RobustVisRAG improves retrieval, generation, and end-to-end performance by 7.35%, 6.35%, and 12.40%, respectively, on real-world degradations, while maintaining comparable accuracy on clean inputs.

comment: Accepted by CVPR2026; Project Page: https://robustvisrag.github.io

♻ ☆ Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive Perception

Seamie Hayes, Ganesh Sistu, Tim Brophy, Ciaran Eising

In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable road users such as pedestrians and cyclists. Previous representation methods, such as Bird's Eye View, collapse vertical information, leading to ambiguity in 3D object localisation and limiting accurate understanding of the environment for downstream tasks such as motion planning and scene forecasting. In contrast, semantic occupancy provides a full 3D representation of the surroundings, addressing these limitations. Furthermore, self-supervised semantic occupancy has seen increased attention in the automated vehicle domain. Unlike supervised methods that rely on manually annotated data, these approaches use 2D pseudo-labels, improving scalability by reducing the need for labour-intensive annotation. Consequently, such models employ techniques such as novel view synthesis, cross-view rendering, and depth estimation to allow for model supervision against the 2D labels. However, such approaches often incur high computational and memory costs during training, especially for novel view synthesis. To address these issues, we propose Easy3D-Labels, which are 3D pseudo-ground-truth labels generated using Grounded-SAM and Metric3Dv2, with temporal aggregation for densification, permitting supervision directly in 3D space. Easy3D-Labels can be readily integrated into existing models to provide model supervision, yielding substantial performance gains, with mIoU increasing by 45% and RayIoU by 49% when applied to OccNeRF on the Occ3D-nuScenes dataset. Additionally, we introduce EasyOcc, a streamlined model trained solely on these 3D pseudo-labels, avoiding the need for complex rendering strategies, and achieving 15.7 mIoU on Occ3D-nuScenes. Easy3D-Labels improve scene understanding by reducing object duplication and enhancing depth estimation accuracy.

♻ ☆ MoRel: Long-Range Flicker-Free 4D Motion Modeling via Anchor Relay-based Bidirectional Blending with Hierarchical Densification

Sangwoon Kwak, Weeyoung Kwon, Jun Young Jeong, Geonho Kim, Won-Sik Cheong, Jihyong Oh

Recent advances in 4D Gaussian Splatting (4DGS) have extended the high-speed rendering capability of 3D Gaussian Splatting (3DGS) into the temporal domain, enabling real-time rendering of dynamic scenes. However, one of the major remaining challenges lies in modeling long-range motion-contained dynamic videos, where a naive extension of existing methods leads to severe memory explosion, temporal flickering, and failure to handle appearing or disappearing occlusions over time. To address these challenges, we propose a novel 4DGS framework characterized by an Anchor Relay-based Bidirectional Blending (ARBB) mechanism, named MoRel, which enables temporally consistent and memory-efficient modeling of long-range dynamic scenes. Our method progressively constructs locally canonical anchor spaces at key-frame time index and models inter-frame deformations at the anchor level, enhancing temporal coherence. By learning bidirectional deformations between KfA and adaptively blending them through learnable opacity control, our approach mitigates temporal discontinuities and flickering artifacts. We further introduce a Feature-variance-guided Hierarchical Densification (FHD) scheme that effectively densifies KfA's while keeping rendering quality, based on an assigned level of feature-variance. To effectively evaluate our model's capability to handle real-world long-range 4D motion, we newly compose long-range 4D motion-contained dataset, called SelfCap$_{\text{LR}}$. It has larger average dynamic motion magnitude, captured at spatially wider spaces, compared to previous dynamic video datasets. Overall, our MoRel achieves temporally coherent and flicker-free long-range 4D reconstruction while maintaining bounded memory usage, demonstrating both scalability and efficiency in dynamic Gaussian-based representations.

comment: CVPR 2026 (camera ready ver.). The first two authors contributed equally to this work (equal contribution). Please visit our project page at https://cmlab-korea.github.io/MoRel/

♻ ☆ HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images

Yumeng Liu, Xiao-Xiao Long, Marc Habermann, Xuanze Yang, Cheng Lin, Yuan Liu, Yuexin Ma, Wenping Wang, Ligang Liu

Recovering high-fidelity 3D hand geometry from images is a critical task in computer vision, holding significant value for domains such as robotics, animation and VR/AR. Crucially, scalable applications demand both accuracy and deployment flexibility, requiring the ability to leverage massive amounts of unstructured image data from the internet or enable deployment on consumer-grade RGB cameras without complex calibration. However, current methods face a dilemma. While single-view approaches are easy to deploy, they suffer from depth ambiguity and occlusion. Conversely, multi-view systems resolve these uncertainties but typically demand fixed, calibrated setups, limiting their real-world utility. To bridge this gap, we draw inspiration from 3D foundation models that learn explicit geometry directly from visual data. By reformulating hand reconstruction from arbitrary views as a visual-geometry grounded task, we propose a feed-forward architecture that, for the first time in literature, jointly infers 3D hand meshes and camera poses from uncalibrated views. Extensive evaluations show that our approach outperforms state-of-the-art benchmarks and demonstrates strong generalization to uncalibrated, in-the-wild scenarios. Here is the link of our project page: https://lym29.github.io/HGGT/.

comment: project page: https://lym29.github.io/HGGT/

♻ ☆ Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset

Geon Choi, Hangyul Yoon, Hyunju Shin, Hyunki Park, Sang Hoon Seo, Eunho Yang, Edward Choi

The applicability of current lesion segmentation models for chest X-rays (CXRs) has been limited both by a small number of target labels and the reliance on complex, expert-level text inputs, creating a barrier to practical use. To address these limitations, we introduce instruction-guided lesion segmentation (ILS), a medical-domain adaptation of referring image segmentation (RIS) designed to segment diverse lesion types based on simple, user-friendly instructions. Under this task, we construct MIMIC-ILS, the first large-scale instruction-answer dataset for CXR lesion segmentation, using our fully automated multimodal pipeline that generates annotations from CXR images and their corresponding reports. MIMIC-ILS contains 1.1M instruction-answer pairs derived from 192K images and 91K unique segmentation masks, covering seven major lesion types. To empirically demonstrate its utility, we present ROSALIA, a LISA model fine-tuned on the MIMIC-ILS dataset. ROSALIA can segment diverse lesions and provide textual explanations in response to user instructions. The model achieves high accuracy in our newly proposed task, highlighting the effectiveness of our pipeline and the value of MIMIC-ILS as a foundational resource for pixel-level CXR lesion grounding. The dataset and model are available at https://github.com/checkoneee/ROSALIA.

comment: Camera-ready version for CVPR 2026

♻ ☆ PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion

Yichen Yang, Hong Li, Haodong Zhu, Linin Yang, Guojun Lei, Sheng Xu, Baochang Zhang

Existing autoregressive (AR) methods for generating artist-designed meshes struggle to balance global structural consistency with high-fidelity local details, and are susceptible to error accumulation. To address this, we propose PartDiffuser, a novel semi-autoregressive diffusion framework for point-cloud-to-mesh generation. The method first performs semantic segmentation on the mesh and then operates in a "part-wise" manner: it employs autoregression between parts to ensure global topology, while utilizing a parallel discrete diffusion process within each semantic part to precisely reconstruct high-frequency geometric features. PartDiffuser is based on the DiT architecture and introduces a part-aware cross-attention mechanism, using point clouds as hierarchical geometric conditioning to dynamically control the generation process, thereby effectively decoupling the global and local generation tasks. Experiments demonstrate that this method significantly outperforms state-of-the-art (SOTA) models in generating 3D meshes with rich detail, exhibiting exceptional detail representation suitable for real-world applications.

♻ ☆ CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection

Zhaonian Kuang, Rui Ding, Haotian Wang, Xinhu Zheng, Meng Yang, Gang Hua

Multi-camera 3D object detection (MC3D) has attracted increasing attention with the growing deployment of multi-sensor physical agents, such as robots and autonomous vehicles. However, MC3D models still struggle to generalize to unseen platforms with new multi-camera configurations. Current solutions simply employ a meta-camera for unified representation but lack comprehensive consideration. In this paper, we revisit this issue and identify that the devil lies in spatial prior discrepancies across source and target configurations, including different intrinsics, extrinsics, and array layouts. To address this, we propose CoIn3D, a generalizable MC3D framework that enables strong transferability from source configurations to unseen target ones. CoIn3D explicitly incorporates all identified spatial priors into both feature embedding and image observation through spatial-aware feature modulation (SFM) and camera-aware data augmentation (CDA), respectively. SFM enriches feature space by integrating four spatial representations, such as focal length, ground depth, ground gradient, and Plücker coordinate. CDA improves observation diversity under various configurations via a training-free dynamic novel-view image synthesis scheme. Extensive experiments demonstrate that CoIn3D achieves strong cross-configuration performance on landmark datasets such as NuScenes, Waymo, and Lyft, under three dominant MC3D paradigms represented by BEVDepth, BEVFormer, and PETR.

comment: Accepted to CVPR 2026 main track

2026-03-25

Sound 16

☆ YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

Chunbo Hao, Junjie Zheng, Guobin Ma, Yuepeng Jiang, Huakang Chen, Wenjie Tian, Gongyu Chen, Zihao Chen, Lei Xie

Regenerating singing voices with altered lyrics while preserving melody consistency remains challenging, as existing methods either offer limited controllability or require laborious manual alignment. We propose YingMusic-Singer, a fully diffusion-based model enabling melody-controllable singing voice synthesis with flexible lyric manipulation. The model takes three inputs: an optional timbre reference, a melody-providing singing clip, and modified lyrics, without manual alignment. Trained with curriculum learning and Group Relative Policy Optimization, YingMusic-Singer achieves stronger melody preservation and lyric adherence than Vevo2, the most comparable baseline supporting melody control without manual alignment. We also introduce LyricEditBench, the first benchmark for melody-preserving lyric modification evaluation. The code, weights, benchmark, and demos are publicly available at https://github.com/ASLP-lab/YingMusic-Singer.

☆ A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English

Dana Serditova, Kevin Tang

Automatic Speech Recognition (ASR) systems are widely used in everyday communication, education, healthcare, and industry, yet their performance remains uneven across speakers, particularly when dialectal variation diverges from the mainstream accents represented in training data. This study investigates ASR bias through a sociolinguistic analysis of Newcastle English, a regional variety of North-East England that has been shown to challenge current speech recognition technologies. Using spontaneous speech from the Diachronic Electronic Corpus of Tyneside English (DECTE), we evaluate the output of a state-of-the-art commercial ASR system and conduct a fine-grained analysis of more than 3,000 transcription errors. Errors are classified by linguistic domain and examined in relation to social variables including gender, age, and socioeconomic status. In addition, an acoustic case study of selected vowel features demonstrates how gradient phonetic variation contributes directly to misrecognition. The results show that phonological variation accounts for the majority of errors, with recurrent failures linked to dialect-specific features like vowel quality and glottalisation, as well as local vocabulary and non-standard grammatical forms. Error rates also vary across social groups, with higher error frequencies observed for men and for speakers at the extremes of the age spectrum. These findings indicate that ASR errors are not random but socially patterned and can be explained from a sociolinguistic perspective. Thus, the study demonstrates the importance of incorporating sociolinguistic expertise into the evaluation and development of speech technologies and argues that more equitable ASR systems require explicit attention to dialectal variation and community-based speech data.

comment: 54 pages, 11 figures

☆ What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification

Massa Baali, Sarthak Bisht, Rita Singh, Bhiksha Raj

Speaker verification at large scale remains an open challenge as fixed-margin losses treat all samples equally regardless of quality. We hypothesize that mislabeled or degraded samples introduce noisy gradients that disrupt compact speaker manifolds. We propose Curry (CURriculum Ranking), an adaptive loss that estimates sample difficulty online via Sub-center ArcFace: confidence scores from dominant sub-center cosine similarity rank samples into easy, medium, and hard tiers using running batch statistics, without auxiliary annotations. Learnable weights guide the model from stable identity foundations through manifold refinement to boundary sharpening. To our knowledge, this is the largest-scale speaker verification system trained to date. Evaluated on VoxCeleb1-O, and SITW, Curry reduces EER by 86.8\% and 60.0\% over the Sub-center ArcFace baseline, establishing a new paradigm for robust speaker verification on imperfect large-scale data.

☆ Iterate to Differentiate: Enhancing Discriminability and Reliability in Zero-Shot TTS Evaluation

Shengfan Shen, Di Wu, Xingchen Song, Dinghao Zhou, Liumeng Xue, Meng Meng, Jian Luan, Shuai Wang

Reliable evaluation of modern zero-shot text-to-speech (TTS) models remains challenging. Subjective tests are costly and hard to reproduce, while objective metrics often saturate, failing to distinguish SOTA systems. To address this, we propose Iterate to Differentiate (I2D), an evaluation framework that recursively synthesizes speech using the model's own outputs as references. Higher-quality models exhibit greater resilience to the distributional shift induced by iterative synthesis, resulting in slower performance degradation. I2D exploits this differential degradation to amplify performance gaps and reveal robustness. By aggregating objective metrics across iterations, I2D improves discriminability and alignment with human judgments, increasing system-level SRCC from 0.118 to 0.464 for UTMOSv2. Experiments on 11 models across Chinese, English, and emotion datasets demonstrate that I2D enables more reliable automated evaluation for zero-shot TTS.

comment: submitted to Interspeech 2026, under review

☆ Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level dropin & Neuroplasticity Mechanisms

Yupei Li, Shuaijie Shao, Manuel Milling, Björn Schuller

comment: Accepted at IJCNN 2026

☆ Bridging Biological Hearing and Neuromorphic Computing: End-to-End Time-Domain Audio Signal Processing with Reservoir Computing

Rinku Sebastian, Simon O'Keefe, Martin Trefzer

Despite the advancements in cutting-edge technologies, audio signal processing continues to pose challenges and lacks the precision of a human speech processing system. To address these challenges, we propose a novel approach to simplify audio signal processing by leveraging time-domain techniques and reservoir computing. Through our research, we have developed a real-time audio signal processing system by simplifying audio signal processing through the utilization of reservoir computers, which are significantly easier to train. Feature extraction is a fundamental step in speech signal processing, with Mel Frequency Cepstral Coefficients (MFCCs) being a dominant choice due to their perceptual relevance to human hearing. However, conventional MFCC extraction relies on computationally intensive time-frequency transformations, limiting efficiency in real-time applications. To address this, we propose a novel approach that leverages reservoir computing to streamline MFCC extraction. By replacing traditional frequency-domain conversions with convolution operations, we eliminate the need for complex transformations while maintaining feature discriminability. We present an end-to-end audio processing framework that integrates this method, demonstrating its potential for efficient and real-time speech analysis. Our results contribute to the advancement of energy-efficient audio processing technologies, enabling seamless deployment in embedded systems and voice-driven applications. This work bridges the gap between biologically inspired feature extraction and modern neuromorphic computing, offering a scalable solution for next-generation speech recognition systems.

☆ Semantic-Aware Interruption Detection in Spoken Dialogue Systems: Benchmark, Metric, and Model

Kangxiang Xia, Bingshen Mu, Xian Shi, Jin Xu, Lei Xie

Achieving natural full-duplex interaction in spoken dialogue systems (SDS) remains a challenge due to the difficulty of accurately detecting user interruptions. Current solutions are polarized between "trigger-happy" VAD-based methods that misinterpret backchannels and robust end-to-end models that exhibit unacceptable response delays. Moreover, the absence of real-world benchmarks and holistic metrics hinders progress in the field. This paper presents a comprehensive frame-work to overcome these limitations. We first introduce SID-Bench, the first benchmark for semantic-aware interruption detection built entirely from real-world human dialogues. To provide a rigorous assessment of the responsiveness-robustness trade-off, we propose the Average Penalty Time (APT) metric, which assigns a temporal cost to both false alarms and late responses. Building on this framework, we design an LLM-based detection model optimized through a novel training paradigm to capture subtle semantic cues of intent. Experimental results show that our model significantly outperforms mainstream baselines, achieving a nearly threefold reduction in APT. By successfully resolving the long-standing tension between speed and stability, our work establishes a new state-of-the-art for intelligent interruption handling in SDS. To facilitate future research, SID-Bench and the associated code are available at: https://github.com/xkx-hub/SID-bench.

comment: Accepted by ICME 2026

☆ ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding ICASSP 2026

Yadong Niu, Tianzi Wang, Heinrich Dinkel, Xingwei Sun, Jiahao Zhou, Gang Li, Jizhong Liu, Junbo Zhang, Jian Luan

General audio understanding is a fundamental goal for large audio-language models, with audio captioning serving as a cornerstone task for their development. However, progress in this domain is hindered by existing datasets, which lack the scale and descriptive granularity required to train truly versatile models. To address this gap, we introduce ACAVCaps, a new large-scale, fine-grained, and multi-faceted audio captioning dataset. Derived from the ACAV100M collection, ACAVCaps is constructed using a multi-expert pipeline that analyzes audio from diverse perspectives-including speech, music, and acoustic properties-which are then synthesized into rich, detailed descriptions by a large language model. Experimental results demonstrate that models pre-trained on ACAVCaps exhibit substantially stronger generalization capabilities on various downstream tasks compared to those trained on other leading captioning datasets. The dataset is available at https://github.com/xiaomi-research/acavcaps.

comment: accepted by ICASSP 2026

☆ Variable-Length Audio Fingerprinting

Hongjie Chen, Hanyu Meng, Huimin Zeng, Ryan A. Rossi, Lie Lu, Josh Kimball

Audio fingerprinting converts audio to much lower-dimensional representations, allowing distorted recordings to still be recognized as their originals through similar fingerprints. Existing deep learning approaches rigidly fingerprint fixed-length audio segments, thereby neglecting temporal dynamics during segmentation. To address limitations due to this rigidity, we propose Variable-Length Audio FingerPrinting (VLAFP), a novel method that supports variable-length fingerprinting. To the best of our knowledge, VLAFP is the first deep audio fingerprinting model capable of processing audio of variable length, for both training and testing. Our experiments show that VLAFP outperforms existing state-of-the-arts in live audio identification and audio retrieval across three real-world datasets.

☆ Rethinking Masking Strategies for Masked Prediction-based Audio Self-supervised Learning

Daisuke Niizumi, Daiki Takeuchi, Masahiro Yasuda, Binh Thien Nguyen, Noboru Harada, Nobutaka Ono

Since the introduction of Masked Autoencoders, various improvements to masking techniques have been explored. In this paper, we rethink masking strategies for audio representation learning using masked prediction-based self-supervised learning (SSL) on general audio spectrograms. While recent informed masking techniques have attracted attention, we observe that they incur substantial computational overhead. Motivated by this observation, we propose dispersion-weighted masking (DWM), a lightweight masking strategy that leverages the spectral sparsity inherent in the frequency structure of audio content. Our experiments show that inverse block masking, commonly used in recent SSL frameworks, improves audio event understanding performance while introducing a trade-off in generalization. The proposed DWM alleviates these limitations and computational complexity, leading to consistent performance improvements. This work provides practical guidance on masking strategy design for masked prediction-based audio representation learning.

comment: 6+1 pages, 2 figures, 3 tables, accepted at IJCNN 2026

☆ AVControl: Efficient Framework for Training Audio-Visual Controls

Matan Ben-Yosef, Tavi Halperin, Naomi Ken Korem, Mohammad Salama, Harel Cain, Asaf Joseph, Anthony Chen, Urska Jelercic, Ofir Bibi

Controlling video and audio generation requires diverse modalities, from depth and pose to camera trajectories and audio transformations, yet existing approaches either train a single monolithic model for a fixed set of controls or introduce costly architectural changes for each new modality. We introduce AVControl, a lightweight, extendable framework built on LTX-2, a joint audio-visual foundation model, where each control modality is trained as a separate LoRA on a parallel canvas that provides the reference signal as additional tokens in the attention layers, requiring no architectural changes beyond the LoRA adapters themselves. We show that simply extending image-based in-context methods to video fails for structural control, and that our parallel canvas approach resolves this. On the VACE Benchmark, we outperform all evaluated baselines on depth- and pose-guided generation, inpainting, and outpainting, and show competitive results on camera control and audio-visual benchmarks. Our framework supports a diverse set of independently trained modalities: spatially-aligned controls such as depth, pose, and edges, camera trajectory with intrinsics, sparse motion control, video editing, and, to our knowledge, the first modular audio-visual controls for a joint generation model. Our method is both compute- and data-efficient: each modality requires only a small dataset and converges within a few hundred to a few thousand training steps, a fraction of the budget of monolithic alternatives. We publicly release our code and trained LoRA checkpoints.

comment: Project page: https://matanby.github.io/AVControl/

☆ When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews

Hasindri Watawana, Sergio Burdisso, Diego A. Moreno-Galván, Fernando Sánchez-Vega, A. Pastor López-Monroy, Petr Motlicek, Esaú Villatoro-Tello

Automatic depression detection from doctor-patient conversations has gained momentum thanks to the availability of public corpora and advances in language modeling. However, interpretability remains limited: strong performance is often reported without revealing what drives predictions. We analyze three datasets: ANDROIDS, DAIC-WOZ, E-DAIC and identify a systematic bias from interviewer prompts in semi-structured interviews. Models trained on interviewer turns exploit fixed prompts and positions to distinguish depressed from control subjects, often achieving high classification scores without using participant language. Restricting models to participant utterances distributes decision evidence more broadly and reflects genuine linguistic cues. While semi-structured protocols ensure consistency, including interviewer prompts inflates performance by leveraging script artifacts. Our results highlight a cross-dataset, architecture-agnostic bias and emphasize the need for analyses that localize decision evidence by time and speaker to ensure models learn from participants' language.

comment: Accepted to LREC 2026 Conference

☆ HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection

Harrison Li, Kevin Wang, Cheol Jun Cho, Jiachen Lian, Rabab Rangwala, Chenxu Guo, Emma Yang, Lynn Kurteff, Zoe Ezzes, Willa Keegan-Rodewald, Jet Vonk, Siddarth Ramkrishnan, Giada Antonicelli, Zachary Miller, Marilu Gorno Tempini, Gopala Anumanchipalli

Building a diagnosis model for primary progressive aphasia (PPA) has been challenging due to the data scarcity. Collecting clinical data at scale is limited by the high vulnerability of clinical population and the high cost of expert labeling. To circumvent this, previous studies simulate dysfluent speech to generate training data. However, those approaches are not comprehensive enough to simulate PPA as holistic, multi-level phenotypes, instead relying on isolated dysfluencies. To address this, we propose a novel, clinically grounded simulation framework, Hierarchical Aphasic Speech Simulation (HASS). HASS aims to simulate behaviors of logopenic variant of PPA (lvPPA) with varying degrees of severity. To this end, semantic, phonological, and temporal deficits of lvPPA are systematically identified by clinical experts, and simulated. We demonstrate that our framework enables more accurate and generalizable detection models.

♻ ☆ DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Model

Massa Baali, Rita Singh, Bhiksha Raj

Self-supervised speech models have achieved remarkable success on content-driven tasks, yet they remain limited in capturing speaker-discriminative features critical for verification, diarization, and profiling applications. We introduce \textsc{DELULU}, a speaker-aware self-trained foundational model that addresses this limitation by incorporating speaker-informed structure into pseudo-label generation. DELULU leverages frame-level embeddings from ReDimNet, a state-of-the-art speaker verification model, to guide k-means clustering during pre-training, introducing a speaker-discriminative inductive bias that aligns representation learning with speaker identity. DELULU significantly outperforms prior SSL models across a range of speaker-centric tasks, achieving up to \textbf{62\% relative improvement} in equal error rate (EER) for speaker verification and consistent gains on zero-shot profiling tasks including gender, age, accent, and speaker counting; notably surpassing even its teacher model on zero-shot evaluations. Our findings demonstrate that \textbf{DELULU is a strong universal encoder for speaker-aware speech processing}, enabling superior performance without task-specific fine-tuning.

♻ ☆ An interpretable speech foundation model for depression detection by revealing prediction-relevant acoustic features from long speech

Qingkun Deng, Saturnino Luz, Sofia de la Fuente Garcia

Speech-based depression detection tools could aid early screening. Here, we propose an interpretable speech foundation model approach to enhance the clinical applicability of such tools. We introduce a speech-level Audio Spectrogram Transformer (AST) to detect depression using long-duration speech instead of short segments, along with a novel interpretation method that reveals prediction-relevant acoustic features for clinician interpretation. Our experiments show the proposed model outperforms a segment-level AST, highlighting the impact of segment-level labelling noise and the advantage of leveraging longer speech duration for more reliable depression detection. Through interpretation, we observe our model identifies reduced loudness and F0 as relevant depression signals, aligning with documented clinical findings. This interpretability supports a responsible AI approach for speech-based depression detection, rendering such tools more clinically applicable.

comment: 5 pages, 3 figures. arXiv admin note: substantial text overlap with arXiv:2309.13476

♻ ☆ OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

Maomao Li, Zhen Li, Kaipeng Zhang, Guosheng Yin, Zhifeng Li, Dong Xu

Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts. Benefiting from the rapid advancement of joint audio-video generation, this paper proposes a more compelling new task: sync audio-video customization, which aims to synchronously customize both video identity and audio timbre. Specifically, given a reference image $I^{r}$ and a reference audio $A^{r}$, this novel task requires generating videos that maintain the identity of the reference image while imitating the timbre of the reference audio, with spoken content freely specifiable through user-provided textual prompts. To this end, we propose OmniCustom, a powerful DiT-based audio-video customization framework that can synthesize a video following reference image identity, audio timbre, and text prompts all at once in a zero-shot manner. Our framework is built on three key contributions. First, identity and audio timbre control are achieved through separate reference identity and audio LoRA modules that operate through self-attention layers within the base audio-video generation model. Second, we introduce a contrastive learning objective alongside the standard flow matching objective. It uses predicted flows conditioned on reference inputs as positive examples and those without reference conditions as negative examples, thereby enhancing the model ability to preserve identity and timbre. Third, we train OmniCustom on our constructed large-scale, high-quality audio-visual human dataset. Extensive experiments demonstrate that OmniCustom outperforms existing methods in generating audio-video content with consistent identity and timbre fidelity. Project page: https://omnicustom-project.github.io/page/.

comment: code: https://github.com/OmniCustom-project/OmniCustom

Audio and Speech Processing 13

☆ YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

Chunbo Hao, Junjie Zheng, Guobin Ma, Yuepeng Jiang, Huakang Chen, Wenjie Tian, Gongyu Chen, Zihao Chen, Lei Xie

☆ ArrayDPS-Refine: Generative Refinement of Discriminative Multi-Channel Speech Enhancement ICASSP 2026

Zhongweiyang Xu, Ashutosh Pandey, Juan Azcarreta, Zhaoheng Ni, Sanjeel Parekh, Buye Xu

Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-linear distortions from regression-based objectives, especially under challenging environmental noise conditions. Inspired by ArrayDPS for unsupervised multi-channel source separation, we introduce ArrayDPS-Refine, a method designed to enhance the outputs of discriminative models using a clean speech diffusion prior. ArrayDPS-Refine is training-free, generative, and array-agnostic. It first estimates the noise spatial covariance matrix (SCM) from the enhanced speech produced by a discriminative model, then uses this estimated noise SCM for diffusion posterior sampling. This approach allows direct refinement of any discriminative model's output without retraining. Our results show that ArrayDPS-Refine consistently improves the performance of various discriminative models, including state-of-the-art waveform and STFT domain models. Audio demos are provided at https://xzwy.github.io/ArrayDPSRefineDemo/.

comment: Accepted to ICASSP 2026

☆ Semantic-Aware Interruption Detection in Spoken Dialogue Systems: Benchmark, Metric, and Model

Kangxiang Xia, Bingshen Mu, Xian Shi, Jin Xu, Lei Xie

comment: Accepted by ICME 2026

☆ How Open is Open TTS? A Practical Evaluation of Open Source TTS Tools for Romanian

Teodora Răgman, Adrian Bogdan Stânea, Horia Cucu, Adriana Stan

comment: Published in IEEE Access

☆ Photogrammetry-Reconstructed 3D Head Meshes for Accessible Individual Head-Related Transfer Functions

Ludovic Pirard, Lorenzo Picinali, Katarina C. Poole

Individual head-related transfer functions (HRTFs) are essential for accurate spatial audio binaural rendering but remain difficult to obtain due to measurement complexity. This study investigates whether photogrammetry-reconstructed (PR) head and ear meshes, acquired with consumer hardware, can provide a practically useful baseline for individual HRTF synthesis. Using the SONICOM HRTF dataset, 72-image photogrammetry captures per subject were processed with Apple's Object Capture API to generate PR meshes for 150 subjects. Mesh2HRTF was used to compute PR synthetic HRTFs, which were compared against measured HRTFs, high-resolution 3D scan-derived HRTFs, KEMAR, and random HRTFs through numerical evaluation, auditory models, and a behavioural sound localisation experiment (N = 27). PR synthetic HRTFs preserved ITD cues but exhibited increased ILD and spectral errors. Auditory-model predictions and behavioural data showed substantially higher quadrant error rates, reduced elevation accuracy, and greater front-back confusions than measured HRTFs, performing worse than random HRTFs on perceptual metrics. Current photogrammetry pipelines support individual HRTF synthesis but are limited by insufficient pinna morphology details and high-frequency spectral fidelity needed for accurate individual HRTFs containing monaural cues.

comment: Submitted to Acta Acustica Topical Issue - Spatial and binaural hearing: From neural processes to applications

☆ ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding ICASSP 2026

Yadong Niu, Tianzi Wang, Heinrich Dinkel, Xingwei Sun, Jiahao Zhou, Gang Li, Jizhong Liu, Junbo Zhang, Jian Luan

comment: accepted by ICASSP 2026

☆ Rethinking Masking Strategies for Masked Prediction-based Audio Self-supervised Learning

Daisuke Niizumi, Daiki Takeuchi, Masahiro Yasuda, Binh Thien Nguyen, Noboru Harada, Nobutaka Ono

comment: 6+1 pages, 2 figures, 3 tables, accepted at IJCNN 2026

☆ Unified Diffusion Refinement for Multi-Channel Speech Enhancement and Separation

Zhongweiyang Xu, Ashutosh Pandey, Juan Azcarreta, Zhaoheng Ni, Sanjeel Parekh, Buye Xu, Romit Roy Choudhury

We propose Uni-ArrayDPS, a novel diffusion-based refinement framework for unified multi-channel speech enhancement and separation. Existing methods for multi-channel speech enhancement/separation are mostly discriminative and are highly effective at producing high-SNR outputs. However, they can still generate unnatural speech with non-linear distortions caused by the neural network and regression-based objectives. To address this issue, we propose Uni-ArrayDPS, which refines the outputs of any strong discriminative model using a speech diffusion prior. Uni-ArrayDPS is generative, array-agnostic, and training-free, and supports both enhancement and separation. Given a discriminative model's enhanced/separated speech, we use it, together with the noisy mixtures, to estimate the noise spatial covariance matrix (SCM). We then use this SCM to compute the likelihood required for diffusion posterior sampling of the clean speech source(s). Uni-ArrayDPS requires only a pre-trained clean-speech diffusion model as a prior and does not require additional training or fine-tuning, allowing it to generalize directly across tasks (enhancement/separation), microphone array geometries, and discriminative model backbones. Extensive experiments show that Uni-ArrayDPS consistently improves a wide range of discriminative models for both enhancement and separation tasks. We also report strong results on a real-world dataset. Audio demos are provided at \href{https://xzwy.github.io/Uni-ArrayDPS/}{https://xzwy.github.io/Uni-ArrayDPS/}.

comment: Paper in submission

☆ When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews

Hasindri Watawana, Sergio Burdisso, Diego A. Moreno-Galván, Fernando Sánchez-Vega, A. Pastor López-Monroy, Petr Motlicek, Esaú Villatoro-Tello

comment: Accepted to LREC 2026 Conference

☆ HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection

♻ ☆ An interpretable speech foundation model for depression detection by revealing prediction-relevant acoustic features from long speech

Qingkun Deng, Saturnino Luz, Sofia de la Fuente Garcia

comment: 5 pages, 3 figures. arXiv admin note: substantial text overlap with arXiv:2309.13476

♻ ☆ OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

Maomao Li, Zhen Li, Kaipeng Zhang, Guosheng Yin, Zhifeng Li, Dong Xu

comment: code: https://github.com/OmniCustom-project/OmniCustom

♻ ☆ Adaptive Federated Fine-Tuning of Self-Supervised Speech Representations

Xin Guo, Chunrui Zhao, Hong Jia, Ting Dang, Gongping Huang, Xianrui Zheng, Yan Gao

Integrating Federated Learning (FL) with self-supervised learning (SSL) enables privacy-preserving fine-tuning for speech tasks. However, federated environments exhibit significant heterogeneity: clients differ in computational capacity, causing straggler effects under unified fine-tuning, while diverse downstream tasks require different representation depths, making full-model updates inefficient. To address these challenges, we propose an adaptive federated fine-tuning framework with early exits. Lightweight prediction heads are inserted at intermediate layers of the SSL backbone, allowing clients to terminate computation based on local constraints and task requirements. We further introduce a layer-wise, depth-aware partial aggregation strategy to better utilize representations from different network depths. Experiments show that the framework reduces edge overhead, supports heterogeneous hardware, and maintains competitive performance in resource-constrained federated environments.

comment: Submitted to Interspeech 2026

Computer Vision and Pattern Recognition 150

☆ TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models

Jiaying Zhou, Zhihao Zhan, Ruifeng Zhai, Qinhan Lyu, Hao Liu, Keze Wang, Liang Lin, Guangrun Wang

Vision--Language--Action (VLA) policies have shown strong progress in mapping language instructions and visual observations to robotic actions, yet their reliability degrades in cluttered scenes with distractors. By analyzing failure cases, we find that many errors do not arise from infeasible motions, but from instance-level grounding failures: the policy often produces a plausible grasp trajectory that lands slightly off-target or even on the wrong object instance. To address this issue, we propose TAG (Target-Agnostic Guidance), a simple inference-time guidance mechanism that explicitly reduces distractor- and appearance-induced bias in VLA policies. Inspired by classifier-free guidance (CFG), TAG contrasts policy predictions under the original observation and an object-erased observation, and uses their difference as a residual steering signal that strengthens the influence of object evidence in the decision process. TAG does not require modifying the policy architecture and can be integrated with existing VLA policies with minimal training and inference changes. We evaluate TAG on standard manipulation benchmarks, including LIBERO, LIBERO-Plus, and VLABench, where it consistently improves robustness under clutter and reduces near-miss and wrong-object executions.

☆ Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving

Linbo Wang, Yupeng Zheng, Qiang Chen, Shiwei Li, Yichen Zhang, Zebin Xing, Qichao Zhang, Xiang Li, Deheng Qian, Pengxuan Yang, Yihang Dong, Ce Hao, Xiaoqing Ye, Junyu han, Yifeng Pan, Dongbin Zhao

We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-informed latent world representations. Existing world-model-based planners suffer from inadequately compressed representations, limited spatial understanding, and underutilized temporal dynamics, resulting in sub-optimal planning under constrained data and compute budgets. Latent-WAM addresses these limitations with two core modules: a Spatial-Aware Compressive World Encoder (SCWE) that distills geometric knowledge from a foundation model and compresses multi-view images into compact scene tokens via learnable queries, and a Dynamic Latent World Model (DLWM) that employs a causal Transformer to autoregressively predict future world status conditioned on historical visual and motion representations. Extensive experiments on NAVSIM v2 and HUGSIM demonstrate new state-of-the-art results: 89.3 EPDMS on NAVSIM v2 and 28.9 HD-Score on HUGSIM, surpassing the best prior perception-free method by 3.2 EPDMS with significantly less training data and a compact 104M-parameter model.

☆ Vision-Language Models vs Human: Perceptual Image Quality Assessment

Imran Mehmood, Imad Ali Shah, Ming Ronnier Luo, Brian Deegan

Psychophysical experiments remain the most reliable approach for perceptual image quality assessment (IQA), yet their cost and limited scalability encourage automated approaches. We investigate whether Vision Language Models (VLMs) can approximate human perceptual judgments across three image quality scales: contrast, colorfulness and overall preference. Six VLMs four proprietary and two openweight models are benchmarked against psychophysical data. This work presents a systematic benchmark of VLMs for perceptual IQA through comparison with human psychophysical data. The results reveal strong attribute dependent variability models with high human alignment for colorfulness (ρup to 0.93) underperform on contrast and vice-versa. Attribute weighting analysis further shows that most VLMs assign higher weights to colorfulness compared to contrast when evaluating overall preference similar to the psychophysical data. Intramodel consistency analysis reveals a counterintuitive tradeoff: the most self consistent models are not necessarily the most human aligned suggesting response variability reflects sensitivity to scene dependent perceptual cues. Furthermore, human-VLM agreement is increased with perceptual separability, indicating VLMs are more reliable when stimulus differences are clearly expressed.

☆ EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction

Falong Fan, Yi Xie, Arnis Lektauers, Bo Liu, Jerzy Rozenblit

Accurate 3D reconstruction of deformable soft tissues is essential for surgical robotic perception. However, low-texture surfaces, specular highlights, and instrument occlusions often fragment geometric continuity, posing a challenge for existing fixed-topology approaches. To address this, we propose EndoVGGT, a geometry-centric framework equipped with a Deformation-aware Graph Attention (DeGAT) module. Rather than using static spatial neighborhoods, DeGAT dynamically constructs feature-space semantic graphs to capture long-range correlations among coherent tissue regions. This enables robust propagation of structural cues across occlusions, enforcing global consistency and improving non-rigid deformation recovery. Extensive experiments on SCARED show that our method significantly improves fidelity, increasing PSNR by 24.6% and SSIM by 9.1% over prior state-of-the-art. Crucially, EndoVGGT exhibits strong zero-shot cross-dataset generalization to the unseen SCARED and EndoNeRF domains, confirming that DeGAT learns domain-agnostic geometric priors. These results highlight the efficacy of dynamic feature-space modeling for consistent surgical 3D reconstruction.

☆ Chameleon: Episodic Memory for Long-Horizon Robotic Manipulation

Xinying Guo, Chenxi Jiang, Hyun Bin Kim, Ying Sun, Yang Xiao, Yuhang Han, Jianfei Yang

Robotic manipulation often requires memory: occlusion and state changes can make decision-time observations perceptually aliased, making action selection non-Markovian at the observation level because the same observation may arise from different interaction histories. Most embodied agents implement memory via semantically compressed traces and similarity-based retrieval, which discards disambiguating fine-grained perceptual cues and can return perceptually similar but decision-irrelevant episodes. Inspired by human episodic memory, we propose Chameleon, which writes geometry-grounded multimodal tokens to preserve disambiguating context and produces goal-directed recall through a differentiable memory stack. We also introduce Camo-Dataset, a real-robot UR5e dataset spanning episodic recall, spatial tracking, and sequential manipulation under perceptual aliasing. Across tasks, Chameleon consistently improves decision reliability and long-horizon control over strong baselines in perceptually confusable settings.

comment: Code is available at https://github.com/gxyes/MARS_Chameleon

☆ VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

Qijia He, Xunmei Liu, Hammaad Memon, Ziang Li, Zixian Ma, Jaemin Cho, Jason Ren, Daniel S Weld, Ranjay Krishna

Scalable Vector Graphics (SVG) are an essential format for technical illustration and digital design, offering precise resolution independence and flexible semantic editability. In practice, however, original vector source files are frequently lost or inaccessible, leaving only "flat" rasterized versions (e.g., PNG or JPEG) that are difficult to modify or scale. Manually reconstructing these figures is a prohibitively labor-intensive process, requiring specialized expertise to recover the original geometric intent. To bridge this gap, we propose VFIG, a family of Vision-Language Models trained for complex and high-fidelity figure-to-SVG conversion. While this task is inherently data-driven, existing datasets are typically small-scale and lack the complexity of professional diagrams. We address this by introducing VFIG-DATA, a large-scale dataset of 66K high-quality figure-SVG pairs, curated from a diverse mix of real-world paper figures and procedurally generated diagrams. Recognizing that SVGs are composed of recurring primitives and hierarchical local structures, we introduce a coarse-to-fine training curriculum that begins with supervised fine-tuning (SFT) to learn atomic primitives and transitions to reinforcement learning (RL) refinement to optimize global diagram fidelity, layout consistency, and topological edge cases. Finally, we introduce VFIG-BENCH, a comprehensive evaluation suite with novel metrics designed to measure the structural integrity of complex figures. VFIG achieves state-of-the-art performance among open-source models and performs on par with GPT-5.2, achieving a VLM-Judge score of 0.829 on VFIG-BENCH.

☆ Towards Training-Free Scene Text Editing

Yubo Li, Xugong Qin, Peng Zhang, Hailun Lin, Gangyan Zeng, Kexin Zhang

Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require task-specific training or paired data, limiting their scalability and adaptability. In this paper, we propose TextFlow, a training-free scene text editing framework that integrates the strengths of Attention Boost (AttnBoost) and Flow Manifold Steering (FMS) to enable flexible, high-fidelity text manipulation without additional training. Specifically, FMS preserves the structural and style consistency by modeling the visual flow of characters and background regions, while AttnBoost enhances the rendering of textual content through attention-based guidance. By jointly leveraging these complementary modules, our approach performs end-to-end text editing through semantic alignment and spatial refinement in a plug-and-play manner. Extensive experiments demonstrate that our framework achieves visual quality and text accuracy comparable to or superior to those of training-based counterparts, generalizing well across diverse scenes and languages. This study advances scene text editing toward a more efficient, generalizable, and training-free paradigm. Code is available at https://github.com/lyb18758/TextFlow

comment: Accepted by CVPR 2026

☆ Anti-I2V: Safeguarding your photos from malicious image-to-video generation

Duc Vu, Anh Nguyen, Chi Tran, Anh Tran

Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos from a specific person's photo and text prompts. Recent efforts have focused on adversarial attacks that introduce crafted perturbations to protect images from diffusion-based models. However, most existing approaches target image generation, while relatively few explicitly address image-to-video diffusion models (VDMs), and most primarily focus on UNet-based architectures. Hence, their effectiveness against Diffusion Transformer (DiT) models remains largely under-explored, as these models demonstrate improved feature retention, and stronger temporal consistency due to larger capacity and advanced attention mechanisms. In this work, we introduce Anti-I2V, a novel defense against malicious human image-to-video generation, applicable across diverse diffusion backbones. Instead of restricting noise updates to the RGB space, Anti-I2V operates in both the $L$*$a$*$b$* and frequency domains, improving robustness and concentrating on salient pixels. We then identify the network layers that capture the most distinct semantic features during the denoising process to design appropriate training objectives that maximize degradation of temporal coherence and generation fidelity. Through extensive validation, Anti-I2V demonstrates state-of-the-art defense performance against diverse video diffusion models, offering an effective solution to the problem.

comment: Accepted to CVPR 2026 (Main Conference)

☆ POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan ACM MM 2026

Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kumar Das, Monorama Swain, Yufang Hou, Elisabeth Andre, Khalid Mahmood Malik, Markus Schedl, Shah Nawaz

Multimodal speaker identification systems typically assume the availability of complete and homogeneous audio-visual modalities during both training and testing. However, in real-world applications, such assumptions often do not hold. Visual information may be missing due to occlusions, camera failures, or privacy constraints, while multilingual speakers introduce additional complexity due to linguistic variability across languages. These challenges significantly affect the robustness and generalization of multimodal speaker identification systems. The POLY-SIM Grand Challenge 2026 aims to advance research in multimodal speaker identification under missing-modality and cross-lingual conditions. Specifically, the Grand Challenge encourages the development of robust methods that can effectively leverage incomplete multimodal inputs while maintaining strong performance across different languages. This report presents the design and organization of the POLY-SIM Grand Challenge 2026, including the dataset, task formulation, evaluation protocol, and baseline model. By providing a standardized benchmark and evaluation framework, the challenge aims to foster progress toward more robust and practical multimodal speaker identification systems.

comment: Grand challenge at ACM MM 2026

☆ LensWalk: Agentic Video Understanding by Planning How You See in Videos

Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan

The dense, temporal nature of video presents a profound challenge for automated analysis. Despite the use of powerful Vision-Language Models, prevailing methods for video understanding are limited by the inherent disconnect between reasoning and perception: they rely on static, pre-processed information and cannot actively seek raw evidence from video as their understanding evolves. To address this, we introduce LensWalk, a flexible agentic framework that empowers a Large Language Model reasoner to control its own visual observation actively. LensWalk establishes a tight reason-plan-observe loop where the agent dynamically specifies, at each step, the temporal scope and sampling density of the video it observes. Using a suite of versatile, Vision-Language Model based tools parameterized by these specifications, the agent can perform broad scans for cues, focus on specific segments for fact extraction, and stitch evidence from multiple moments for holistic verification. This design allows for progressive, on-demand evidence gathering that directly serves the agent's evolving chain of thought. Without requiring any model fine-tuning, LensWalk delivers substantial, plug-and-play performance gains on multiple model recipes, boosting their accuracy by over 5\% on challenging long-video benchmarks like LVBench and Video-MME. Our analysis reveals that enabling an agent to control how it sees is key to unlocking more accurate, robust, and interpretable video reasoning.

comment: To be published in CVPR 2026

☆ The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series

Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mirela Tulbure, Patrick Hostert, Stefan Erasmi

Organic farming is a key element in achieving more sustainable agriculture. For a better understanding of the development and impact of organic farming, comprehensive, spatially explicit information is needed. This study presents an approach for the discrimination of organic and conventional farming systems using intra-annual Sentinel-2 time series. In addition, it examines two factors influencing this discrimination: the joint learning of crop type information in a concurrent task and the role of spatial context. A Vision Transformer model based on the Temporo-Spatial Vision Transformer (TSViT) architecture was used to construct a classification model for the two farming systems. The model was extended for simultaneous learning of the crop type, creating a multitask learning setting. By varying the patch size presented to the model, we tested the influence of spatial context on the classification accuracy of both tasks. We show that discrimination between organic and conventional farming systems using multispectral remote sensing data is feasible. However, classification performance varies substantially across crop types. For several crops, such as winter rye, winter wheat, and winter oat, F1 scores of 0.8 or higher can be achieved. In contrast, other agricultural land use classes, such as permanent grassland, orchards, grapevines, and hops, cannot be reliably distinguished, with F1 scores for the organic management class of 0.4 or lower. Joint learning of farming system and crop type provides only limited additional benefits over single-task learning. In contrast, incorporating wider spatial context improves the performance of both farming system and crop type classification. Overall, we demonstrate that a classification of agricultural farming systems is possible in a diverse agricultural region using multispectral remote sensing data.

☆ A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English

Dana Serditova, Kevin Tang

comment: 54 pages, 11 figures

☆ SEGAR: Selective Enhancement for Generative Augmented Reality

Fanjun Bu, Chenyang Yuan, Hiroshi Yasuda

Generative world models offer a compelling foundation for augmented-reality (AR) applications: by predicting future image sequences that incorporate deliberate visual edits, they enable temporally coherent, augmented future frames that can be computed ahead of time and cached, avoiding per-frame rendering from scratch in real time. In this work, we present SEGAR, a preliminary framework that combines a diffusion-based world model with a selective correction stage to support this vision. The world model generates augmented future frames with region-specific edits while preserving others, and the correction stage subsequently aligns safety-critical regions with real-world observations while preserving intended augmentations elsewhere. We demonstrate this pipeline in driving scenarios as a representative setting where semantic region structure is well defined and real-world feedback is readily available. We view this as an early step toward generative world models as practical AR infrastructure, where future frames can be generated, cached, and selectively corrected on demand.

☆ CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition

Florian Stilz, Vinkle Srivastav, Nassir Navab, Nicolas Padoy

Video-language foundation models have proven to be highly effective in zero-shot applications across a wide range of tasks. A particularly challenging area is the intraoperative surgical procedure domain, where labeled data is scarce, and precise temporal understanding is often required for complex downstream tasks. To address this challenge, we introduce CliPPER (Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition), a novel video-language pretraining framework trained on surgical lecture videos. Our method is designed for fine-grained temporal video-text recognition and introduces several novel pretraining strategies to improve multimodal alignment in long-form surgical videos. Specifically, we propose Contextual Video-Text Contrastive Learning (VTC_CTX) and Clip Order Prediction (COP) pretraining objectives, both of which leverage temporal and contextual dependencies to enhance local video understanding. In addition, we incorporate a Cycle-Consistency Alignment over video-text matches within the same surgical video to enforce bidirectional consistency and improve overall representation coherence. Moreover, we introduce a more refined alignment loss, Frame-Text Matching (FTM), to improve the alignment between video frames and text. As a result, our model establishes a new state-of-the-art across multiple public surgical benchmarks, including zero-shot recognition of phases, steps, instruments, and triplets. The source code and pretraining captions can be found at https://github.com/CAMMA-public/CliPPER.

☆ UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience

Zichuan Lin, Feiyu Liu, Yijun Yang, Jiafei Lyu, Yiming Gao, Yicheng Liu, Zhicong Lu, Yangbin Yu, Mingyu Yang, Junyou Li, Deheng Ye, Jie Jiang

Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second stage introduces Group Relative Self-Distillation (GRSD), which identifies critical fork points in group rollouts and constructs dense step-level supervision from successful trajectories to correct failed ones. Extensive experiments on AndroidWorld show that our 4B model achieves an 81.0% Pass@1 success rate, outperforming numerous recent baselines and exceeding human-level performance. Ablation and case studies further verify the effectiveness of GRSD. Our method represents a significant leap toward efficient, self-evolving, and high-performance mobile GUI automation without expensive manual data annotation.

comment: Code and models are available at https://github.com/ui-voyager/UI-Voyager

☆ Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification

Dipam Goswami, Simone Magistri, Gido M. van de Ven, Bartłomiej Twardowski, Andrew D. Bagdanov, Tinne Tuytelaars, Joost van de Weijer

Vision-language models (VLMs) like CLIP are trained with the objective of aligning text and image pairs. To improve CLIP-based few-shot image classification, recent works have observed that, along with text embeddings, image embeddings from the training set are an important source of information. In this work we investigate the impact of directly mixing image and text prototypes for few-shot classification and analyze this from a bias-variance perspective. We show that mixing prototypes acts like a shrinkage estimator. Although mixed prototypes improve classification performance, the image prototypes still add some noise in the form of instance-specific background or context information. In order to capture only information from the image space relevant to the given classification task, we propose projecting image prototypes onto the principal directions of the semantic text embedding space to obtain a text-aligned semantic image subspace. These text-aligned image prototypes, when mixed with text embeddings, further improve classification. However, for downstream datasets with poor cross-modal alignment in CLIP, semantic alignment might be suboptimal. We show that the image subspace can still be leveraged by modeling the anisotropy using class covariances. We demonstrate that combining a text-aligned mixed prototype classifier and an image-specific LDA classifier outperforms existing methods across few-shot classification benchmarks.

comment: Preprint

☆ Toward Physically Consistent Driving Video World Models under Challenging Trajectories

Jiawei Zhou, Zhenxin Zhu, Lingyi Du, Linye Lyu, Lijun Zhou, Zhanqian Wu, Hongcheng Luo, Zhuotao Tian, Bing Wang, Guang Chen, Hangjun Ye, Haiyang Sun, Yu Li

☆ Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Models

Siqi Liu, Xinyang Li, Bochao Zou, Junbao Zhuo, Huimin Ma, Jiansheng Chen

As large language models (LLMs) continue to advance, there is increasing interest in their ability to infer human mental states and demonstrate a human-like Theory of Mind (ToM). Most existing ToM evaluations, however, are centered on text-based inputs, while scenarios relying solely on visual information receive far less attention. This leaves a gap, since real-world human-AI interaction typically requires multimodal understanding. In addition, many current methods regard the model as a black box and rarely probe how its internal attention behaves in multiple-choice question answering (QA). The impact of LLM hallucinations on such tasks is also underexplored from an interpretability perspective. To address these issues, we introduce VisionToM, a vision-oriented intervention framework designed to strengthen task-aware reasoning. The core idea is to compute intervention vectors that align visual representations with the correct semantic targets, thereby steering the model's attention through different layers of visual features. This guidance reduces the model's reliance on spurious linguistic priors, leading to more reliable multimodal language model (MLLM) outputs and better QA performance. Experiments on the EgoToM benchmark-an egocentric, real-world video dataset for ToM with three multiple-choice QA settings-demonstrate that our method substantially improves the ToM abilities of MLLMs. Furthermore, results on an additional open-ended generation task show that VisionToM enables MLLMs to produce free-form explanations that more accurately capture agents' mental states, pushing machine-human collaboration toward greater alignment.

comment: 20 pages, 7 figures, accepted at CVPR 2026, project page: see https://founce.github.io/VisionToM

☆ Positive-First Most Ambiguous: A Simple Active Learning Criterion for Interactive Retrieval of Rare Categories

Kawtar Zaher, Olivier Buisson, Alexis Joly

Real-world fine-grained visual retrieval often requires discovering a rare concept from large unlabeled collections with minimal supervision. This is especially critical in biodiversity monitoring, ecological studies, and long-tailed visual domains, where the target may represent only a tiny fraction of the data, creating highly imbalanced binary problems. Interactive retrieval with relevance feedback offers a practical solution: starting from a small query, the system selects candidates for binary user annotation and iteratively refines a lightweight classifier. While Active Learning (AL) is commonly used to guide selection, conventional AL assumes symmetric class priors and large annotation budgets, limiting effectiveness in imbalanced, low-budget, low-latency settings. We introduce Positive-First Most Ambiguous (PF-MA), a simple yet effective AL criterion that explicitly addresses the class imbalance asymmetry: it prioritizes near-boundary samples while favoring likely positives, enabling rapid discovery of subtle visual categories while maintaining informativeness. Unlike standard methods that oversample negatives, PF-MA consistently returns small batches with a high proportion of relevant samples, improving early retrieval and user satisfaction. To capture retrieval diversity, we also propose a class coverage metric that measures how well selected positives span the visual variability of the target class. Experiments on long-tailed datasets, including fine-grained botanical data, demonstrate that PF-MA consistently outperforms strong baselines in both coverage and classifier performance, across varying class sizes and descriptors. Our results highlight that aligning AL with the asymmetric and user-centric objectives of interactive fine-grained retrieval enables simple yet powerful solutions for retrieving rare and visually subtle categories in realistic human-in-the-loop settings.

☆ Counting Without Numbers \& Finding Without Words

Badri Narayana Patro

Every year, 10 million pets enter shelters, separated from their families. Despite desperate searches by both guardians and lost animals, 70% never reunite, not because matches do not exist, but because current systems look only at appearance, while animals recognize each other through sound. We ask, why does computer vision treat vocalizing species as silent visual objects? Drawing on five decades of cognitive science showing that animals perceive quantity approximately and communicate identity acoustically, we present the first multimodal reunification system integrating visual and acoustic biometrics. Our species-adaptive architecture processes vocalizations from 10Hz elephant rumbles to 4kHz puppy whines, paired with probabilistic visual matching that tolerates stress-induced appearance changes. This work demonstrates that AI grounded in biological communication principles can serve vulnerable populations that lack human language.

☆ OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning

Kaihang Pan, Qi Tian, Jianwei Zhang, Weijie Kong, Jiangfeng Xiong, Yanxin Long, Shixue Zhang, Haiyi Qiu, Tan Wang, Zheqi Lv, Yue Wu, Liefeng Bo, Siliang Tang, Zhao Zhong

While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fragmented, and the few existing efforts toward unified video generation still struggle to seamlessly integrate diverse tasks within a single framework. To bridge this gap, we propose OmniWeaving, an omni-level video generation model featuring powerful multimodal composition and reasoning-informed capabilities. By leveraging a massive-scale pretraining dataset that encompasses diverse compositional and reasoning-augmented scenarios, OmniWeaving learns to temporally bind interleaved text, multi-image, and video inputs while acting as an intelligent agent to infer complex user intentions for sophisticated video creation. Furthermore, we introduce IntelligentVBench, the first comprehensive benchmark designed to rigorously assess next-level intelligent unified video generation. Extensive experiments demonstrate that OmniWeaving achieves SoTA performance among open-source unified models. The codes and model will be made publicly available soon. Project Page: https://omniweaving.github.io.

comment: 32 pages, 22 figures. Project Page: https://omniweaving.github.io

☆ Unleashing Vision-Language Semantics for Deepfake Video Detection

Jiawen Zhu, Yunqi Miao, Xueyi Zhang, Jiankang Deng, Guansong Pang

Recent Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) such as CLIP exhibit strong generalization capabilities in detecting artifacts across different identities. However, existing approaches focus on leveraging visual features only, overlooking their most distinctive strength -- the rich vision-language semantics embedded in the latent space. We propose VLAForge, a novel DFD framework that unleashes the potential of such cross-modal semantics to enhance model's discriminability in deepfake detection. This work i) enhances the visual perception of VLM through a ForgePerceiver, which acts as an independent learner to capture diverse, subtle forgery cues both granularly and holistically, while preserving the pretrained Vision-Language Alignment (VLA) knowledge, and ii) provides a complementary discriminative cue -- Identity-Aware VLA score, derived by coupling cross-modal semantics with the forgery cues learned by ForgePerceiver. Notably, the VLA score is augmented by an identity prior-informed text prompting to capture authenticity cues tailored to each identity, thereby enabling more discriminative cross-modal semantics. Comprehensive experiments on video DFD benchmarks, including classical face-swapping forgeries and recent full-face generation forgeries, demonstrate that our VLAForge substantially outperforms state-of-the-art methods at both frame and video levels. Code is available at https://github.com/mala-lab/VLAForge.

comment: 14 pages, 7 figures, accepted by CVPR 2026

☆ CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin, Aarash Feizi, Kaixin Li, Patrice Bechard, Spandana Gella, Sai Rajeswar

Computer-use agents (CUAs) hold great promise for automating complex desktop workflows, yet progress toward general-purpose agents is bottlenecked by the scarcity of continuous, high-quality human demonstration videos. Recent work emphasizes that continuous video, not sparse screenshots, is the critical missing ingredient for scaling these agents. However, the largest existing open dataset, ScaleCUA, contains only 2 million screenshots, equating to less than 20 hours of video. To address this bottleneck, we introduce CUA-Suite, a large-scale ecosystem of expert video demonstrations and dense annotations for professional desktop computer-use agents. At its core is VideoCUA, which provides approximately 10,000 human-demonstrated tasks across 87 diverse applications with continuous 30 fps screen recordings, kinematic cursor traces, and multi-layerfed reasoning annotations, totaling approximately 55 hours and 6 million frames of expert video. Unlike sparse datasets that capture only final click coordinates, these continuous video streams preserve the full temporal dynamics of human interaction, forming a superset of information that can be losslessly transformed into the formats required by existing agent frameworks. CUA-Suite further provides two complementary resources: UI-Vision, a rigorous benchmark for evaluating grounding and planning capabilities in CUAs, and GroundCUA, a large-scale grounding dataset with 56K annotated screenshots and over 3.6 million UI element annotations. Preliminary evaluation reveals that current foundation action models struggle substantially with professional desktop applications (~60% task failure rate). Beyond evaluation, CUA-Suite's rich multimodal corpus supports emerging research directions including generalist screen parsing, continuous spatial control, video-based reward modeling, and visual world models. All data and models are publicly released.

comment: Project Page: https://cua-suite.github.io/

☆ The Gait Signature of Frailty: Transfer Learning based Deep Gait Models for Scalable Frailty Assessment

Laura McDaniel, Basudha Pal, Crystal Szczesny, Yuxiang Guo, Ryan Roemmich, Peter Abadir, Rama Chellappa

Frailty is a condition in aging medicine characterized by diminished physiological reserve and increased vulnerability to stressors. However, frailty assessment remains subjective, heterogeneous, and difficult to scale in clinical practice. Gait is a sensitive marker of biological aging, capturing multisystem decline before overt disability. Yet the application of modern computer vision to gait-based frailty assessment has been limited by small, imbalanced datasets and a lack of clinically representative benchmarks. In this work, we introduce a publicly available silhouette-based frailty gait dataset collected in a clinically realistic setting, spanning the full frailty spectrum and including older adults who use walking aids. Using this dataset, we evaluate how pretrained gait recognition models can be adapted for frailty classification under limited data conditions. We study both convolutional and hybrid attention-based architectures and show that predictive performance depends primarily on how pretrained representations are transferred rather than architectural complexity alone. Across models, selectively freezing low-level gait representations while allowing higher-level features to adapt yields more stable and generalizable performance than either full fine-tuning or rigid freezing. Conservative handling of class imbalance further improves training stability, and combining complementary learning objectives enhances discrimination between clinically adjacent frailty states. Interpretability analyses reveal consistent model attention to lower-limb and pelvic regions, aligning with established biomechanical correlates of frailty. Together, these findings establish gait-based representation learning as a scalable, non-invasive, and interpretable framework for frailty assessment and support the integration of modern biometric modeling approaches into aging research and clinical practice.

☆ Teacher-Student Diffusion Model for Text-Driven 3D Hand Motion Generation ICASSP2026

Ching-Lam Cheng, Bin Zhu, Shengfeng He

Generating realistic 3D hand motion from natural language is vital for VR, robotics, and human-computer interaction. Existing methods either focus on full-body motion, overlooking detailed hand gestures, or require explicit 3D object meshes, limiting generality. We propose TSHaMo, a model-agnostic teacher-student diffusion framework for text-driven hand motion generation. The student model learns to synthesize motions from text alone, while the teacher leverages auxiliary signals (e.g., MANO parameters) to provide structured guidance during training. A co-training strategy enables the student to benefit from the teacher's intermediate predictions while remaining text-only at inference. Evaluated using two diffusion backbones on GRAB and H2O, TSHaMo consistently improves motion quality and diversity. Ablations confirm its robustness and flexibility in using diverse auxiliary inputs without requiring 3D objects at test time.

comment: 5 pages, accepted by ICASSP2026

☆ Causal Transfer in Medical Image Analysis

Mohammed M. Abdelsamea, Daniel Tweneboah Anyimadu, Tasneem Selim, Saif Alzubi, Lei Zhang, Ahmed Karam Eldaly, Xujiong Ye

Medical imaging models frequently fail when deployed across hospitals, scanners, populations, or imaging protocols due to domain shift, limiting their clinical reliability. While transfer learning and domain adaptation address such shifts statistically, they often rely on spurious correlations that break under changing conditions. On the other hand, causal inference provides a principled way to identify invariant mechanisms that remain stable across environments. This survey introduces and systematises Causal Transfer Learning (CTL) for medical image analysis. This paradigm integrates causal reasoning with cross-domain representation learning to enable robust and generalisable clinical AI. We frame domain shift as a causal problem and analyse how structural causal models, invariant risk minimisation, and counterfactual reasoning can be embedded within transfer learning pipelines. We studied spanning classification, segmentation, reconstruction, anomaly detection, and multimodal imaging, and organised them by task, shift type, and causal assumption. A unified taxonomy is proposed that connects causal frameworks and transfer mechanisms. We further summarise datasets, benchmarks, and empirical gains, highlighting when and why causal transfer outperforms correlation-based domain adaptation. Finally, we discuss how CTL supports fairness, robustness, and trustworthy deployment in multi-institutional and federated settings, and outline open challenges and research directions for clinically reliable medical imaging AI.

☆ ViHOI: Human-Object Interaction Synthesis with Visual Priors

Songjin Cai, Linjie Zhong, Ling Guo, Changxing Ding

Generating realistic and physically plausible 3D Human-Object Interactions (HOI) remains a key challenge in motion generation. One primary reason is that describing these physical constraints with words alone is difficult. To address this limitation, we propose a new paradigm: extracting rich interaction priors from easily accessible 2D images. Specifically, we introduce ViHOI, a novel framework that enables diffusion-based generative models to leverage rich, task-specific priors from 2D images to enhance generation quality. We utilize a large Vision-Language Model (VLM) as a powerful prior-extraction engine and adopt a layer-decoupled strategy to obtain visual and textual priors. Concurrently, we design a Q-Former-based adapter that compresses the VLM's high-dimensional features into compact prior tokens, which significantly facilitates the conditional training of our diffusion model. Our framework is trained on motion-rendered images from the dataset to ensure strict semantic alignment between visual inputs and motion sequences. During inference, it leverages reference images synthesized by a text-to-image generation model to improve generalization to unseen objects and interaction categories. Experimental results demonstrate that ViHOI achieves state-of-the-art performance, outperforming existing methods across multiple benchmarks and demonstrating superior generalization.

comment: Accepted to CVPR 2026

☆ GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization

Pengyue Jia, Derong Xu, Yingyi Zhang, Xiaopeng Li, Wenlin Zhang, Yi Wen, Yuanshao Zhu, Xiangyu Zhao

Worldwide image geolocalization aims to predict precise GPS coordinates for images captured anywhere on Earth, which is challenging due to the large visual and geographic diversity. Recent methods mainly follow two paradigms: retrieval-based approaches that match queries against a reference database, and generation-based approaches that directly predict coordinates using Large Vision-Language Models (LVLMs). However, we observe distinct error profiles between them: retrieval excels at fine-grained instance matching, while generation offers robust semantic reasoning. This complementary heterogeneity suggests that no single paradigm is universally superior. To harness this potential, we propose GeoRouter, a dynamic routing framework that adaptively assigns each query to the optimal paradigm. GeoRouter leverages an LVLM backbone to analyze visual content and provide routing decisions. To optimize GeoRouter, we introduce a distance-aware preference objective that converts the distance gap between paradigms into a continuous supervision signal, explicitly reflecting relative performance differences. Furthermore, we construct GeoRouting, the first large-scale dataset tailored for training routing policies with independent paradigm predictions. Extensive experiments on IM2GPS3k and YFCC4k demonstrate that GeoRouter significantly outperforms state-of-the-art baselines.

☆ PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks

Cheng Cui, Yubo Zhang, Ting Sun, Xueqing Wang, Hongen Liu, Manhui Lin, Yue Zhang, Tingquan Gao, Changda Zhou, Jiaxuan Liu, Zelun Zhang, Jing Zhang, Jun Zhang, Yi Liu

The advent of "OCR 2.0" and large-scale vision-language models (VLMs) has set new benchmarks in text recognition. However, these unified architectures often come with significant computational demands, challenges in precise text localization within complex layouts, and a propensity for textual hallucinations. Revisiting the prevailing notion that model scale is the sole path to high accuracy, this paper introduces PP-OCRv5, a meticulously optimized, lightweight OCR system with merely 5 million parameters. We demonstrate that PP-OCRv5 achieves performance competitive with many billion-parameter VLMs on standard OCR benchmarks, while offering superior localization precision and reduced hallucinations. The cornerstone of our success lies not in architectural expansion but in a data-centric investigation. We systematically dissect the role of training data by quantifying three critical dimensions: data difficulty, data accuracy, and data diversity. Our extensive experiments reveal that with a sufficient volume of high-quality, accurately labeled, and diverse data, the performance ceiling for traditional, efficient two-stage OCR pipelines is far higher than commonly assumed. This work provides compelling evidence for the viability of lightweight, specialized models in the large-model era and offers practical insights into data curation for OCR. The source code and models are publicly available at https://github.com/PaddlePaddle/PaddleOCR.

☆ Language-Guided Structure-Aware Network for Camouflaged Object Detection

Min Zhang

Camouflaged Object Detection (COD) aims to segment objects that are highly integrated with the background in terms of color, texture, and structure, making it a highly challenging task in computer vision. Although existing methods introduce multi-scale fusion and attention mechanisms to alleviate the above issues, they generally lack the guidance of textual semantic priors, which limits the model's ability to focus on camouflaged regions in complex scenes. To address this issue, this paper proposes a Language-Guided Structure-Aware Network (LGSAN). Specifically, based on the visual backbone PVT-v2, we introduce CLIP to generate masks from text prompts and RGB images, thereby guiding the multi-scale features extracted by PVT-v2 to focus on potential target regions. On this foundation, we further design a Fourier Edge Enhancement Module (FEEM), which integrates multi-scale features with high-frequency information in the frequency domain to extract edge enhancement features. Furthermore, we propose a Structure-Aware Attention Module (SAAM) to effectively enhance the model's perception of object structures and boundaries. Finally, we introduce a Coarse-Guided Local Refinement Module (CGLRM) to enhance fine-grained reconstruction and boundary integrity of camouflaged object regions. Extensive experiments demonstrate that our method consistently achieves highly competitive performance across multiple COD datasets, validating its effectiveness and robustness.

☆ GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents

Yunzhe Wang, Runhui Xu, Kexin Zheng, Tianyi Zhang, Jayavibhav Niranjan Kogundi, Soham Hans, Volkan Ustun

Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds. These applications require agents to perceive rapid state changes, attribute actions to the correct entities, and reason about concurrent multi-agent behaviors from a first-person perspective, capabilities that existing benchmarks do not adequately evaluate. We introduce GameplayQA, a framework for evaluating agentic-centric perception and reasoning through video understanding. Specifically, we densely annotate multiplayer 3D gameplay videos at 1.22 labels/second, with time-synced, concurrent captions of states, actions, and events structured around a triadic system of Self, Other Agents, and the World, a natural decomposition for multi-agent environments. From these annotations, we refined 2.4K diagnostic QA pairs organized into three levels of cognitive complexity, accompanied by a structured distractor taxonomy that enables fine-grained analysis of where models hallucinate. Evaluation of frontier MLLMs reveals a substantial gap from human performance, with common failures in temporal and cross-video grounding, agent-role attribution, and handling the decision density of the game. We hope GameplayQA stimulates future research at the intersection of embodied AI, agentic perception, and world modeling.

☆ Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens

Ciem Cornelissen, Sam Leroux, Pieter Simoens

☆ Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

Cheng Cui, Ting Sun, Suyin Liang, Tingquan Gao, Zelun Zhang, Jiaxuan Liu, Xueqing Wang, Changda Zhou, Hongen Liu, Manhui Lin, Yue Zhang, Yubo Zhang, Jing Zhang, Jun Zhang, Xing Wei, Yi Liu, Dianhai Yu, Yanjun Ma

Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to a quadratic increase in the number of vision tokens and significantly raises computational costs. We attribute this inefficiency to substantial visual regions redundancy in document images, like background. To tackle this, we propose PaddleOCR-VL, a novel coarse-to-fine architecture that focuses on semantically relevant regions while suppressing redundant ones, thereby improving both efficiency and performance. Specifically, we introduce a lightweight Valid Region Focus Module (VRFM) which leverages localization and contextual relationship prediction capabilities to identify valid vision tokens. Subsequently, we design and train a compact yet powerful 0.9B vision-language model (PaddleOCR-VL-0.9B) to perform detailed recognition, guided by VRFM outputs to avoid direct processing of the entire large image. Extensive experiments demonstrate that PaddleOCR-VL achieves state-of-the-art performance in both page-level parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference while utilizing substantially fewer vision tokens and parameters, highlighting the effectiveness of targeted coarse-to-fine parsing for accurate and efficient document understanding. The source code and models are publicly available at https://github.com/PaddlePaddle/PaddleOCR.

comment: Accepted by CVPR2026

☆ Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

Shiqin Wang, Haoyang Chen, Huaizhou Huang, Yinkan He, Dongfang Sun, Xiaoqing Chen, Xingyu Liu, Zheng Wang, Kaiyan Zhao

The learning order of semantic classes significantly impacts unsupervised domain adaptation for semantic segmentation, especially under adverse weather conditions. Most existing curricula rely on handcrafted heuristics (e.g., fixed uncertainty metrics) and follow a static schedule, which fails to adapt to a model's evolving, high-dimensional training dynamics, leading to category bias. Inspired by Reinforcement Learning, we cast curriculum learning as a sequential decision problem and propose an autonomous class scheduler. This scheduler consists of two components: (i) a high-dimensional state encoder that maps the model's training status into a latent space and distills key features indicative of progress, and (ii) a category-fair policy-gradient objective that ensures balanced improvement across classes. Coupled with mixed source-target supervision, the learned class rankings direct the network's focus to the most informative classes at each stage, enabling more adaptive and dynamic learning. It is worth noting that our method achieves state-of-the-art performance on three widely used benchmarks (e.g., ACDC, Dark Zurich, and Nighttime Driving) and shows generalization ability in synthetic-to-real semantic segmentation.

comment: Accepted by CVPR 2026

☆ Refining time-space traffic diagrams: A neighborhood-adaptive linear regression method

Zhihong Yao, Yi Yu, Yunxia Wu, Hao Li, Yangsheng Jiang, Zhengbing He

The time-space (TS) traffic diagram serves as a crucial tool for characterizing the dynamic evolution of traffic flow, with its resolution directly influencing the effectiveness of traffic theory research and engineering applications. However, constrained by monitoring precision and sampling frequency, existing TS traffic diagrams commonly suffer from low resolution. To address this issue, this paper proposes a refinement method for TS traffic diagrams based on neighborhood-adaptive linear regression. Introducing the concept of neighborhood embedding into TS diagram refinement, the method leverages local pattern similarity in TS diagrams, adaptively identifies neighborhoods similar to target cells, and fits the low-to-high resolution mapping within these neighborhoods for refinement. It avoids the over-smoothing tendency of the traditional global linear model, allows the capture of unique traffic wave propagation and congestion evolution characteristics, and outperforms the traditional neighborhood embedding method in terms of local information utilization to achieve target cell refinement. Validation on two real datasets across multiple scales and upscaling factors shows that, compared to benchmark methods, the proposed method achieves improvements of 9.16%, 8.16%, 1.86%, 3.89%, and 5.83% in metrics including MAE, MAPE, CMJS, SSIM, and GMSD, respectively. Furthermore, the proposed method exhibits strong generalization and robustness in cross-day and cross-scenario validations. In summary, requiring only a minimal amount of paired high- and low-resolution training data, the proposed method features a concise formulation, providing a foundation for the low-cost, fine-grained refinement of low-sampling-rate traffic data.

☆ AMIF: Authorizable Medical Image Fusion Model with Built-in Authentication

Jie Song, Jun Jia, Wei Sun, Wangqiu Zhou, Tao Tan, Guangtao Zhai

Multimodal image fusion enables precise lesion localization and characterization for accurate diagnosis, thereby strengthening clinical decision-making and driving its growing prominence in medical imaging research. A powerful multimodal image fusion model relies on high-quality, clinically representative multimodal training data and a rigorously engineered model architecture. Therefore, the development of such professional radiomics models represents a collaborative achievement grounded in standardized acquisition, clinical-specific expertise, and algorithmic design proficiency, which necessitates protection of associated intellectual property rights. However, current multimodal image fusion models generate fused outputs without built-in mechanisms to safeguard intellectual property rights, inadvertently exposing proprietary model knowledge and sensitive training data through inference leakage. For example, malicious users can exploit fusion outputs and model distillation or other inference-based reverse engineering techniques to approximate the fusion performance of proprietary models. To address this issue, we propose AMIF, the first Authorizable Medical Image Fusion model with built-in authentication, which integrates authorization access control into the image fusion objective. For unauthorized usage, AMIF embeds explicit and visible copyright identifiers into fusion results. In contrast, high-quality fusion results are accessible upon successful key-based authentication.

☆ RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation

Kai Zhu, Zhenyu Cui, Zehua Zang, Jiahuan Zhou

comment: Accepted by CVPR 2026

☆ VERIA: Verification-Centric Multimodal Instance Augmentation for Long-Tailed 3D Object Detection

Jumin Lee, Siyeong Lee, Namil Kim, Sung-Eui Yoon

Long-tail distributions in driving datasets pose a fundamental challenge for 3D perception, as rare classes exhibit substantial intra-class diversity yet available samples cover this variation space only sparsely. Existing instance augmentation methods based on copy-paste or asset libraries improve rare-class exposure but are often limited in fine-grained diversity and scene-context placement. We propose VERIA, an image-first multimodal augmentation framework that synthesizes synchronized RGB--LiDAR instances using off-the-shelf foundation models and curates them with sequential semantic and geometric verification. This verification-centric design tends to select instances that better match real LiDAR statistics while spanning a wider range of intra-class variation. Stage-wise yield decomposition provides a log-based diagnostic of pipeline reliability. On nuScenes and Lyft, VERIA improves rare-class 3D object detection in both LiDAR-only and multimodal settings. Our code is available at https://sgvr.kaist.ac.kr/VERIA/.

☆ TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification

Guan Luo, Xiu Li, Rui Chen, Xuanyu Yi, Jing Lin, Chia-Hao Chen, Jiahang Liu, Song-Hai Zhang, Jianfeng Zhang

The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge limiting existing VAEs is the representation mismatch between ground-truth meshes and network predictions: GT meshes have arbitrary, variable topology, while VAEs typically predict fixed-structure implicit fields (\eg, SDF on regular grids). This inherent misalignment prevents establishing explicit mesh-level correspondences, forcing prior work to rely on indirect supervision signals such as SDF or rendering losses. Consequently, fine geometric details, particularly sharp features, are poorly preserved during reconstruction. To address this, we introduce TopoMesh, a sparse voxel-based VAE that unifies both GT and predicted meshes under a shared Dual Marching Cubes (DMC) topological framework. Specifically, we convert arbitrary input meshes into DMC-compliant representations via a remeshing algorithm that preserves sharp edges using an L$\infty$ distance metric. Our decoder outputs meshes in the same DMC format, ensuring that both predicted and target meshes share identical topological structures. This establishes explicit correspondences at the vertex and face level, allowing us to derive explicit mesh-level supervision signals for topology, vertex positions, and face orientations with clear gradients. Our sparse VAE architecture employs this unified framework and is trained with Teacher Forcing and progressive resolution training for stable and efficient convergence. Extensive experiments demonstrate that TopoMesh significantly outperforms existing VAEs in reconstruction fidelity, achieving superior preservation of sharp features and geometric details.

☆ ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors

Haodong Yu, Yabo Zhang, Donglin Di, Ruyi Zhang, Wangmeng Zuo

While diffusion models excel at generating images with conventional dimensions, pushing them to synthesize ultra-high-resolution imagery at extreme aspect ratios (EAR) often triggers catastrophic structural failures, such as object repetition and spatial fragmentation.This limitation fundamentally stems from a lack of robust spatial priors, as static text-to-image models are primarily trained on image distributions with conventional dimensions.To overcome this bottleneck, we present ScrollScape, a novel framework that reformulates EAR image synthesis into a continuous video generation process through two core innovations.By mapping the spatial expansion of a massive canvas to the temporal evolution of video frames, ScrollScape leverages the inherent temporal consistency of video models as a powerful global constraint to ensure long-range structural integrity.Specifically, Scanning Positional Encoding (ScanPE) distributes global coordinates across frames to act as a flexible moving camera, while Scrolling Super-Resolution (ScrollSR) leverages video super-resolution priors to circumvent memory bottlenecks, efficiently scaling outputs to an unprecedented 32K resolution. Fine-tuned on a curated 3K multi-ratio image dataset, ScrollScape effectively aligns pre-trained video priors with the EAR generation task. Extensive evaluations demonstrate that it significantly outperforms existing image-diffusion baselines by eliminating severe localized artifacts. Consequently, our method overcomes inherent structural bottlenecks to ensure exceptional global coherence and visual fidelity across diverse domains at extreme scales.

☆ Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep

Tianyi Liu, Ye Lu, Linfeng Zhang, Chen Cai, Jianjun Gao, Yi Wang, Kim-Hui Yap, Lap-Pui Chau

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally expensive due to the iterative denoising process, posing challenges for practical deployment. Existing video diffusion acceleration methods primarily exploit denoising timestep-level feature reuse, which mitigates the redundancy in denoising process, but overlooks the architectural redundancy within the DiT that many attention operations over spatio-temporal tokens are redundantly executed, offering little to no incremental contribution to the model output. This work introduces HetCache, a training-free diffusion acceleration framework designed to exploit the inherent heterogeneity in diffusion-based masked video-to-video (MV2V) generation and editing. Instead of uniformly reuse or randomly sampling tokens, HetCache assesses the contextual relevance and interaction strength among various types of tokens in designated computing steps. Guided by spatial priors, it divides the spatial-temporal tokens in DiT model into context and generative tokens, and selectively caches the context tokens that exhibit the strongest correlation and most representative semantics with generative ones. This strategy reduces redundant attention operations while maintaining editing consistency and fidelity. Experiments show that HetCache achieves a noticeable acceleration, including a 2.67$\times$ latency speedup and FLOPs reduction over commonly used foundation models, with negligible degradation in editing quality.

comment: 10 pages, 6 figures, accepted by CVPR2026

☆ Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning

Tommaso Galliena, Stefano Rosa, Tommaso Apicella, Pietro Morerio, Alessio Del Bue, Lorenzo Natale

comment: 24 pages, 7 figures, 7 tables (including Supplementary Materials)

☆ B-MoE: A Body-Part-Aware Mixture-of-Experts "All Parts Matter" Approach to Micro-Action Recognition

Nishit Poddar, Aglind Reka, Diana-Laura Borza, Snehashis Majhi, Michal Balazia, Abhijit Das, Francois Bremond

Micro-actions, fleeting and low-amplitude motions, such as glances, nods, or minor posture shifts, carry rich social meaning but remain difficult for current action recognition models to recognize due to their subtlety, short duration, and high inter-class ambiguity. In this paper, we introduce B-MoE, a Body-part-aware Mixture-of-Experts framework designed to explicitly model the structured nature of human motion. In B-MoE, each expert specializes in a distinct body region (head, body, upper limbs, lower limbs), and is based on the lightweight Macro-Micro Motion Encoder (M3E) that captures long-range contextual structure and fine-grained local motion. A cross-attention routing mechanism learns inter-region relationships and dynamically selects the most informative regions for each micro-action. B-MoE uses a dual-stream encoder that fuses these region-specific semantic cues with global motion features to jointly capture spatially localized cues and temporally subtle variations that characterize micro-actions. Experiments on three challenging benchmarks (MA-52, SocialGesture, and MPII-GroupInteraction) show consistent state-of-theart gains, with improvements in ambiguous, underrepresented, and low amplitude classes.

☆ InstanceRSR: Real-World Super-Resolution via Instance-Aware Representation Alignment ICASSP 2026

Zixin Guo, Kai Zhao, Luyan Zhang

Existing real-world super-resolution (RSR) methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions. However, they often struggle to recover fine-grained details of diverse object instances in complex real-world scenes. This limitation primarily arises because commonly adopted denoising losses (e.g., MSE) inherently favor global consistency while neglecting instance-level perception and restoration. To address this issue, we propose InstanceRSR, a novel RSR framework that jointly models semantic information and introduces instance-level feature alignment. Specifically, we employ low-resolution (LR) images as global consistency guidance while jointly modeling image data and semantic segmentation maps to enforce semantic relevance during sampling. Moreover, we design an instance representation learning module to align the diffusion latent space with the instance latent space, enabling instance-aware feature alignment, and further incorporate a scale alignment mechanism to enhance fine-grained perception and detail recovery. Benefiting from these designs, our approach not only generates photorealistic details but also preserves semantic consistency at the instance level. Extensive experiments on multiple real-world benchmarks demonstrate that InstanceRSR significantly outperforms existing methods in both quantitative metrics and visual quality, achieving new state-of-the-art (SOTA) performance.

comment: 4 pages, 4 figures, 2 tables. Accepted by ICASSP 2026

☆ Attack Assessment and Augmented Identity Recognition for Human Skeleton Data

Joseph G. Zalameda, Megan A. Witherow, Alexander M. Glandon, Jose Aguilera, Khan M. Iftekharuddin

Machine learning models trained on small data sets for security applications are especially vulnerable to adversarial attacks. Person identification from LiDAR based skeleton data requires time consuming and expensive data acquisition for each subject identity. Recently, Assessment and Augmented Identity Recognition for Skeletons (AAIRS) has been used to train Hierarchical Co-occurrence Networks for Person Identification (HCN-ID) with small LiDAR based skeleton data sets. However, AAIRS does not evaluate robustness of HCN-ID to adversarial attacks or inoculate the model to defend against such attacks. Popular perturbation-based approaches to generating adversarial attacks are constrained to targeted perturbations added to real training samples, which is not ideal for inoculating models with small training sets. Thus, we propose Attack-AAIRS, a novel addition to the AAIRS framework. Attack-AAIRS leverages a small real data set and a GAN generated synthetic data set to assess and improve model robustness against unseen adversarial attacks. Rather than being constrained to perturbations of limited real training samples, the GAN learns the distribution of adversarial attack samples that exploit weaknesses in HCN-ID. Attack samples drawn from this distribution augment training for inoculation of the HCN-ID to improve robustness. Ten-fold cross validation of Attack-AAIRS yields increased robustness to unseen attacks- including FGSM, PGD, Additive Gaussian Noise, MI-FGSM, and BIM. The HCN-ID Synthetic Data Quality Score for Attack-AAIRS indicates that generated attack samples are of similar quality to the original benign synthetic samples generated by AAIRS. Furthermore, inoculated models show consistent final test accuracy with the original model trained on real data, demonstrating that our method improves robustness to adversarial attacks without reducing test performance on real data.

comment: 8 pages, 9 figures, 3 tables

☆ RVLM: Recursive Vision-Language Models with Adaptive Depth

Nicanor Mayumu, Zeenath Khan, Melodena Stephens, Patrick Mukala, Farhad Oroumchian

Medical AI systems face two fundamental limitations. First, conventional vision-language models (VLMs) perform single-pass inference, yielding black-box predictions that cannot be audited or explained in clinical terms. Second, iterative reasoning systems that expose intermediate steps rely on fixed iteration budgets wasting compute on simple cases while providing insufficient depth for complex ones. We address both limitations with a unified framework. RVLM replaces single-pass inference with an iterative generate-execute loop: at each step, the model writes Python code, invokes vision sub-agents, manipulates images, and accumulates evidence. Every diagnostic claim is grounded in executable code, satisfying auditability requirements of clinical AI governance frameworks. RRouter makes iteration depth adaptive: a lightweight controller predicts the optimal budget from task-complexity features, then monitors progress and terminates early when reasoning stalls. We evaluate on BraTS 2023 Meningioma (brain MRI) and MIMIC-CXR (chest X-ray) using Gemini 2.5 Flash without fine-tuning. Across repeated runs, RVLM shows high consistency on salient findings (e.g., mass presence and enhancement) and can detect cross-modal discrepancies between Fluid-Attenuated Inversion Recovery (FLAIR) signal characteristics and segmentation boundaries. On MIMIC-CXR, it generates structured reports and correctly recognises view-specific artefacts. Code: https://github.com/nican2018/rvlm.

☆ HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer

Minjun Kim, Minje Kim

Personalized Federated Learning (PFL) aims to deliver effective client-specific models under heterogeneous distributions, yet existing methods suffer from shallow prototype alignment and brittle server-side distillation. We propose HEART-PFL, a dual-sided framework that (i) performs depth-aware Hierarchical Directional Alignment (HDA) using cosine similarity in the early stage and MSE matching in the deep stage to preserve client specificity, and (ii) stabilizes global updates through Adversarial Knowledge Transfer (AKT) with symmetric KL distillation on clean and adversarial proxy data. Using lightweight adapters with only 1.46M trainable parameters, HEART-PFL achieves state-of-the-art personalized accuracy on CIFAR-100, Flowers-102, and Caltech-101 (63.42%, 84.23%, and 95.67%, respectively) under Dirichlet non-IID partitions, and remains robust to out-of-domain proxy data. Ablation studies further confirm that HDA and AKT provide complementary gains in alignment, robustness, and optimization stability, offering insights into how the two components mutually reinforce effective personalization. Overall, these results demonstrate that HEART-PFL simultaneously enhances personalization and global stability, highlighting its potential as a strong and scalable solution for PFL(code available at https://github.com/danny0628/HEART-PFL).

comment: Accepted at WACV 2026. 8 pages, 7 figures, 3 tables

☆ Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement

Xin Zhang, Jianyang Xu, Hao Peng, Dongjing Wang, Jingyuan Zheng, Yu Li, Yuyu Yin, Hongbo Wang

Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of enhancing teacher knowledge quality. In this paper, we propose Text-guided Multi-view Knowledge Distillation (TMKD), which leverages dual-modality teachers, a visual teacher and a text teacher (CLIP), to provide richer supervisory signals. Specifically, we enhance the visual teacher with multi-view inputs incorporating visual priors (edge and high-frequency features), while the text teacher generates semantic weights through prior-aware prompts to guide adaptive feature fusion. Additionally, we introduce vision-language contrastive regularization to strengthen semantic knowledge in the student model. Extensive experiments on five benchmarks demonstrate that TMKD consistently improves knowledge distillation performance by up to 4.49\%, validating the effectiveness of our dual-teacher multi-view enhancement strategy. Code is available at https://anonymous.4open.science/r/TMKD-main-44D1.

comment: 9 pages, 6 figures

☆ RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution

Yushuai Song, Weize Quan, Weining Wang, Jiahui Sun, Jing Liu, Meng Li, Pengbin Yu, Zhentao Chen, Wei Shen, Lunxi Yuan, Dong-ming Yan

Recent advances in generative super-resolution (SR) have greatly improved visual realism, yet existing evaluation and optimization frameworks remain misaligned with human perception. Full-Reference and No-Reference metrics often fail to reflect perceptual preference, either penalizing semantically plausible details due to pixel misalignment or favoring visually sharp but inconsistent artifacts. Moreover, most SR methods rely on ground-truth (GT)-dependent distribution matching, which does not necessarily correspond to human judgments. In this work, we propose RefReward-SR, a low-resolution (LR) reference-aware reward model for preference-aligned SR. Instead of relying on GT supervision or NR evaluation, RefReward-SR assesses high-resolution (HR) reconstructions conditioned on their LR inputs, treating the LR image as a semantic anchor. Leveraging the visual-linguistic priors of a Multimodal Large Language Models (MLLM), it evaluates semantic consistency and plausibility in a reasoning-aware manner. To support this paradigm, we construct RefSR-18K, the first large-scale LR-conditioned preference dataset for SR, providing pairwise rankings based on LR-HR consistency and HR naturalness. We fine-tune the MLLM with Group Relative Policy Optimization (GRPO) using LR-conditioned ranking rewards, and further integrate GRPO into SR model training with RefReward-SR as the core reward signal for preference-aligned generation. Extensive experiments show that our framework achieves substantially better alignment with human judgments, producing reconstructions that preserve semantic consistency while enhancing perceptual plausibility and visual naturalness. Code, models, and datasets will be released upon paper acceptance.

☆ Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection

Adhemar de Senneville, Xavier Bou, Jérémy Anger, Rafael Grompone, Gabriele Facciolo

Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor performance at image classification tasks, underperforming against CLIP-based methods. Notably, this gap is surprising because many LVLMs use CLIP-pretrained vision encoders. Yet LVLMs are not inherently limited by CLIP's architecture with independent vision and text encoders. In CLIP, this separation biases classification toward class-name matching rather than joint visual-text reasoning. In this paper we show that, despite their poor raw performance, LVLMs can improve visual feature class separability at inference using prompt conditioning, and LVLMs' internal representations, especially attention heads, can outperform the model itself at zero-shot and few-shot classification. We introduce Head Ensemble Classifiers (HEC) to bridge the performance gap between CLIP-based and LVLM-based classification methods. Inspired by Gaussian Discriminant Analysis, HEC ranks the most discriminative vision and text heads and combines them into a training-free classifier. We show that HEC achieves state-of-the-art performance in few-shot and zero-shot classification across 12 datasets.

☆ Modeling Spatiotemporal Neural Frames for High Resolution Brain Dynamic

Wanying Qu, Jianxiong Gao, Wei Wang, Yanwei Fu

comment: CVPR 2026

☆ Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object Detection

Xu Zhang, Zhe Chen, Jing Zhang, Dacheng Tao

Most referring object detection (ROD) models, especially the modern grounding detectors, are designed for data-rich conditions, yet many practical deployments, such as robotics, augmented reality, and other specialized domains, would face severe label scarcity. In such regimes, end-to-end grounding detectors need to learn spatial and semantic structure from scratch, wasting precious samples. We ask a simple question: Can explicit reasoning priors help models learn more efficiently when data is scarce? To explore this, we first introduce a Data-efficient Referring Object Detection (De-ROD) task, which is a benchmark protocol for measuring ROD performance in low-data and few-shot settings. We then propose the HeROD (Heuristic-inspired ROD), a lightweight, model-agnostic framework that injects explicit, heuristic-inspired spatial and semantic reasoning priors, which are interpretable signals derived based on the referring phrase, into 3 stages of a modern DETR-style pipeline: proposal ranking, prediction fusion, and Hungarian matching. By biasing both training and inference toward plausible candidates, these priors promise to improve label efficiency and convergence performance. On RefCOCO, RefCOCO+, and RefCOCOg, HeROD consistently outperforms strong grounding baselines in scarce-label regimes. More broadly, our results suggest that integrating simple, interpretable reasoning priors provides a practical and extensible path toward better data-efficient vision-language understanding.

comment: CVPR2026

☆ CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare

Akash Ghosh, Tajamul Ashraf, Rishu Kumar Singh, Numan Saeed, Sriparna Saha, Xiuying Chen, Salman Khan

Multimodal agentic pipelines are transforming human-computer interaction by enabling efficient and accessible automation of complex, real-world tasks. However, recent efforts have focused on short-horizon or general-purpose applications (e.g., mobile or desktop interfaces), leaving long-horizon automation for domain-specific systems, particularly in healthcare, largely unexplored. To address this, we introduce CareFlow, a high-quality human-annotated benchmark comprising complex, long-horizon software workflows across medical annotation tools, DICOM viewers, EHR systems, and laboratory information systems. On this benchmark, existing vision-language models (VLMs) perform poorly, struggling with long-horizon reasoning and multi-step interactions in medical contexts. To overcome this, we propose CarePilot, a multi-agent framework based on the actor-critic paradigm. The Actor integrates tool grounding with dual-memory mechanisms (long-term and short-term experience) to predict the next semantic action from the visual interface and system state. The Critic evaluates each action, updates memory based on observed effects, and either executes or provides corrective feedback to refine the workflow. Through iterative agentic simulation, the Actor learns to perform more robust and reasoning-aware predictions during inference. Our experiments show that CarePilot achieves state-of-the-art performance, outperforming strong closed-source and open-source multimodal baselines by approximately 15.26% and 3.38%, respectively, on our benchmark and out-of-distribution dataset.

comment: CVPR 2026 Findings

☆ A convergent Plug-and-Play Majorization-Minimization algorithm for Poisson inverse problems

Thibaut Modrzyk, Ane Etxebeste, Élie Bretin, Voichita Maxim

In this paper, we present a novel variational plug-and-play algorithm for Poisson inverse problems. Our approach minimizes an explicit functional which is the sum of a Kullback-Leibler data fidelity term and a regularization term based on a pre-trained neural network. By combining classical likelihood maximization methods with recent advances in gradient-based denoisers, we allow the use of pre-trained Gaussian denoisers without sacrificing convergence guarantees. The algorithm is formulated in the majorization-minimization framework, which guarantees convergence to a stationary point. Numerical experiments confirm state-of-the-art performance in deconvolution and tomography under moderate noise, and demonstrate clear superiority in high-noise conditions, making this method particularly valuable for nuclear medicine applications.

☆ LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds

Jaehun Bang, Jinhyeok Kim, Minji Kim, Seungheon Jeong, Kyungdon Joo

Open-vocabulary 3D scene understanding enables users to segment novel objects in complex 3D environments through natural language. However, existing approaches remain slow, memory-intensive, and overly complex due to iterative optimization and dense per-Gaussian feature assignments. To address this, we propose LightSplat, a fast and memory-efficient training-free framework that injects compact 2-byte semantic indices into 3D representations from multi-view images. By assigning semantic indices only to salient regions and managing them with a lightweight index-feature mapping, LightSplat eliminates costly feature optimization and storage overhead. We further ensure semantic consistency and efficient inference via single-step clustering that links geometrically and semantically related masks in 3D. We evaluate our method on LERF-OVS, ScanNet, and DL3DV-OVS across complex indoor-outdoor scenes. As a result, LightSplat achieves state-of-the-art performance with up to 50-400x speedup and 64x lower memory, enabling scalable language-driven 3D understanding. For more details, visit our project page https://vision3d-lab.github.io/lightsplat/.

comment: Accepted to CVPR 2026

☆ Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection

Zhanhe Lei, Zhongyuan Wang, Jikang Cheng, Baojin Huang, Yuhong Yang, Zhen Han, Chao Liang, Dengpan Ye

Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning (TSRL) framework to dynamically optimize the training curriculum. Our method models the training process as a Markov Decision Process where a ``Tutor'' agent learns to guide a ``Student'' (the deepfake detector). The Tutor, implemented as a Proximal Policy Optimization (PPO) agent, observes a rich state representation for each training sample, encapsulating not only its visual features but also its historical learning dynamics, such as EMA loss and forgetting counts. Based on this state, the Tutor takes an action by assigning a continuous weight (0-1) to the sample's loss, thereby dynamically re-weighting the training batch. The Tutor is rewarded based on the Student's immediate performance change, specifically rewarding transitions from incorrect to correct predictions. This strategy encourages the Tutor to learn a curriculum that prioritizes high-value samples, such as hard-but-learnable examples, leading to a more efficient and effective training process. We demonstrate that this adaptive curriculum improves the Student's generalization capabilities against unseen manipulation techniques compared to traditional training methods. Code is available at https://github.com/wannac1/TSRL.

comment: Accepted to CVPR 2026

☆ Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation

Haoyu Ji, Bowen Chen, Zhihao Yang, Wenze Huang, Yu Gao, Xueting Liu, Weihong Ren, Zhiyong Wang, Honghai Liu

Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS methodologies face challenges of limited inter-class discriminability and blurred segmentation boundaries, primarily due to insufficient distinction of spatio-temporal patterns between adjacent actions. To address these limitations, we propose Spectral Scalpel, a frequency-selective filtering framework aimed at suppressing shared frequency components between adjacent distinct actions while amplifying their action-specific frequencies, thereby enhancing inter-action discrepancies and sharpening transition boundaries. Specifically, Spectral Scalpel employs adaptive multi-scale spectral filters as scalpels to edit frequency spectra, coupled with a discrepancy loss between adjacent actions serving as the surgical objective. This design amplifies representational disparities between neighboring actions, effectively mitigating boundary localization ambiguities and inter-class confusion. Furthermore, complementing long-term temporal modeling, we introduce a frequency-aware channel mixer to strengthen channel evolution by aggregating spectra across channels. This work presents a novel paradigm for STAS that extends conventional spatio-temporal modeling by incorporating frequency-domain analysis. Extensive experiments on five public datasets demonstrate that Spectral Scalpel achieves state-of-the-art performance. Code is available at https://github.com/HaoyuJi/SpecScalpel.

comment: CVPR Conference

☆ Reservoir-Based Graph Convolutional Networks

Mayssa Soussia, Gita Ayu Salsabila, Mohamed Ali Mahjoub, Islem Rekik

Message passing is a core mechanism in Graph Neural Networks (GNNs), enabling the iterative update of node embeddings by aggregating information from neighboring nodes. Graph Convolutional Networks (GCNs) exemplify this approach by adapting convolutional operations for graph structures, allowing features from adjacent nodes to be combined effectively. However, GCNs encounter challenges with complex or dynamic data. Capturing long-range dependencies often requires deeper layers, which not only increase computational costs but also lead to over-smoothing, where node embeddings become indistinguishable. To overcome these challenges, reservoir computing has been integrated into GNNs, leveraging iterative message-passing dynamics for stable information propagation without extensive parameter tuning. Despite its promise, existing reservoir-based models lack structured convolutional mechanisms, limiting their ability to accurately aggregate multi-hop neighborhood information. To address these limitations, we propose RGC-Net (Reservoir-based Graph Convolutional Network), which integrates reservoir dynamics with structured graph convolution. Key contributions include: (i) a reimagined convolutional framework with fixed random reservoir weights and a leaky integrator to enhance feature retention; (ii) a robust, adaptable model for graph classification; and (iii) an RGC-Net-powered transformer for graph generation with application to dynamic brain connectivity. Extensive experiments show that RGC-Net achieves state-of-the-art performance in classification and generative tasks, including brain graph evolution, with faster convergence and reduced over-smoothing. Source code is available at https://github.com/basiralab/RGC-Net .

☆ Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization

David Faget, José Luis Lisani, Miguel Colom

Planet-scale photo geolocalization involves the intricate task of estimating the geographic location depicted in an image purely based on its visual features. While deep learning models, particularly convolutional neural networks (CNNs), have significantly advanced this field, understanding the reasoning behind their predictions remains challenging. In this paper, we present Combi-CAM, a novel method that enhances the explainability of CNN-based geolocalization models by combining gradient-weighted class activation maps obtained from several layers of the network architecture, rather than using only information from the deepest layer as is typically done. This approach provides a more detailed understanding of how different image features contribute to the model's decisions, offering deeper insights than the traditional approaches.

☆ Retinal Layer Segmentation in OCT Images With 2.5D Cross-slice Feature Fusion Module for Glaucoma Assessment

Hyunwoo Kim, Heesuk Kim, Wungrak Choi, Jae-Sang Hyun

For accurate glaucoma diagnosis and monitoring, reliable retinal layer segmentation in OCT images is essential. However, existing 2D segmentation methods often suffer from slice-to-slice inconsistencies due to the lack of contextual information across adjacent B-scans. 3D segmentation methods are better for capturing slice-to-slice context, but they require expensive computational resources. To address these limitations, we propose a 2.5D segmentation framework that incorporates a novel cross-slice feature fusion (CFF) module into a U-Net-like architecture. The CFF module fuses inter-slice features to effectively capture contextual information, enabling consistent boundary detection across slices and improved robustness in noisy regions. The framework was validated on both a clinical dataset and the publicly available DUKE DME dataset. Compared to other segmentation methods without the CFF module, the proposed method achieved an 8.56% reduction in mean absolute distance and a 13.92% reduction in root mean square error, demonstrating improved segmentation accuracy and robustness. Overall, the proposed 2.5D framework balances contextual awareness and computational efficiency, enabling anatomically reliable retinal layer delineation for automated glaucoma evaluation and potential clinical applications.

☆ Comparative analysis of dual-form networks for live land monitoring using multi-modal satellite image time series

Iris Dumeur, Jérémy Anger, Gabriele Facciolo

Multi-modal Satellite Image Time Series (SITS) analysis faces significant computational challenges for live land monitoring applications. While Transformer architectures excel at capturing temporal dependencies and fusing multi-modal data, their quadratic computational complexity and the need to reprocess entire sequences for each new acquisition limit their deployment for regular, large-area monitoring. This paper studies various dual-form attention mechanisms for efficient multi-modal SITS analysis, that enable parallel training while supporting recurrent inference for incremental processing. We compare linear attention and retention mechanisms within a multi-modal spectro-temporal encoder. To address SITS-specific challenges of temporal irregularity and unalignment, we develop temporal adaptations of dual-form mechanisms that compute token distances based on actual acquisition dates rather than sequence indices. Our approach is evaluated on two tasks using Sentinel-1 and Sentinel-2 data: multi-modal SITS forecasting as a proxy task, and real-world solar panel construction monitoring. Experimental results demonstrate that dual-form mechanisms achieve performance comparable to standard Transformers while enabling efficient recurrent inference. The multimodal framework consistently outperforms mono-modal approaches across both tasks, demonstrating the effectiveness of dual mechanisms for sensor fusion. The results presented in this work open new opportunities for operational land monitoring systems requiring regular updates over large geographic areas.

☆ Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting

Fan Chen, Shuyin Xia, Yi Wang, Xinbo Gao

Single-source domain generalization for crowd counting remains highly challenging because a single labeled source domain often contains heterogeneous latent domains, while test data may exhibit severe distribution shifts. A fundamental difficulty lies in stable latent domain discovery: directly performing flat clustering on evolving sample-level latent features is easily affected by feature noise, outliers, and representation drift, leading to unreliable pseudo-domain assignments and weakened domain-structured learning. To address this issue, we propose a granular ball guided stable latent domain discovery framework for domain-general crowd counting. Specifically, the proposed method first organizes samples into compact local granular balls and then clusters granular ball centers as representatives to obtain pseudo-domains, transforming direct sample-level clustering into a hierarchical representative-based clustering process. This design yields more stable and semantically consistent pseudo-domain assignments. Built upon the discovered latent domains, we further develop a two-branch learning framework that enhances transferable semantic representations via semantic codebook re-encoding while modeling domain-specific appearance variations through a style branch, thereby reducing semantic--style entanglement and improving generalization under domain shifts. Extensive experiments on ShanghaiTech A/B, UCF\_QNRF, and NWPU-Crowd under a strict no-adaptation protocol demonstrate that the proposed method consistently outperforms strong baselines, especially under large domain gaps.

☆ LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation

Haoyu Ji, Xueting Liu, Yu Gao, Wenze Huang, Zhihao Yang, Weihong Ren, Zhiyong Wang, Honghai Liu

Skeleton-based Temporal Action Segmentation (STAS) aims to densely parse untrimmed skeletal sequences into frame-level action categories. However, existing methods, while proficient at capturing spatio-temporal kinematics, neglect the underlying physical dynamics that govern human motion. This oversight limits inter-class discriminability between actions with similar kinematics but distinct dynamic intents, and hinders precise boundary localization where dynamic force profiles shift. To address these, we propose the Lagrangian-Dynamic Informed Network (LaDy), a framework integrating principles of Lagrangian dynamics into the segmentation process. Specifically, LaDy first computes generalized coordinates from joint positions and then estimates Lagrangian terms under physical constraints to explicitly synthesize the generalized forces. To further ensure physical coherence, our Energy Consistency Loss enforces the work-energy theorem, aligning kinetic energy change with the work done by the net force. The learned dynamics then drive a Spatio-Temporal Modulation module: Spatially, generalized forces are fused with spatial representations to provide more discriminative semantics. Temporally, salient dynamic signals are constructed for temporal gating, thereby significantly enhancing boundary awareness. Experiments on challenging datasets show that LaDy achieves state-of-the-art performance, validating the integration of physical dynamics for action segmentation. Code is available at https://github.com/HaoyuJi/LaDy.

comment: CVPR Conference

☆ LGTM: Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulation

Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser, Ko Watanabe, Riku Takahashi, Andreas Dengel

Diffusion models have demonstrated high-quality performance in conditional text-to-image generation, particularly with structural cues such as edges, layouts, and depth. However, lighting conditions have received limited attention and remain difficult to control within the generative process. Existing methods handle lighting through a two-stage pipeline that relights images after generation, which is inefficient. Moreover, they rely on fine-tuning with large datasets and heavy computation, limiting their adaptability to new models and tasks. To address this, we propose a novel Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulation (LGTM), which manipulates the initial latent noise of the diffusion process to guide image generation with text prompts and user-specified light directions. Through a channel-wise analysis of the latent space, we find that selectively manipulating latent channels enables fine-grained lighting control without fine-tuning or modifying the pre-trained model. Extensive experiments show that our method surpasses prompt-based baselines in lighting consistency, while preserving image quality and text alignment. This approach introduces new possibilities for dynamic, user-guided light control. Furthermore, it integrates seamlessly with models like ControlNet, demonstrating adaptability across diverse scenarios.

comment: Accepted to IJCNN2026

☆ When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm

Ye Leng, Junjie Chu, Mingjie Li, Chenhao Lin, Chao Shen, Michael Backes, Yun Shen, Yang Zhang

Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much stronger capability for semantic understanding, enabling them to process more complex textual inputs and comprehend richer contextual meanings. However, this enhanced semantic ability may also introduce new and potentially greater safety risks. Taking diffusion models as a reference point, we systematically analyze and compare the safety risks of emerging MLLMs along two dimensions: unsafe content generation and fake image synthesis. Across multiple unsafe generation benchmark datasets, we observe that MLLMs tend to generate more unsafe images than diffusion models. This difference partly arises because diffusion models often fail to interpret abstract prompts, producing corrupted outputs, whereas MLLMs can comprehend these prompts and generate unsafe content. For current advanced fake image detectors, MLLM-generated images are also notably harder to identify. Even when detectors are retrained with MLLMs-specific data, they can still be bypassed by simply providing MLLMs with longer and more descriptive inputs. Our measurements indicate that the emerging safety risks of the cutting-edge generative paradigm, MLLMs, have not been sufficiently recognized, posing new challenges to real-world safety.

comment: Accepted by CVPR 2026. 15 pages, 11 figures

☆ PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation

Yuheng Feng, Wen Zhang, Haodong Duan, Xingxing Zou

We present PosterIQ, a design-driven benchmark for poster understanding and generation, annotated across composition structure, typographic hierarchy, and semantic intent. It includes 7,765 image-annotation instances and 822 generation prompts spanning real, professional, and synthetic cases. To bridge visual design cognition and generative modeling, we define tasks for layout parsing, text-image correspondence, typography/readability and font perception, design quality assessment, and controllable, composition-aware generation with metaphor. We evaluate state-of-the-art MLLMs and diffusion-based generators, finding persistent gaps in visual hierarchy, typographic semantics, saliency control, and intention communication; commercial models lead on high-level reasoning but act as insensitive automatic raters, while generators render text well yet struggle with composition-aware synthesis. Extensive analyses show PosterIQ is both a quantitative benchmark and a diagnostic tool for design reasoning, offering reproducible, task-specific metrics. We aim to catalyze models' creativity and integrate human-centred design principles into generative vision-language systems.

comment: CVPR 2026, Project Page: https://github.com/ArtmeScienceLab/PosterIQ-Benchmark

☆ AD-Reasoning: Multimodal Guideline-Guided Reasoning for Alzheimer's Disease Diagnosis

Qiuhui Chen, Yushan Deng, Xuancheng Yao, Yi Hong

Alzheimer's disease (AD) diagnosis requires integrating neuroimaging with heterogeneous clinical evidence and reasoning under established criteria, yet most multimodal models remain opaque and weakly guideline-aligned. We present AD-Reasoning, a multimodal framework that couples structural MRI with six clinical modalities and a rule-based verifier to generate structured, NIA-AA-consistent diagnoses. AD-Reasoning combines modality-specific encoders, bidirectional cross-attention fusion, and reinforcement fine-tuning with verifiable rewards that enforce output format, guideline evidence coverage, and reasoning--decision consistency. We also release AD-MultiSense, a 10,378-visit multimodal QA dataset with guideline-validated rationales built from ADNI/AIBL. On AD-MultiSense, AD-Reasoning achieves state-of-the-art diagnostic accuracy and produces structured rationales that improve transparency over recent baselines, while providing transparent rationales.

comment: ICME 2026

☆ Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

Han Sun, Qin Li, Peixin Wang, Min Zhang

Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous driving and medical image analysis. Through systematic empirical investigation, we identify that the imbalanced attention allocation, both across modalities (i.e., vision and language) and within modalities (among individual tokens), exhibits a strong causal correlation with the occurrence of object hallucination. Leveraging this insight, we introduce a novel concept termed attention imbalance, which not only quantifies the degree of attention disparity but also visually delineates the underlying patterns (e.g., over-attentiveness to irrelevant language tokens or under-attentiveness to discriminative visual features) that drive object hallucination. To mitigate object hallucination, we further propose Attention Imbalance Rectification (AIR), a lightweight decoding-time intervention method that reallocates attention weights and adjusts attention distributions to rectify modality-wise and token-wise imbalances. Extensive evaluations on four mainstream LVLMs and three benchmarks (CHAIR, POPE, and MM-Vet) with seven baselines demonstrate that AIR consistently reduces object hallucination rates, achieving up to a 35.1% reduction compared to the baselines, while improving up to 15.9% of LVLMs' general capability across diverse vision-language tasks.

comment: CVPR 2026(Findings)

☆ Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics

Jipeng Liu, Haichao Shi, Siyu Xing, Rong Yin, Xiao-Yu Zhang

While Vision-Language Models (VLMs) like CLIP have emerged as a dominant paradigm for generalizable deepfake detection, a representational disconnect remains: their semantic-centric pre-training is ill-suited for capturing non-semantic artifacts inherent to hyper-realistic synthesis. In this work, we identify a failure mode termed Optimization Collapse, where detectors trained with Sharpness-Aware Minimization (SAM) degenerate to random guessing on non-semantic forgeries once the perturbation radius exceeds a narrow threshold. To theoretically formalize this collapse, we propose the Critical Optimization Radius (COR) to quantify the geometric stability of the optimization landscape, and leverage the Gradient Signal-to-Noise Ratio (GSNR) to measure generalization potential. We establish a theorem proving that COR increases monotonically with GSNR, thereby revealing that the geometric instability of SAM optimization originates from degraded intrinsic generalization potential. This result identifies the layer-wise attenuation of GSNR as the root cause of Optimization Collapse in detecting non-semantic forgeries. Although naively reducing perturbation radius yields stable convergence under SAM, it merely treats the symptom without mitigating the intrinsic generalization degradation, necessitating enhanced gradient fidelity. Building on this insight, we propose the Contrastive Regional Injection Transformer (CoRIT), which integrates a computationally efficient Contrastive Gradient Proxy (CGP) with three training-free strategies: Region Refinement Mask to suppress CGP variance, Regional Signal Injection to preserve CGP magnitude, and Hierarchical Representation Integration to attain more generalizable representations. Extensive experiments demonstrate that CoRIT mitigates optimization collapse and achieves state-of-the-art generalization across cross-domain and universal forgery benchmarks.

☆ LGEST: Dynamic Spatial-Spectral Expert Routing for Hyperspectral Image Classification

Jiawen Wen, Suixuan Qiu, Zihang Luo, Xiaofei Yang, Haotian Shi

Deep learning methods, including Convolutional Neural Networks, Transformers and Mamba, have achieved remarkable success in hyperspectral image (HSI) classification. Nevertheless, existing methods exhibit inflexible integration of local-global representations, inadequate handling of spectral-spatial scale disparities across heterogeneous bands, and susceptibility to the Hughes phenomenon under high-dimensional sample heterogeneity. To address these challenges, we propose Local-Global Expert Spatial-Spectral Transformer (LGEST), a novel framework that synergistically combines three key innovations. The LGEST first employs a Deep Spatial-Spectral Autoencoder (DSAE) to generate compact yet discriminative embeddings through hierarchical nonlinear compression, preserving 3D neighborhood coherence while mitigating information loss in high-dimensional spaces. Secondly, a Cross-Interactive Mixed Expert Feature Pyramid (CIEM-FPN) leverages cross-attention mechanisms and residual mixture-of-experts layers to dynamically fuse multi-scale features, adaptively weighting spectral discriminability and spatial saliency through learnable gating functions. Finally, a Local-Global Expert System (LGES) processes decomposed features via sparsely activated expert pairs: convolutional sub-experts capture fine-grained textures, while transformer sub-experts model long-range contextual dependencies, with a routing controller dynamically selecting experts based on real-time feature saliency. Extensive experiments on four benchmark datasets demonstrate that LGEST consistently outperforms state-of-the-art methods.

☆ HAM: A Training-Free Style Transfer Approach via Heterogeneous Attention Modulation for Diffusion Models

Yeqi He, Liang Li, Zhiwen Yang, Xichun Sheng, Zhidong Zhao, Chenggang Yan

Diffusion models have demonstrated remarkable performance in image generation, particularly within the domain of style transfer. Prevailing style transfer approaches typically leverage pre-trained diffusion models' robust feature extraction capabilities alongside external modular control pathways to explicitly impose style guidance signals. However, these methods often fail to capture complex style reference or retain the identity of user-provided content images, thus falling into the trap of style-content balance. Thus, we propose a training-free style transfer approach via $\textbf{h}$eterogeneous $\textbf{a}$ttention $\textbf{m}$odulation ($\textbf{HAM}$) to protect identity information during image/text-guided style reference transfer, thereby addressing the style-content trade-off challenge. Specifically, we first introduces style noise initialization to initialize latent noise for diffusion. Then, during the diffusion process, it innovatively employs HAM for different attention mechanisms, including Global Attention Regulation (GAR) and Local Attention Transplantation (LAT), which better preserving the details of the content image while capturing complex style references. Our approach is validated through a series of qualitative and quantitative experiments, achieving state-of-the-art performance on multiple quantitative metrics.

comment: Accepted in CVPR 2026 Findings

☆ SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons

Haiyang Xu, Ronghuan Wu, Li-Yi Wei, Nanxuan Zhao, Chenxi Liu, Cuong Nguyen, Zhuowen Tu, Zhaowen Wang

Graphic icons are a cornerstone of modern design workflows, yet they are often distributed as flattened single-path or compound-path graphics, where the original semantic layering is lost. This absence of semantic decomposition hinders downstream tasks such as editing, restyling, and animation. We formalize this problem as semantic layer construction for flattened vector art and introduce SemLayer, a visual generation empowered pipeline that restores editable layered structures. Given an abstract icon, SemLayer first generates a chromatically differentiated representation in which distinct semantic components become visually separable. To recover the complete geometry of each part, including occluded regions, we then perform a semantic completion step that reconstructs coherent object-level shapes. Finally, the recovered parts are assembled into a layered vector representation with inferred occlusion relationships. Extensive qualitative comparisons and quantitative evaluations demonstrate the effectiveness of SemLayer, enabling editing workflows previously inapplicable to flattened vector graphics and establishing semantic layer reconstruction as a practical and valuable task. Project page: https://xxuhaiyang.github.io/SemLayer/

comment: Accepted to CVPR 2026

☆ A^3: Towards Advertising Aesthetic Assessment

Kaiyuan Ji, Yixuan Gao, Lu Sun, Yushuo Zheng, Zijian Chen, Jianbo Zhang, Xiangyang Zhu, Yuan Tian, Zicheng Zhang, Guangtao Zhai

comment: Accepted to CVPR 2026

☆ SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision

Avigail Cohen Rimon, Amir Mann, Mirela Ben Chen, Or Litany

3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based video tracking. However, leveraging the differentiability of the 3DGS renderer "in the wild" remains notoriously fragile. A fundamental bottleneck lies in the compact, local support of the Gaussian primitives. Standard photometric objectives implicitly rely on spatial overlap; if severe camera misalignment places the rendered object outside the target's local footprint, gradients strictly vanish, leaving the optimizer stranded. We introduce SpectralSplats, a robust tracking framework that resolves this "vanishing gradient" problem by shifting the optimization objective from the spatial to the frequency domain. By supervising the rendered image via a set of global complex sinusoidal features (Spectral Moments), we construct a global basin of attraction, ensuring that a valid, directional gradient toward the target exists across the entire image domain, even when pixel overlap is completely nonexistent. To harness this global basin without introducing periodic local minima associated with high frequencies, we derive a principled Frequency Annealing schedule from first principles, gracefully transitioning the optimizer from global convexity to precise spatial alignment. We demonstrate that SpectralSplats acts as a seamless, drop-in replacement for spatial losses across diverse deformation parameterizations (from MLPs to sparse control points), successfully recovering complex deformations even from severely misaligned initializations where standard appearance-based tracking catastrophically fails.

comment: Project page: https://avigailco.github.io/SpectralSplats/

☆ Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection

Sa Zhu, Wanqian Zhang, Lin Wang, Xiaohua Chen, Chenxu Cui, Jinchao Zhang, Bo Li

Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features, which is insufficient to transfer temporal consistent visual knowledge from seen to unseen classes. To address this, we propose a Phase-wise Decomposition and Alignment (PDA) framework, which enables fine-grained action pattern learning for effective prior knowledge transfer. Specifically, we first introduce the CoT-Prompting Semantic Decomposition (CSD) module, which leverages the chain-of-thought (CoT) reasoning ability of large language models to automatically decompose action labels into coherent phase-level descriptions, emulating human cognitive processes. Then, Text-infused Foreground Filtering (TIF) module is introduced to adaptively filter action-relevant segments for each phase leveraging phase-wise semantic cues, producing semantically aligned visual representations. Furthermore, we propose the Adaptive Phase-wise Alignment (APA) module to perform phase-level visual-textual matching, and adaptively aggregates alignment results across phases for final prediction. This adaptive phase-wise alignment facilitates the capture of transferable action patterns and significantly enhances generalization to unseen actions. Extensive experiments on two OV-TAD benchmarks demonstrated the superiority of the proposed method.

comment: Accepted by CVPR 2026

☆ COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm

Zekun Qian, Wei Feng, Ruize Han, Junhui Hou

Multi-Object Tracking (MOT) has traditionally focused on a few specific categories, restricting its applicability to real-world scenarios involving diverse objects. Open-Vocabulary Multi-Object Tracking (OVMOT) addresses this by enabling tracking of arbitrary categories, including novel objects unseen during training. However, current progress is constrained by two challenges: the lack of continuously annotated video data for training, and the lack of a customized OVMOT framework to synergistically handle detection and association. We address the data bottleneck by constructing C-TAO, the first continuously annotated training set for OVMOT, which increases annotation density by 26x over the original TAO and captures smooth motion dynamics and intermediate object states. For the framework bottleneck, we propose COVTrack++, a synergistic framework that achieves a bidirectional reciprocal mechanism between detection and association through three modules: (1) Multi-Cue Adaptive Fusion (MCF) dynamically balances appearance, motion, and semantic cues for association feature learning; (2) Multi-Granularity Hierarchical Aggregation (MGA) exploits hierarchical spatial relationships in dense detections, where visible child nodes (e.g., object parts) assist occluded parent objects (e.g., whole body) for association feature enhancement; (3) Temporal Confidence Propagation (TCP) recovers flickering detections through high-confidence tracked objects boosting low-confidence candidates across frames, stabilizing trajectories. Extensive experiments on TAO demonstrate state-of-the-art performance, with novel TETA reaching 35.4% and 30.5% on validation and test sets, improving novel AssocA by 4.8% and novel LocA by 5.8% over previous methods, and show strong zero-shot generalization on BDD100K. The code and dataset will be publicly available.

☆ UW-VOS: A Large-Scale Dataset for Underwater Video Object Segmentation

Hongshen Zhao, Jingkang Tai, Yuhang Wu, Wenkang Zhang, Xi Lan, Shangyan Wang, Tianyu Zhang, Wankou Yang

Underwater Video Object Segmentation (VOS) is essential for marine exploration, yet open-air methods suffer significant degradation due to color distortion, low contrast, and prevalent camouflage. A primary hurdle is the lack of high-quality training data. To bridge this gap, we introduce $\textbf{UW-VOS}$, the first large-scale underwater VOS benchmark comprising 1,431 video sequences across 409 categories with 309,295 mask annotations, constructed via a semi-automatic data engine with rigorous human verification. We further propose $\textbf{SAM-U}$, a parameter-efficient framework that adapts SAM2 to the underwater domain. By inserting lightweight adapters into the image encoder, SAM-U achieves state-of-the-art performance with only $\sim$2$\%$ trainable parameters. Extensive experiments reveal that existing methods experience an average 13-point $\mathcal{J}\&\mathcal{F}$ drop on UW-VOS, while SAM-U effectively bridges this domain gap. Detailed attribute-based analysis further identifies small targets, camouflage, and exit-re-entry as critical bottlenecks, providing a roadmap for future research in robust underwater perception.

☆ DB SwinT: A Dual-Branch Swin Transformer Network for Road Extraction in Optical Remote Sensing Imagery

Zongyang He, Xiangli Yang, Xian Gao, Zhiguo Wang

With the continuous improvement in the spatial resolution of optical remote sensing imagery, accurate road extraction has become increasingly important for applications such as urban planning, traffic monitoring, and disaster management. However, road extraction in complex urban and rural environments remains challenging, as roads are often occluded by trees, buildings, and other objects, leading to fragmented structures and reduced extraction accuracy. To address this problem, this paper proposes a Dual-Branch Swin Transformer network (DB SwinT) for road extraction. The proposed framework combines the long-range dependency modeling capability of the Swin Transformer with the multi-scale feature fusion strategy of U-Net, and employs a dual-branch encoder to learn complementary local and global representations. Specifically, the local branch focuses on recovering fine structural details in occluded areas, while the global branch captures broader semantic context to preserve the overall continuity of road networks. In addition, an Attentional Feature Fusion (AFF) module is introduced to adaptively fuse features from the two branches, further enhancing the representation of occluded road segments. Experimental results on the Massachusetts and DeepGlobe datasets show that DB SwinT achieves Intersection over Union (IoU) scores of 79.35\% and 74.84\%, respectively, demonstrating its effectiveness for road extraction from optical remote sensing imagery.

☆ HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images

Yumeng Liu, Xiao-Xiao Long, Marc Habermann, Xuanze Yang, Cheng Lin, Yuan Liu, Yuexin Ma, Wenping Wang, Ligang Liu

comment: project page: https://lym29.github.io/HGGT/

☆ CAKE: Real-time Action Detection via Motion Distillation and Background-aware Contrastive Learning

Hieu Hoang, Dung Trung Tran, Hong Nguyen, Nam-Phong Nguyen

Online Action Detection (OAD) systems face two primary challenges: high computational cost and insufficient modeling of discriminative temporal dynamics against background motion. Adding optical flow could provides strong motion cues but it incurs significant computational overhead. We propose CAKE, a OAD Flow-based distillation framework to transfer motion knowledge into RGB models. We propose Dynamic Motion Adapter (DMA) to suppress static background noise and emphasize pixel changes, effectively approximating optical flow without explicit computation. The framework also integrates a Floating Contrastive Learning strategy to distinguish informative motion dynamics from temporal background. Various experiments conducted on the TVSeries, THUMOS'14, Kinetics-400 datasets show effectiveness of our model. CAKE achieves a standout mAP compared with SOTA while using the same backbone. Our model operates at over 72 FPS on a single CPU, making it highly suitable for resource-constrained systems.

☆ SilLang: Improving Gait Recognition with Silhouette Language Encoding

Ruiyi Zhan, Guozhen Peng, Canyu Chen, Jian Lei, Annan Li

Gait silhouettes, which can be encoded into binary gait codes, are widely adopted to representing motion patterns of pedestrian. Recent approaches commonly leverage visual backbones to encode gait silhouettes, achieving successful performance. However, they primarily focus on continuous visual features, overlooking the discrete nature of binary silhouettes that inherently share a discrete encoding space with natural language. Large Language Models (LLMs) have demonstrated exceptional capability in extracting discriminative features from discrete sequences and modeling long-range dependencies, highlighting their potential to capture temporal motion patterns by identifying subtle variations. Motivated by these observations, we explore bridging binary gait silhouettes and natural language within a binary encoding space. However, the encoding spaces of text tokens and binary gait silhouettes remain misaligned, primarily due to differences in token frequency and density. To address this issue, we propose the Contour-Velocity Tokenizer, which encodes binary gait silhouettes while reshaping their distribution to better align with the text token space. We then establish a dual-branch framework termed Silhouette Language Model, which enhances visual silhouettes by integrating discrete linguistic embeddings derived from LLMs. Implemented on mainstream gait backbones, SilLang consistently improves state-of-the-art methods across SUSTech1K, GREW, and Gait3D.

☆ HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception

Minwoo Song, Minhee Kang, Heejin Ahn

In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Domain-Aware Robust Architecture), a unified pipeline that integrates intermediate and late fusion within a domain-aware framework. We introduce a lightweight domain classifier that dynamically identifies heterogeneous agents and assigns them to the late-fusion branch. Furthermore, we propose anchor-guided pose graph optimization to mitigate localization errors inherent in late fusion, leveraging reliable detections from intermediate fusion as fixed spatial anchors. Extensive experiments demonstrate that, despite requiring no additional training, HyDRA achieves performance comparable to state-of-the-art heterogeneity-aware CP methods. Importantly, this performance is maintained as the number of collaborating agents increases, enabling zero-cost scaling without retraining.

comment: 8 pages, 6 figures, Submitted to IROS 2026

☆ Machine vision with small numbers of detected photons per inference

Shi-Yuan Ma, Jérémie Laydevant, Mandar M. Sohoni, Logan G. Wright, Tianyu Wang, Peter L. McMahon

Machine vision, including object recognition and image reconstruction, is a central technology in many consumer devices and scientific instruments. The design of machine-vision systems has been revolutionized by the adoption of end-to-end optimization, in which the optical front end and the post-processing back end are jointly optimized. However, while machine vision currently works extremely well in moderate-light or bright-light situations -- where a camera may detect thousands of photons per pixel and billions of photons per frame -- it is far more challenging in very low-light situations. We introduce photon-aware neuromorphic sensing (PANS), an approach for end-to-end optimization in highly photon-starved scenarios. The training incorporates knowledge of the low photon budget and the stochastic nature of light detection when the average number of photons per pixel is near or less than 1. We report a proof-of-principle experimental demonstration in which we performed low-light image classification using PANS, achieving 73% (82%) accuracy on FashionMNIST with an average of only 4.9 (17) detected photons in total per inference, and 86% (97%) on MNIST with 8.6 (29) detected photons -- orders of magnitude more photon-efficient than conventional approaches. We also report simulation studies showing how PANS could be applied to other classification, event-detection, and image-reconstruction tasks. By taking into account the statistics of measurement results for non-classical states or alternative sensing hardware, PANS could in principle be adapted to enable high-accuracy results in quantum and other photon-starved setups.

comment: 98 pages, 34 figures

☆ SLAT-Phys: Fast Material Property Field Prediction from Structured 3D Latents

Rocktim Jyoti Das, Dinesh Manocha

Estimating the material property field of 3D assets is critical for physics-based simulation, robotics, and digital twin generation. Existing vision-based approaches are either too expensive and slow or rely on 3D information. We present SLAT-Phys, an end-to-end method that predicts spatially varying material property fields of 3D assets directly from a single RGB image without explicit 3D reconstruction. Our approach leverages spatially organised latent features from a pretrained 3D asset generation model that encodes rich geometry and semantic prior, and trains a lightweight neural decoder to estimate Young's modulus, density, and Poisson's ratio. The coarse volumetric layout and semantic cues of the latent representation about object geometry and appearance enable accurate material estimation. Our experiments demonstrate that our method provides competitive accuracy in predicting continuous material parameters when compared against prior approaches, while significantly reducing computation time. In particular, SLAT-Phys requires only 9.9 seconds per object on an NVIDIA RTXA5000 GPU and avoids reconstruction and voxelization preprocessing. This results in 120x speedup compared to prior methods and enables faster material property estimation from a single image.

comment: 8 page, 4 figures

☆ GRMLR: Knowledge-Enhanced Small-Data Learning for Deep-Sea Cold Seep Stage Inference

Chenxu Zhou, Zelin Liu, Rui Cai, Houlin Gong, Yikang Yu, Jia Zeng, Yanru Pei, Liang Zhang, Weishu Zhao, Xiaofeng Gao

Deep-sea cold seep stage assessment has traditionally relied on costly, high-risk manned submersible operations and visual surveys of macrofauna. Although microbial communities provide a promising and more cost-effective alternative, reliable inference remains challenging because the available deep-sea dataset is extremely small ($n = 13$) relative to the microbial feature dimension ($p = 26$), making purely data-driven models highly prone to overfitting. To address this, we propose a knowledge-enhanced classification framework that incorporates an ecological knowledge graph as a structural prior. By fusing macro-microbe coupling and microbial co-occurrence patterns, the framework internalizes established ecological logic into a \underline{\textbf{G}}raph-\underline{\textbf{R}}egularized \underline{\textbf{M}}ultinomial \underline{\textbf{L}}ogistic \underline{\textbf{R}}egression (GRMLR) model, effectively constraining the feature space through a manifold penalty to ensure biologically consistent classification. Importantly, the framework removes the need for macrofauna observations at inference time: macro-microbe associations are used only to guide training, whereas prediction relies solely on microbial abundance profiles. Experimental results demonstrate that our approach significantly outperforms standard baselines, highlighting its potential as a robust and scalable framework for deep-sea ecological assessment.

☆ Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection

Jielun Peng, Yabin Wang, Yaqi Li, Long Kong, Xiaopeng Hong

The rapid progress of generative AI has enabled hyper-realistic audio-visual deepfakes, intensifying threats to personal security and social trust. Most existing deepfake detectors rely either on uni-modal artifacts or audio-visual discrepancies, failing to jointly leverage both sources of information. Moreover, detectors that rely on generator-specific artifacts tend to exhibit degraded generalization when confronted with unseen forgeries. We argue that robust and generalizable detection should be grounded in intrinsic audio-visual coherence within and across modalities. Accordingly, we propose HAVIC, a Holistic Audio-Visual Intrinsic Coherence-based deepfake detector. HAVIC first learns priors of modality-specific structural coherence, inter-modal micro- and macro-coherence by pre-training on authentic videos. Based on the learned priors, HAVIC further performs holistic adaptive aggregation to dynamically fuse audio-visual features for deepfake detection. Additionally, we introduce HiFi-AVDF, a high-fidelity audio-visual deepfake dataset featuring both text-to-video and image-to-video forgeries from state-of-the-art commercial generators. Extensive experiments across several benchmarks demonstrate that HAVIC significantly outperforms existing state-of-the-art methods, achieving improvements of 9.39% AP and 9.37% AUC on the most challenging cross-dataset scenario. Our code and dataset are available at https://github.com/tuffy-studio/HAVIC.

☆ PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning

Yankai Wang, Yiding Sun, Qirui Wang, Pengbo Li, Chaoyi Lu, Dongxu Zhang

Understanding spatial dynamics and semantics in point cloud is fundamental for comprehensive 3D comprehension. While reinforcement learning algorithms such as Group Relative Policy Optimization (GRPO) have recently achieved remarkable breakthroughs in large language models by incentivizing reasoning capabilities through strategic reward design, their potential remains largely unexplored in the 3D perception domain. This naturally raises a pivotal question: Can RL-based methods effectively empower 3D point cloud fine-tuning? In this paper, we propose PointRFT, the first reinforcement fine-tuning paradigm tailored specifically for point cloud representation learning. We select three prevalent 3D foundation models and devise specialized accuracy reward and dispersion reward functions to stabilize training and mitigate distribution shifts. Through comprehensive few-shot classification experiments comparing distinct training paradigms, we demonstrate that PointRFT consistently outperforms vanilla supervised fine-tuning (SFT) across diverse benchmarks. Furthermore, when organically integrated into a hybrid Pretraining-SFT-RFT paradigm, the representational capacity of point cloud foundation models is substantially unleashed, achieving state-of-the-art performance particularly under data-scarce scenarios.

☆ SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization

Qi Zhang, Daijie Chen, Yunfei Gong, Hui Huang

Existing multi-view crowd counting and localization methods are evaluated under relatively small scenes with limited crowd numbers, camera views, and frames. This makes the evaluation and comparison of existing methods impractical, as small datasets are easily overfit by these methods. To avoid these issues, 3DROM proposes a data augmentation method. Instead, in this paper, we propose a large synthetic benchmark, SynMVCrowd, for more practical evaluation and comparison of multi-view crowd counting and localization tasks. The SynMVCrowd benchmark consists of 50 synthetic scenes with a large number of multi-view frames and camera views and a much larger crowd number (up to 1000), which is more suitable for large-scene multi-view crowd vision tasks. Besides, we propose strong multi-view crowd localization and counting baselines that outperform all comparison methods on the new SynMVCrowd benchmark. Moreover, we prove that better domain transferring multi-view and single-image counting performance could be achieved with the aid of the benchmark on novel new real scenes. As a result, the proposed benchmark could advance the research for multi-view and single-image crowd counting and localization to more practical applications. The codes and datasets are here: https://github.com/zqyq/SynMVCrowd.

comment: IJCV 2026

☆ VOLMO: Versatile and Open Large Models for Ophthalmology

Zhenyue Qin, Younjoon Chung, Elijah Lee, Wanyue Feng, Xuguang Ai, Serina Applebaum, Minjie Zou, Yang Liu, Pan Xiao, Mac Singer, Amisha Dave, Aidan Gilson, Tiarnan D. L. Keenan, Emily Y. Chew, Zhiyong Lu, Yih-Chung Tham, Ron Adelman, Luciano V. Del Priore, Qingyu Chen

Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require clinicians to integrate medical images, structured clinical data, and free-text notes to determine disease severity and management, which is time-consuming and burdensome. Recent multimodal large language models (MLLMs) show promise, but existing general and medical MLLMs perform poorly in ophthalmology, and few ophthalmology-specific MLLMs are openly available. We present VOLMO (Versatile and Open Large Models for Ophthalmology), a model-agnostic, data-open framework for developing ophthalmology-specific MLLMs. VOLMO includes three stages: ophthalmology knowledge pretraining on 86,965 image-text pairs from 26,569 articles across 82 journals; domain task fine-tuning on 26,929 annotated instances spanning 12 eye conditions for disease screening and severity classification; and multi-step clinical reasoning on 913 patient case reports for assessment, planning, and follow-up care. Using this framework, we trained a compact 2B-parameter MLLM and compared it with strong baselines, including InternVL-2B, LLaVA-Med-7B, MedGemma-4B, MedGemma-27B, and RETFound. We evaluated these models on image description generation, disease screening and staging classification, and assessment-and-management generation, with additional manual review by two healthcare professionals and external validation on three independent cohorts for age-related macular degeneration and diabetic retinopathy. Across settings, VOLMO-2B consistently outperformed baselines, achieving stronger image description performance, an average F1 of 87.4% across 12 eye conditions, and higher scores in external validation.

♻ ☆ Knot-10:A Tightness-Stratified Benchmark for Real-World Knot Classification with Topological Difficulty Analysis

Shiheng Nie, Yunguang Yue

Physical knot classification is a fine-grained visual classification (FGVC) scenario in which appearance cues are deliberately suppressed: different classes share the same rope material, color, and background, and class identity resides primarily in crossing structure. We introduce the Knots-10 benchmark, comprising 1,440 images with a deployment-oriented split that trains on loosely tied knots and tests on tightly dressed ones. Swin-T and TransFG both average 97.2% accuracy; PMG scores 94.5%, consistent with the hypothesis that jigsaw shuffling disrupts crossing continuity. McNemar tests cannot separate four of the five general-purpose backbones, so small ranking margins should be interpreted with caution. A Mantel permutation test shows that topological distance significantly correlates with confusion patterns in three of the five models (p < 0.01). We propose TACA regularization, which improves embedding-topology alignment from rho=0.46 to rho=0.65 without improving classification accuracy; a random-distance ablation yields comparable alignment, indicating the benefit is likely driven by generic regularization. A pilot cross-domain test with 100 phone photographs reveals a 58-69 percentage-point accuracy drop, exposing rope appearance bias as the dominant failure mode.

comment: 48 pages, 12 figures, 10 supplementary sections

♻ ☆ Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation

Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim

3D Gaussian Splatting has recently enabled fast and photorealistic reconstruction of static 3D scenes. However, dynamic editing of such scenes remains a significant challenge. We introduce a novel framework, Physics-Guided Score Distillation, to address a fundamental conflict: physics simulation provides a strong motion prior that is insufficient for photorealism , while video-based Score Distillation Sampling (SDS) alone cannot generate coherent motion for complex, multi-particle scenarios. We resolve this through a unified optimization framework where physics simulation guides Score Distillation to jointly refine the motion prior for photorealism while simultaneously optimizing appearance. Specifically, we learn a neural dynamics model that predicts particle motion and appearance, optimized end-to-end via a combined loss integrating Video-SDS for photorealism with our physics-guidance prior. This allows for photorealistic refinements while ensuring the dynamics remain plausible. Our framework enables scene-wide dynamic weather effects, including snowfall, rainfall, fog, and sandstorms, with physically plausible motion. Experiments demonstrate our physics-guided approach significantly outperforms baselines, with ablations confirming this joint refinement is essential for generating coherent, high-fidelity dynamics.

comment: Accepted to CVPR 2026. Project webpage: https://galfiebelman.github.io/let-it-snow/

♻ ☆ Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation

Yara Bahram, Mélodie Desbos, Mohammadhadi Shateri, Eric Granger

Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation for novel domains relies on two-stage pipelines: Adapt-then-Distill or Distill-then-Adapt. However, both add design complexity and often degrade quality or diversity. We introduce Uni-DAD, a single-stage pipeline that unifies DM distillation and adaptation. It couples two training signals: (i) a dual-domain distribution-matching distillation (DMD) objective that guides the student toward the distributions of the source teacher and a target teacher, and (ii) a multi-head generative adversarial network (GAN) loss that encourages target realism across multiple feature scales. The source domain distillation preserves diverse source knowledge, while the multi-head GAN stabilizes training and reduces overfitting, especially in few-shot regimes. The inclusion of a target teacher facilitates adaptation to more structurally distant domains. We evaluate Uni-DAD on two comprehensive benchmarks for few-shot image generation (FSIG) and subject-driven personalization (SDP) using diffusion backbones. It delivers better or comparable quality to state-of-the-art (SoTA) adaptation methods even with less than 4 sampling steps, and often surpasses two-stage pipelines in quality and diversity. Code: https://github.com/yaramohamadi/uni-DAD.

comment: Accepted at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

♻ ☆ Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration

Mengyu Yang, Yanming Yang, Chenyi Xu, Chenxi Song, Yufan Zuo, Tong Zhao, Ruibo Li, Chi Zhang

Diffusion models have achieved impressive generative quality across modalities like 2D images, videos, and 3D shapes, but their inference remains computationally expensive due to the iterative denoising process. While recent caching-based methods effectively reuse redundant computations to speed up 2D and video generation, directly applying these techniques to 3D diffusion models can severely disrupt geometric consistency. In 3D synthesis, even minor numerical errors in cached latent features accumulate, causing structural artifacts and topological inconsistencies. To overcome this limitation, we propose Fast3Dcache, a training-free geometry-aware caching framework that accelerates 3D diffusion inference while preserving geometric fidelity. Our method introduces a Predictive Caching Scheduler Constraint (PCSC) to dynamically determine cache quotas according to voxel stabilization patterns and a Spatiotemporal Stability Criterion (SSC) to select stable features for reuse based on velocity magnitude and acceleration criterion. Comprehensive experiments show that Fast3Dcache accelerates inference significantly, achieving up to a 27.12% speed-up and a 54.83% reduction in FLOPs, with minimal degradation in geometric quality as measured by Chamfer Distance (2.48%) and F-Score (1.95%).

comment: Accepted by CVPR 2026; Project page: https://fast3dcache-agi.github.io

♻ ☆ FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation

Eric Tillmann Bill, Enis Simsar, Thomas Hofmann

Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. We present a principled theoretical framework that steers sampling toward multi-subject fidelity by casting flow matching (FM) as stochastic optimal control (SOC), yielding a single hyperparameter controlled trade-off between fidelity and object-centric state separation / binding consistency. Within this framework, we derive two architecture-agnostic algorithms: (i) a training-free test-time controller that perturbs the base velocity with a single-pass update, and (ii) Adjoint Matching, a lightweight fine-tuning rule that regresses a control network to a backward adjoint signal. The same formulation unifies prior attention heuristics, extends to diffusion models via a flow--diffusion correspondence, and provides the first fine-tuning route explicitly designed for multi-subject fidelity. In addition, we also introduce FOCUS (Flow Optimal Control for Unentangled Subjects), a probabilistic attention-binding objective compatible with both algorithms. Empirically, on Stable Diffusion 3.5 and FLUX.1, both algorithms consistently improve multi-subject alignment while maintaining base-model style; test-time control runs efficiently on commodity GPUs, and fine-tuned models generalize to unseen prompts.

comment: Project Page: https://ericbill21.github.io/FOCUS/

♻ ☆ VocSegMRI: Multimodal Learning for Precise Vocal Tract Segmentation in Real-time MRI

Daiqi Liu, Johannes Enk, Maureen Stone, Fangxu Xing, Tomás Arias-Vergara, Jerry L. Prince, Jana Hutter, Jonghye Woo, Andreas Maier, Paula Andrea Pérez-Toro

Accurate segmentation of articulatory structures in real-time MRI (rtMRI) remains challenging, as existing methods rely primarily on visual cues and overlook complementary information from synchronized speech signals. We propose VocSegMRI, a multimodal framework integrating video, audio, and phonological inputs via cross-attention fusion and a contrastive learning objective that improves cross-modal alignment and segmentation precision. Evaluated on USC-75 and further validated via zero-shot transfer on USC-TIMIT, VocSegMRI outperforms unimodal and multimodal baselines, with ablations confirming the contribution of each component.

comment: Preprint submitted to MIDL short paper 2026

♻ ☆ Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning

Xingyu Zhu, Liang Yi, Shuo Wang, Wenbo Zhu, Yonglinag Wu, Beier Zhu, Hanwang Zhang

Multimodal 3D vision-language models show strong generalization across diverse 3D tasks, but their performance still degrades notably under domain shifts. This has motivated recent studies on test-time adaptation (TTA), which enables models to adapt online using test-time data. Among existing TTA methods, cache-based mechanisms are widely adopted for leveraging previously observed samples in online prediction refinement. However, they store only limited historical information, leading to progressive information loss as the test stream evolves. In addition, their prediction logits are fused heuristically, making adaptation unstable. To address these limitations, we propose BayesMM, a Multimodal Bayesian Distribution Learning framework for test-time point cloud analysis. BayesMM models textual priors and streaming visual features of each class as Gaussian distributions: textual parameters are derived from semantic prompts, while visual parameters are updated online with arriving samples. The two modalities are fused via Bayesian model averaging, which automatically adjusts their contributions based on posterior evidence, yielding a unified prediction that adapts continually to evolving test-time data without training. Extensive experiments on multiple point cloud benchmarks demonstrate that BayesMM maintains robustness under distributional shifts, yielding over 4% average improvement.

comment: CVPR 2026

♻ ☆ Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models

Xingyu Zhu, Beier Zhu, Shuo Wang, Junfeng Fang, Kesen Zhao, Hanwang Zhang, Xiangnan He

As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to generate harmful content, posing serious risks to model safety and trustworthy usage. Recent activation steering methods inject directional vectors into model activations during inference to induce refusal behaviors and have demonstrated effectiveness. However, a steering vector may both enhance refusal ability and cause over-refusal, thereby degrading model performance on benign inputs. Moreover, due to the lack of theoretical interpretability, these methods still suffer from limited robustness and effectiveness. To better balance safety and utility, we propose NullSteer, a null-space projected activation defense framework. Our method constructs refusal directions within model activations through a linear transformation: it maintains zero perturbation within the benign subspace while dynamically inducing refusal along potentially harmful directions, thereby theoretically achieving safety enhancement without impairing the model's general capabilities. Extensive experiments show that NullSteer significantly reduces harmful outputs under various jailbreak attacks (average ASR reduction over 15 percent on MiniGPT-4) while maintaining comparable performance to the original model on general benchmarks.

comment: CVPR 2026

♻ ☆ KINESIS: Motion Imitation for Human Musculoskeletal Locomotion

Merkourios Simos, Alberto Silvio Chiappa, Alexander Mathis

How do humans move? Advances in reinforcement learning (RL) have produced impressive results in capturing human motion using physics-based humanoid control. However, torque-controlled humanoids fail to model key aspects of human motor control such as biomechanical joint constraints & non-linear and overactuated musculotendon control. We present KINESIS, a model-free motion imitation framework that tackles these challenges. KINESIS is trained on 1.8 hours of locomotion data and achieves strong motion imitation performance on unseen trajectories. Through a negative mining approach, KINESIS learns robust locomotion priors that we leverage to deploy the policy on several downstream tasks such as text-to-control, target point reaching, and football penalty kicks. Importantly, KINESIS learns to generate muscle activity patterns that correlate well with human EMG activity. We show that these results scale seamlessly across biomechanical model complexity, demonstrating control of up to 290 muscles. Overall, the physiological plausibility makes KINESIS a promising model for tackling challenging problems in human motor control. Code, videos and benchmarks are available at https://github.com/amathislab/Kinesis.

comment: Accepted to ICRA. Here we include an appendix

♻ ☆ Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding

Yuchen Feng, Zhenyu Zhang, Naibin Gu, Yilong Chen, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang

Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, perceive complex scenes efficiently by dynamically scanning and focusing on salient regions in a sequential "blink-like" process. Motivated by this strategy, we first investigate whether MLLMs exhibit similar behavior. Our pilot analysis reveals that MLLMs naturally attend to different visual regions across layers and that selectively allocating more computation to salient tokens can enhance visual perception. Building on this insight, we propose Blink, a dynamic visual token resolution framework that emulates the human-inspired process within a single forward pass. Specifically, Blink includes two modules: saliency-guided scanning and dynamic token resolution. It first estimates the saliency of visual tokens in each layer based on the attention map, and extends important tokens through a plug-and-play token super-resolution (TokenSR) module. In the next layer, it drops the extended tokens when they lose focus. This dynamic mechanism balances broad exploration and fine-grained focus, thereby enhancing visual perception adaptively and efficiently. Extensive experiments validate Blink, demonstrating its effectiveness in enhancing visual perception and multimodal understanding.

comment: CVPR 2026

♻ ☆ VCBench: A Streaming Counting Benchmark for Spatial-Temporal State Maintenance in Long Videos

Pengyiang Liu, Zhongyue Shi, Hongye Hao, Qi Fu, Xueting Bi, Siwei Zhang, Xiaoyang Hu, Zitian Wang, Linjiang Huang, Si Liu

Video understanding requires models to continuously track and update world state during playback. While existing benchmarks have advanced video understanding evaluation across multiple dimensions, the observation of how models maintain world state remains insufficient. We propose VCBench, a streaming counting benchmark that repositions counting as a minimal probe for diagnosing world state maintenance capability. We decompose this capability into object counting and event counting, forming 8 fine-grained subcategories. Object counting covers tracking currently visible objects and cumulative unique identities, while event counting covers detecting instantaneous actions and tracking complete activity cycles. VCBench contains 406 videos with frame-by-frame annotations of 10,071 event occurrence moments and object state change moments, generating 1,000 streaming QA pairs with 4,576 query points along timelines. By observing state maintenance trajectories through streaming multi-point queries, we design three complementary metrics to diagnose numerical precision, trajectory consistency, and temporal awareness. Evaluation on mainstream video-language models shows that current models still exhibit significant deficiencies in spatial-temporal state maintenance, particularly struggling with tasks like periodic event counting. VCBench provides a diagnostic framework for measuring and improving state maintenance in video understanding systems. Our code and data are available at https://github.com/buaaplay/VCBench.

♻ ☆ Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework

Kaihua Tang, Jiaxin Qi, Jinli Ou, Yuhua Zheng, Jianqiang Huang

The emergence of Large Language Models (LLMs) has driven rapid progress in multi-modal learning, particularly in the development of Large Vision-Language Models (LVLMs). However, existing LVLM training paradigms place excessive reliance on the LLM component, giving rise to two critical robustness challenges: language bias and language sensitivity. To address both issues simultaneously, we propose a novel Self-Critical Inference (SCI) framework that extends Visual Contrastive Decoding by conducting multi-round counterfactual reasoning through both textual and visual perturbations. This process further introduces a new strategy for improving robustness by scaling the number of counterfactual rounds. Moreover, we also observe that failure cases of LVLMs differ significantly across models, indicating that fixed robustness benchmarks may not be able to capture the true reliability of LVLMs. To this end, we propose the Dynamic Robustness Benchmark (DRBench), a model-specific evaluation framework targeting both language bias and sensitivity issues. Extensive experiments show that SCI consistently outperforms baseline methods on DRBench, and that increasing the number of inference rounds further boosts robustness beyond existing single-step counterfactual reasoning methods.

comment: Accepted to CVPR 2026. Code: https://github.com/KaihuaTang/Self-Critical-Inference-Framework

♻ ☆ SERA-H: Beyond Native Sentinel Spatial Limits for High-Resolution Canopy Height Mapping

Thomas Boudras, Martin Schwartz, Rasmus Fensholt, Martin Brandt, Ibrahim Fayad, Jean-Pierre Wigneron, Gabriel Belouze, Fajwel Fogel, Philippe Ciais

High-resolution mapping of canopy height is essential for forest management and biodiversity monitoring. Although recent studies have led to the advent of deep learning methods using satellite imagery to predict height maps, these approaches often face a trade-off between data accessibility and spatial resolution. To overcome these limitations, we present SERA-H, an end-to-end model combining a super-resolution module (EDSR) and temporal attention encoding (UTAE). Trained under the supervision of high-density LiDAR-derived Canopy Height Models (CHM), our model generates 2.5 m resolution height maps from freely available Sentinel-1 and Sentinel-2 (10 m) time series data. Evaluated on an open-source benchmark dataset in France, SERA-H, with a MAE of 2.6 m and R2 of 0.82, not only outperforms standard Sentinel- 1/2 baselines but also achieves performance comparable to or better than methods relying on commercial very high-resolution imagery (SPOT-6/7, PlanetScope, Maxar). These results demonstrate that combining high-resolution supervision with the spatiotemporal information embedded in time series enables the reconstruction of details beyond the input sensors' native resolution. SERA-H opens the possibility of freely mapping forests with high revisit frequency, achieving accuracy comparable to that of costly commercial imagery.

comment: 17 pages, 8 figures, 3 tables

♻ ☆ A Generalizable Deep Learning System for Cardiac MRI

Rohan Shad, Cyril Zakka, Dhamanpreet Kaur, Mrudang Mathur, Robyn Fong, Joseph Cho, Ross Warren Filice, John Mongan, Kimberly Kalianos, Nishith Khandwala, David Eng, Matthew Leipzig, Walter R. Witschey, Alejandro de Feria, Victor A. Ferrari, Euan A. Ashley, Michael A. Acker, Curtis Langlotz, William Hiesinger

Cardiac MRI allows for a comprehensive assessment of myocardial structure, function and tissue characteristics. Here we describe a foundational vision system for cardiac MRI, capable of representing the breadth of human cardiovascular disease and health. Our deep-learning model is trained via self-supervised contrastive learning, in which visual concepts in cine-sequence cardiac MRI scans are learned from the raw text of the accompanying radiology reports. We train and evaluate our model on data from four large academic clinical institutions in the United States. We additionally showcase the performance of our models on the UK BioBank and two additional publicly available external datasets. We explore emergent capabilities of our system and demonstrate remarkable performance across a range of tasks, including the problem of left-ventricular ejection fraction regression and the diagnosis of 39 different conditions such as cardiac amyloidosis and hypertrophic cardiomyopathy. We show that our deep-learning system is capable of not only contextualizing the staggering complexity of human cardiovascular disease but can be directed towards clinical problems of interest, yielding impressive, clinical-grade diagnostic accuracy with a fraction of the training data typically required for such tasks.

comment: Published in Nature Biomedical Engineering; Supplementary Appendix available on publisher website. Code: https://github.com/rohanshad/cmr_transformer

♻ ☆ PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation

Mingju Gao, Kaisen Yang, Huan-ang Gao, Bohan Li, Ao Ding, Wenyi Li, Yangcheng Yu, Jinkun Liu, Shaocong Xu, Yike Niu, Haohan Chi, Hao Chen, Hao Tang, Yu Zhang, Li Yi, Hao Zhao

Hand-object interaction (HOI) reconstruction and synthesis are becoming central to embodied AI and AR/VR. Yet, despite rapid progress, existing HOI generation research remains fragmented across three disjoint tracks: (1) pose-only synthesis that predicts MANO trajectories without producing pixels; (2) single-image HOI generation that hallucinates appearance from masks or 2D cues but lacks dynamics; and (3) video generation methods that require both the entire pose sequence and the ground-truth first frame as inputs, preventing true sim-to-real deployment. Inspired by the philosophy of Joo et al. (2018), we think that HOI generation requires a unified engine that brings together pose, appearance, and motion within one coherent framework. Thus we introduce PAM: a Pose-Appearance-Motion Engine for controllable HOI video generation. The performance of our engine is validated by: (1) On DexYCB, we obtain an FVD of 29.13 (vs. 38.83 for InterDyn), and MPJPE of 19.37 mm (vs. 30.05 mm for CosHand), while generating higher-resolution 480x720 videos compared to 256x256 and 256x384 baselines. (2) On OAKINK2, our full multi-condition model improves FVD from 68.76 to 46.31. (3) An ablation over input conditions on DexYCB shows that combining depth, segmentation, and keypoints consistently yields the best results. (4) For a downstream hand pose estimation task using SimpleHand, augmenting training with 3,400 synthetic videos (207k frames) allows a model trained on only 50% of the real data plus our synthetic data to match the 100% real baseline.

comment: Accepted to CVPR 2026 Code: https://github.com/GasaiYU/PAM

♻ ☆ OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents

Akashah Shabbir, Muhammad Umer Sheikh, Muhammad Akhtar Munir, Hiyam Debary, Mustansar Fiaz, Muhammad Zaigham Zaheer, Paolo Fraccaro, Fahad Shahbaz Khan, Muhammad Haris Khan, Xiao Xiang Zhu, Salman Khan

Recent progress in multimodal reasoning has enabled agents that interpret imagery, connect it with language, and execute structured analytical tasks. Extending these capabilities to remote sensing remains challenging, as models must reason over spatial scale, geographic structures, and multispectral indices while maintaining coherent multi-step logic. To address this gap, we introduce \textit{OpenEarthAgent}, a unified framework for tool-augmented geospatial reasoning trained on satellite imagery, natural-language queries, and structured reasoning traces. Beyond serving as a benchmark, OpenEarthAgent establishes a cohesive agentic architecture built around a unified executable tool registry and trajectory-based policy learning. The framework standardizes heterogeneous visual, spectral, GIS, and georeferenced raster operations under a consistent callable schema, enabling modular orchestration and deterministic execution. Training is performed via supervised fine-tuning on structured reasoning trajectories with deterministic replay validation to ensure executability and spatial correctness. The accompanying corpus comprises 14,538 training and 1,169 evaluation instances with over 107K reasoning steps, spanning urban, environmental, disaster, and infrastructure domains and incorporating GIS operations alongside index analyses such as NDVI, NBR, and NDBI. Grounded in explicit reasoning traces, the learned agent demonstrates structured reasoning, stable spatial understanding, and interpretable tool-driven behaviour across diverse EO scenarios. We report consistent improvements over a strong baseline and competitive performance against recent open and closed-source models. Our code and trained models will be publicly available.

♻ ☆ CADC: Content Adaptive Diffusion-Based Generative Image Compression

Xihua Sheng, Lingyu Zhu, Tianyu Zhang, Dong Liu, Shiqi Wang, Jing Wang

Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential lies in making the entire compression process content-adaptive, ensuring that the encoder's representation and the decoder's generative prior are dynamically aligned with the semantic and structural characteristics of the input image. However, existing methods suffer from three critical limitations that prevent effective content adaptation. First, isotropic quantization applies a uniform quantization step, failing to adapt to the spatially varying complexity of image content and creating a misalignment with the diffusion model's noise-dependent prior. Second, the information concentration bottleneck -- arising from the dimensional mismatch between the high-dimensional noisy latent and the diffusion decoder's fixed input -- prevents the model from adaptively preserving essential semantic information in the primary channels. Third, existing textual conditioning strategies either need significant textual bitrate overhead or rely on generic, content-agnostic textual prompts, thereby failing to provide adaptive semantic guidance efficiently. To overcome these limitations, we propose a content-adaptive diffusion-based image codec with three technical innovations: 1) an Uncertainty-Guided Adaptive Quantization method that learns spatial uncertainty maps to adaptively align quantization distortion with content characteristics; 2) an Auxiliary Decoder-Guided Information Concentration method that uses a lightweight auxiliary decoder to enforce content-aware information preservation in the primary latent channels; and 3) a Bitrate-Free Adaptive Textual Conditioning method that derives content-aware textual descriptions from the auxiliary reconstructed image, enabling semantic guidance without bitrate cost.

♻ ☆ ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees AAAI-26

Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda

Pixel-level feature attributions are an important tool in eXplainable AI for Computer Vision (XCV), providing visual insights into how image features influence model predictions. The Owen formula for hierarchical Shapley values has been widely used to interpret machine learning (ML) models and their learned representations. However, existing hierarchical Shapley approaches do not exploit the multiscale structure of image data, leading to slow convergence and weak alignment with the actual morphological features. Moreover, no prior Shapley method has leveraged data-aware hierarchies for Computer Vision tasks, leaving a gap in model interpretability of structured visual data. To address this, this paper introduces ShapBPT, a novel data-aware XCV method based on the hierarchical Shapley formula. ShapBPT assigns Shapley coefficients to a multiscale hierarchical structure tailored for images, the Binary Partition Tree (BPT). By using this data-aware hierarchical partitioning, ShapBPT ensures that feature attributions align with intrinsic image morphology, effectively prioritizing relevant regions while reducing computational overhead. This advancement connects hierarchical Shapley methods with image data, providing a more efficient and semantically meaningful approach to visual interpretability. Experimental results confirm ShapBPT's effectiveness, demonstrating superior alignment with image structures and improved efficiency over existing XCV methods, and a 20-subject user study confirming that ShapBPT explanations are preferred by humans.

comment: Presented at AAAI-26 conference and published in Proceedings of the The Fortieth AAAI Conference on Artificial Intelligence (AAAI-26)

♻ ☆ WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion

Manuel-Andreas Schneider, Angela Dai

Recent progress in image and video synthesis has inspired their use in advancing 3D scene generation. However, we observe that text-to-image and -video approaches struggle to maintain scene- and object-level consistency beyond a limited environment scale due to the absence of explicit geometry. We thus present a geometry-first approach that decouples this complex problem of large-scale 3D scene synthesis into its structural composition, represented as a mesh scaffold, and realistic appearance synthesis, which leverages powerful image synthesis models conditioned on the mesh scaffold. From an input text description, we first construct a mesh capturing the environment's geometry (walls, floors, etc.), and then use image synthesis, segmentation and object reconstruction to populate the mesh structure with objects in realistic layouts. This mesh scaffold is then rendered to condition image synthesis, providing a structural backbone for consistent appearance generation. This enables scalable, arbitrarily-sized 3D scenes of high object richness and diversity, combining robust 3D consistency with photorealistic detail. We believe this marks a significant step toward generating truly environment-scale, immersive 3D worlds.

comment: Project page: https://mschneider456.github.io/world-mesh/ Video: https://www.youtube.com/watch?v=MKMEbPT38-s Code: https://github.com/mschneider456/worldmesh

♻ ☆ CA-LoRA: Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation

Minho Park, Sunghyun Park, Jungsoo Lee, Hyojin Park, Kyuwoong Hwang, Fatih Porikli, Jaegul Choo, Sungha Choi

This paper addresses the challenge of data scarcity in semantic segmentation by generating datasets through text-to-image (T2I) generation models, reducing image acquisition and labeling costs. Segmentation dataset generation faces two key challenges: 1) aligning generated samples with the target domain and 2) producing informative samples beyond the training data. Fine-tuning T2I models can help generate samples aligned with the target domain. However, it often overfits and memorizes training data, limiting their ability to generate diverse and well-aligned samples. To overcome these issues, we propose Concept-Aware LoRA (CA-LoRA), a novel fine-tuning approach that selectively identifies and updates only the weights associated with necessary concepts (e.g., style or viewpoint) for domain alignment while preserving the pretrained knowledge of the T2I model to produce informative samples. We demonstrate its effectiveness in generating datasets for urban-scene segmentation, outperforming baseline and state-of-the-art methods in in-domain (few-shot and fully-supervised) settings, as well as in domain generalization tasks, especially under challenging conditions such as adverse weather and varying illumination, further highlighting its superiority.

comment: Accepted to CVPR 2026

♻ ☆ E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion

Zhihao Zhan, Jiaying Zhou, Likui Zhang, Qinhan Lv, Hao Liu, Jusheng Zhang, Weizheng Li, Ziliang Chen, Tianshui Chen, Ruifeng Zhai, Keze Wang, Liang Lin, Guangrun Wang

Vision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating visual perception, language understanding, and control generation. However, existing VLA systems still struggle to generalize across diverse tasks, scenes, and camera viewpoints, and often produce coarse or unstable actions. We argue that these limitations are closely tied to the structural properties of actions in VLA settings, including the inherent multi-peaked nature of action distributions, the token-based symbolic reasoning of pretrained VLM/VLA backbones, and the effective finite resolution imposed by real-world robotic control. Motivated by these properties, we introduce E0, a tweedie discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens. By operating in a discrete action space with a principled diffusion process, E0 naturally aligns with token-based reasoning, supports fine-grained yet executable action control, and avoids the distributional mismatch of masking-based discrete diffusion. We further introduce a spherical viewpoint perturbation augmentation to enhance robustness to camera shifts without additional data. Experiments on LIBERO, VLABench, ManiSkill, and a real-world Franka arm demonstrate that E0 achieves state-of-the-art performance across 14 diverse environments, outperforming strong baselines by 10.7% on average.

♻ ☆ TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning

Christian Greisinger, Steffen Eger

Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures from textual descriptions, often represented as TikZ programs that can be rendered as scientific images. Prior research has proposed a variety of datasets and modeling approaches for this task. However, existing datasets for Text-to-TikZ are too small and noisy to capture the complexity of TikZ, causing mismatches between text and rendered figures. Moreover, prior approaches rely solely on supervised fine-tuning (SFT), which does not expose the model to the rendered semantics of the figure, often resulting in errors such as looping, irrelevant content, and incorrect spatial relations. To address these issues, we construct DaTikZ-V4, a dataset more than four times larger and substantially higher in quality than DaTikZ-V3, enriched with LLM-generated figure descriptions. Using this dataset, we train TikZilla, a family of small open-source Qwen models (3B and 8B) with a two-stage pipeline of SFT followed by reinforcement learning (RL). For RL, we leverage an image encoder trained via inverse graphics to provide semantically faithful reward signals. Extensive human evaluations with over 1,000 judgments show that TikZilla improves by 1.5-2 points over its base models on a 5-point scale, surpasses GPT-4o by 0.5 points, and matches GPT-5 in the image-based evaluation, while operating at much smaller model sizes. Code, data, and models will be made available.

♻ ☆ MedAugment: Universal Automatic Data Augmentation Plug-in for Medical Image Analysis

Zhaoshan Liu, Qiujie Lv, Yifan Li, Ziduo Yang, Lei Shen

Data augmentation (DA) has been widely leveraged in computer vision to alleviate data shortage, while its application in medical imaging faces multiple challenges. The prevalent DA approaches in medical image analysis encompass conventional DA, synthetic DA, and automatic DA. However, these approaches may result in experience-driven design and intensive computation costs. Here, we propose a suitable yet general automatic DA method for medical images termed MedAugment. We propose pixel and spatial augmentation spaces and exclude the operations that can break medical details and features. Besides, we propose a sampling strategy by sampling a limited number of operations from the two spaces. Moreover, we present a hyperparameter mapping relationship to produce a rational augmentation level and make the MedAugment fully controllable using a single hyperparameter. These configurations settle the differences between natural and medical images. Extensive experimental results on four classification and four segmentation datasets demonstrate the superiority of MedAugment. Compared with existing approaches, the proposed MedAugment prevents producing color distortions or structural alterations while involving negligible computational overhead. Our method can serve as a plugin without an extra training stage, offering significant benefits to the community and medical experts lacking a deep learning foundation. The code is available at https://github.com/NUS-Tim/MedAugment.

comment: Knowledge-Based Systems Accepted

♻ ☆ ChordEdit: One-Step Low-Energy Transport for Image Editing

Liangsi Lu, Xuhang Chen, Minzhe Guo, Shichu Li, Jingchao Wang, Yang Shi

The advent of one-step text-to-image (T2I) models offers unprecedented synthesis speed. However, their application to text-guided image editing remains severely hampered, as forcing existing training-free editors into a single inference step fails. This failure manifests as severe object distortion and a critical loss of consistency in non-edited regions, resulting from the high-energy, erratic trajectories produced by naive vector arithmetic on the models' structured fields. To address this problem, we introduce ChordEdit, a model agnostic, training-free, and inversion-free method that facilitates high-fidelity one-step editing. We recast editing as a transport problem between the source and target distributions defined by the source and target text prompts. Leveraging dynamic optimal transport theory, we derive a principled, low-energy control strategy. This strategy yields a smoothed, variance-reduced editing field that is inherently stable, facilitating the field to be traversed in a single, large integration step. A theoretically grounded and experimentally validated approach allows ChordEdit to deliver fast, lightweight and precise edits, finally achieving true real-time editing on these challenging models.

comment: Accepted by CVPR 2026

♻ ☆ DepthFocus: Controllable Depth Estimation for See-Through Scenes

Junhong Min, Jimin Kim, Minwook Kim, Cheol-Hui Min, Youngpil Jeon, Minyong Choi

Depth in the real world is rarely singular. Transmissive materials create layered ambiguities that confound conventional perception systems. Existing models remain passive; conventional approaches typically estimate static depth maps anchored to the nearest surface, and even recent multi-head extensions suffer from a representational bottleneck due to fixed feature representations. This stands in contrast to human vision, which actively shifts focus to perceive a desired depth. We introduce \textbf{DepthFocus}, a steerable Vision Transformer that redefines stereo depth estimation as condition-aware control. Instead of extracting fixed features, our model dynamically modulates its computation based on a physical reference depth, integrating dual conditional mechanisms to selectively perceive geometry aligned with the desired focus. Leveraging a newly curated large-scale synthetic dataset, \textbf{DepthFocus} achieves state-of-the-art results across all evaluated benchmarks, including both standard single-layer and complex multi-layered scenarios. While maintaining high precision in opaque regions, our approach effectively resolves depth ambiguities in transparent and reflective scenes by selectively reconstructing geometry at a target distance. This capability enables robust, intent-driven perception that significantly outperforms existing multi-layer methods, marking a substantial step toward active 3D perception. \noindent \textbf{Project page}: \href{https://junhong-3dv.github.io/depthfocus-project/}{\textbf{this https URL}}.

comment: 8pages, 5 figures, 5 tables

♻ ☆ Anchored Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models

Mariam Hassan, Bastien Van Delft, Wuyang Li, Alexandre Alahi

State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal instructions. In this paper, we argue that many errors, including apparent motion failures, originate from the model's inability to construct a semantically correct or logically consistent initial frame. We introduce Anchored Video Generation (AVG), a modular pipeline that decouples these tasks by decomposing the Text-to-Video generation into three specialized stages: (1) Reasoning, where a Large Language Model (LLM) rewrites the video prompt to describe only the initial scene, resolving temporal ambiguities; (2) Composition, where a Text-to-Image (T2I) model synthesizes a high-quality, compositionally-correct anchor frame from this new prompt; and (3) Temporal Synthesis, where a video model, finetuned to understand this anchor, focuses its entire capacity on animating the scene and following the prompt. Our approach sets a new state-of-the-art on the T2V CompBench benchmark and significantly improves all tested models on VBench2. Furthermore, we show that visual anchoring allows us to cut the number of sampling steps by 70% without any loss in performance. AVG offers a simple yet practical path toward more efficient, robust, and controllable video synthesis.

♻ ☆ Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features

Zheng Gao, Debin Meng, Yunqi Miao, Zhensong Zhang, Songcen Xu, Ioannis Patras, Jifei Song

Current diffusion-based makeup transfer methods commonly use the makeup information encoded by off-the-shelf foundation models (e.g., CLIP) as condition to preserve the makeup style of reference image in the generation. Although effective, these works mainly have two limitations: (1) foundation models pre-trained for generic tasks struggle to capture makeup styles; (2) the makeup features of reference image are injected to the diffusion denoising model as a whole for global makeup transfer, overlooking the facial region-aware makeup features (i.e., eyes, mouth, etc) and limiting the regional controllability for region-specific makeup transfer. To address these, in this work, we propose Facial Region-Aware Makeup features (FRAM), which has two stages: (1) makeup CLIP fine-tuning; (2) identity and facial region-aware makeup injection. For makeup CLIP fine-tuning, unlike prior works using off-the-shelf CLIP, we synthesize annotated makeup style data using GPT-o3 and text-driven image editing model, and then use the data to train a makeup CLIP encoder through self-supervised and image-text contrastive learning. For identity and facial region-aware makeup injection, we construct before-and-after makeup image pairs from the edited images in stage 1 and then use them to learn to inject identity of source image and makeup of reference image to the diffusion denoising model for makeup transfer. Specifically, we use learnable tokens to query the makeup CLIP encoder to extract facial region-aware makeup features for makeup injection, which is learned via an attention loss to enable regional control. As for identity injection, we use a ControlNet Union to encode source image and its 3D mesh simultaneously. The experimental results verify the superiority of our regional controllability and our makeup transfer performance. Code is available at https://github.com/zaczgao/Facial_Region-Aware_Makeup.

comment: Accepted by CVPR'26

♻ ☆ SPARE: Self-distillation for PARameter-Efficient Removal

Natnael Mola, Leonardo S. B. Pereira, Carolina R. Kelsch, Luis H. Arribas, Juan C. S. M. Avedillo

Machine Unlearning aims to remove the influence of specific data or concepts from trained models while preserving overall performance, a capability increasingly required by data protection regulations and responsible AI practices. Despite recent progress, unlearning in text-to-image diffusion models remains challenging due to high computational costs and the difficulty of balancing effective forgetting with retention of unrelated concepts. We introduce Self-distillation for PARameter Efficient Removal (SPARE), a two-stage unlearning method for image generation that combines parameter localization with self-distillation. SPARE first identifies parameters most responsible for generation of the unwanted concepts using gradient-based saliency and constrains updates through sparse low rank adapters, ensuring lightweight, localized modifications. In a second stage, SPARE applies a self-distillation objective that overwrites the unwanted concept with a user-defined surrogate while preserving behavior for other concepts. In addition we proposed a timestep sampling scheme for diffusion models to target only the crucial timesteps for a given concept leading to efficient unlearning. SPARE surpasses the current state-of-the-art on the UnlearnCanvas benchmark, and ablation studies on several datasets indicate fine-grained control over the forgetting-retention trade-off. Our results demonstrate that SPARE achieves strong concept erasure and high retainability across various domains, making it a suitable solution for selective unlearning in diffusion-based image generation models.

♻ ☆ Physics-driven human-like working memory outperforms digital networks in dynamic vision

Jingli Liu, Huannan Zheng, Bohao Zou, Kezhou Yang

While the unsustainable energy cost of artificial intelligence necessitates physics-driven computing, its performance superiority over full-precision GPUs remains a challenge. We bridge this gap by repurposing the Joule-heating relaxation dynamics of magnetic tunnel junctions, conventionally suppressed as noise, into neuronal intrinsic plasticity, realizing working memory with human-like features. Traditional AI utilizes energy-intensive digital memory that accumulates historical noise in dynamic environments. Conversely, our Intrinsic Plasticity Network (IPNet) leverages thermodynamic dissipation as a temporal filter. We provide direct system-level evidence that this physics-driven memory yields an 18x error reduction compared to spatiotemporal convolutional models in dynamic vision tasks, reducing memory-energy overhead by >90,000x. In autonomous driving, IPNet reduces prediction errors by 12.4% versus recurrent networks. This establishes a neuromorphic paradigm that shatters efficiency limits and surpasses conventional algorithmic performance.

♻ ☆ EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

Longfei Liu, Yongjie Hou, Yang Li, Qirui Wang, Youyang Sha, Yongjun Yu, Yinzhi Wang, Peizhe Ru, Xuanlong Yu, Xi Shen

Deploying high-performance dense prediction models on resource-constrained edge devices remains challenging due to strict limits on computation and memory. In practice, lightweight systems for object detection, instance segmentation, and pose estimation are still dominated by CNN-based architectures such as YOLO, while compact Vision Transformers (ViTs) often struggle to achieve similarly strong accuracy efficiency tradeoff, even with large scale pretraining. We argue that this gap is largely due to insufficient task specific representation learning in small scale ViTs, rather than an inherent mismatch between ViTs and edge dense prediction. To address this issue, we introduce EdgeCrafter, a unified compact ViT framework for edge dense prediction centered on ECDet, a detection model built from a distilled compact backbone and an edge-friendly encoder decoder design. On the COCO dataset, ECDet-S achieves 51.7 AP with fewer than 10M parameters using only COCO annotations. For instance segmentation, ECInsSeg achieves performance comparable to RF-DETR while using substantially fewer parameters. For pose estimation, ECPose-X reaches 74.8 AP, significantly outperforming YOLO26Pose-X (71.6 AP) despite the latter's reliance on extensive Objects365 pretraining. These results show that compact ViTs, when paired with task-specialized distillation and edge-aware design, can be a practical and competitive option for edge dense prediction. Code is available at: https://intellindust-ai-lab.github.io/projects/EdgeCrafter/

comment: Code is available at: https://intellindust-ai-lab.github.io/projects/EdgeCrafter/

♻ ☆ Continual GUI Agents

Ziwei Liu, Borui Kang, Hangjie Yuan, Zixiang Zhao, Wei Li, Yifan Zhu, Tao Feng

As digital environments (data distribution) are in flux, with new GUI data arriving over time-introducing new domains or resolutions-agents trained on static environments deteriorate in performance. In this work, we introduce Continual GUI Agents, a new task that requires GUI agents to perform continual learning under shifted domains and resolutions. We find existing methods fail to maintain stable grounding as GUI distributions shift over time, due to the diversity of UI interaction points and regions in fluxing scenarios. To address this, we introduce GUI-Anchoring in Flux (GUI-AiF), a new reinforcement fine-tuning framework that stabilizes continual learning through two novel rewards: Anchoring Point Reward in Flux (APR-iF) and Anchoring Region Reward in Flux (ARR-iF). These rewards guide the agents to align with shifting interaction points and regions, mitigating the tendency of existing reward strategies to over-adapt to static grounding cues (e.g., fixed coordinates or element scales). Extensive experiments show GUI-AiF surpasses state-of-the-art baselines. Our work establishes the first continual learning framework for GUI agents, revealing the untapped potential of reinforcement fine-tuning for continual GUI Agents.

comment: Code is available at: https://github.com/xavierliu34/GUI-AiF

♻ ☆ Dehallu3D: Hallucination-Mitigated 3D Generation from Single Image via Cyclic View Consistency Refinement

Xiwen Wang, Shichao Zhang, Hailun Zhang, Ruowei Wang, Mao Li, Chenyu Zhou, Qijun Zhao, Ji-Zhe Zhou

Large 3D reconstruction models have revolutionized the 3D content generation field, enabling broad applications in virtual reality and gaming. Just like other large models, large 3D reconstruction models suffer from hallucinations as well, introducing structural outliers (e.g., odd holes or protrusions) that deviate from the input data. However, unlike other large models, hallucinations in large 3D reconstruction models remain severely underexplored, leading to malformed 3D-printed objects or insufficient immersion in virtual scenes. Such hallucinations majorly originate from that existing methods reconstruct 3D content from sparsely generated multi-view images which suffer from large viewpoint gaps and discontinuities. To mitigate hallucinations by eliminating the outliers, we propose Dehallu3D for 3D mesh generation. Our key idea is to design a balanced multi-view continuity constraint to enforce smooth transitions across dense intermediate viewpoints, while avoiding over-smoothing that could erase sharp geometric features. Therefore, Dehallu3D employs a plug-and-play optimization module with two key constraints: (i) adjacent consistency to ensure geometric continuity across views, and (ii) adaptive smoothness to retain fine details.We further propose the Outlier Risk Measure (ORM) metric to quantify geometric fidelity in 3D generation from the perspective of outliers. Extensive experiments show that Dehallu3D achieves high-fidelity 3D generation by effectively preserving structural details while removing hallucinated outliers.

♻ ☆ Understanding Pure Textual Reasoning for Blind Image Quality Assessment

Yuan Li, Shin'ya Nishida

Textual reasoning has recently been widely adopted in Blind Image Quality Assessment (BIQA). However, it remains unclear how textual information contributes to quality prediction and to what extent text can represent the score-related image contents. This work addresses these questions from an information-flow perspective by comparing existing BIQA models with three paradigms designed to learn the image-text-score relationship: Chain-of-Thought, Self-Consistency, and Autoencoder. Our experiments show that the score prediction performance of the existing model significantly drops when only textual information is used for prediction. Whereas the Chain-of-Thought paradigm introduces little improvement in BIQA performance, the Self-Consistency paradigm significantly reduces the gap between image- and text-conditioned predictions, narrowing the PLCC/SRCC difference to 0.02/0.03. The Autoencoder-like paradigm is less effective in closing the image-text gap, yet it reveals a direction for further optimization. These findings provide insights into how to improve the textual reasoning for BIQA and high-level vision tasks.

comment: Code available at https://github.com/AnonymousUserPublish/Bridging-Image-Text-Gap-for-BIQA/tree/main. This work is accepted by ICME (IEEE International Conference on Multimedia and Expo) 2026

♻ ☆ PoseDriver: A Unified Approach to Multi-Category Skeleton Detection for Autonomous Driving

Yasamin Borhani, Taylor Mordan, Yihan Wang, Reyhaneh Hosseininejad, Javad Khoramdel, Alexandre Alahi

Object skeletons offer a concise representation of structural information, capturing essential aspects of posture and orientation that are crucial for autonomous driving applications. However, a unified architecture that simultaneously handles multiple instances and categories using only the input image remains elusive. In this paper, we introduce PoseDriver, a unified framework for bottom-up multi-category skeleton detection tailored to common objects in driving scenarios. We model each category as a distinct task to systematically address the challenges of multi-task learning. Specifically, we propose a novel approach for lane detection based on skeleton representations, achieving state-of-the-art performance on the OpenLane dataset. Moreover, we present a new dataset for bicycle skeleton detection and assess the transferability of our framework to novel categories. Experimental results validate the effectiveness of the proposed approach.

♻ ☆ Thinking with Geometry: Active Geometry Integration for Spatial Reasoning

Haoyuan Li, Qihang Cao, Tao Tang, Kun Xiang, Zihan Guo, Jianhua Han, Hang Xu, Xiaodan Liang

Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration strategies remain passive: geometry is exposed as a global stream and fused in an indiscriminate manner, which often induces semantic-geometry misalignment and redundant signals. We propose GeoThinker, a framework that shifts the paradigm from passive fusion to active perception. Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands. GeoThinker achieves this through Spatial-Grounded Fusion applied at carefully selected VLM layers, where semantic visual priors selectively query and integrate task-relevant geometry via frame-strict cross-attention, further calibrated by Importance Gating that biases per-frame attention toward task-relevant structures. Comprehensive evaluation results show that GeoThinker sets a new state-of-the-art in spatial intelligence, achieving a peak score of 72.6 on the VSI-Bench. Furthermore, GeoThinker demonstrates robust generalization and significantly improved spatial perception across complex downstream scenarios, including embodied referring and autonomous driving. Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence. Code can be found at https://github.com/Li-Hao-yuan/GeoThinker.

♻ ☆ Ontology-Guided Diffusion for Zero-Shot Visual Sim2Real Transfer

Mohamed Youssef, Mayar Elfares, Anna-Maria Meer, Matteo Bortoletto, Andreas Bulling

Bridging the simulation-to-reality (sim2real) gap remains challenging as labelled real-world data is scarce. Existing diffusion-based approaches rely on unstructured prompts or statistical alignment, which do not capture the structured factors that make images look real. We introduce Ontology- Guided Diffusion (OGD), a neuro-symbolic zero-shot sim2real image translation framework that represents realism as structured knowledge. OGD decomposes realism into an ontology of interpretable traits -- such as lighting and material properties -- and encodes their relationships in a knowledge graph. From a synthetic image, OGD infers trait activations and uses a graph neural network to produce a global embedding. In parallel, a symbolic planner uses the ontology traits to compute a consistent sequence of visual edits needed to narrow the realism gap. The graph embedding conditions a pretrained instruction-guided diffusion model via cross-attention, while the planned edits are converted into a structured instruction prompt. Across benchmarks, our graph-based embeddings better distinguish real from synthetic imagery than baselines, and OGD outperforms state-of-the-art diffusion methods in sim2real image translations. Overall, OGD shows that explicitly encoding realism structure enables interpretable, data-efficient, and generalisable zero-shot sim2real transfer.

♻ ☆ From Feature Learning to Spectral Basis Learning: A Unifying and Flexible Framework for Efficient and Robust Shape Matching

Feifan Luo, Hongyang Chen

Shape matching is a fundamental task in computer graphics and vision, with deep functional maps becoming a prominent paradigm. However, existing methods primarily focus on learning informative feature representations by constraining pointwise and functional maps, while neglecting the optimization of the spectral basis-a critical component of the functional map pipeline. This oversight often leads to suboptimal matching results. Furthermore, many current approaches rely on conventional, time-consuming functional map solvers, incurring significant computational overhead. To bridge these gaps, we introduce Advanced Functional Maps, a framework that generalizes standard functional maps by replacing fixed basis functions with learnable ones, supported by rigorous theoretical guarantees. Specifically, the spectral basis is optimized through a set of learned inhibition functions. Building on this, we propose the first unsupervised spectral basis learning method for robust non-rigid 3D shape matching, enabling the joint, end-to-end optimization of feature extraction and basis functions. Our approach incorporates a novel heat diffusion module and an unsupervised loss function, alongside a streamlined architecture that bypasses expensive solvers and auxiliary losses. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art feature-learning approaches, particularly in challenging non-isometric and topological noise scenarios, while maintaining high efficiency. Finally, we reveal that optimizing basis functions is equivalent to spectral convolution, where inhibition functions act as filters. This insight enables enhanced representations inspired by spectral graph networks, opening new avenues for future research. Our code is available at https://github.com/LuoFeifan77/Unsupervised-Spectral-Basis-Learning.

♻ ☆ One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara, Nicola Messina, Giuseppe Amato, Fabrizio Falchi

Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption an image, they proceed by textually decoding a text-aligned image feature, but they limit their scope to global representations and whole-image captions. We present a unified framework for zero-shot captioning that shifts from an image-centric to a patch-centric paradigm, enabling the captioning of arbitrary regions without the need of region-level supervision. Instead of relying on global image representations, we treat individual patches as atomic captioning units and aggregate them to describe arbitrary regions, from single patches to non-contiguous areas and entire images. We analyze the key ingredients that enable current latent captioners to work in our novel proposed framework. Experiments demonstrate that backbones producing meaningful, dense visual features, such as DINO, are key to achieving state-of-the-art performance in multiple region-based captioning tasks. Compared to other baselines and state-of-the-art competitors, our models achieve better performance on zero-shot dense captioning and region-set captioning. We also introduce a new trace captioning task that further demonstrates the effectiveness of patch-wise semantic representations for flexible caption generation. Project page at https://paciosoft.com/Patch-ioner/ .

comment: CVPR 2026

♻ ☆ ExpPortrait: Expressive Portrait Generation via Personalized Representation

Junyi Wang, Yudong Guo, Boyang Guo, Shengming Yang, Juyong Zhang

While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challenge. Existing intermediate signals for portrait generation, such as 2D landmarks and parametric models, have limited disentanglement capabilities and cannot express personalized details due to their sparse or low-rank representation. Therefore, existing methods based on these models struggle to accurately preserve subject identity and expressions, hindering the generation of highly expressive portrait videos. To overcome these limitations, we propose a high-fidelity personalized head representation that more effectively disentangles expression and identity. This representation captures both static, subject-specific global geometry and dynamic, expression-related details. Furthermore, we introduce an expression transfer module to achieve personalized transfer of head pose and expression details between different identities. We use this sophisticated and highly expressive head model as a conditional signal to train a diffusion transformer (DiT)-based generator to synthesize richly detailed portrait videos. Extensive experiments on self- and cross-reenactment tasks demonstrate that our method outperforms previous models in terms of identity preservation, expression accuracy, and temporal stability, particularly in capturing fine-grained details of complex motion.

comment: CVPR 2026, Project Page: https://ustc3dv.github.io/ExpPortrait/

♻ ☆ Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration

Chen Wu, Ling Wang, Zhuoran Zheng, Yuning Cui, Zhixiong Yang, Xiangyu Chen, Yue Zhang, Weidong Jiang, Jingyuan Xia

Ultra-High-Definition (UHD) image restoration is trapped in a scalability crisis: existing models, bound to pixel-wise operations, demand unsustainable computation. While state space models (SSMs) like Mamba promise linear complexity, their pixel-serial scanning remains a fundamental bottleneck for the millions of pixels in UHD content. We ask: must we process every pixel to understand the image? This paper introduces C$^2$SSM, a visual state space model that breaks this taboo by shifting from pixel-serial to cluster-serial scanning. Our core discovery is that the rich feature distribution of a UHD image can be distilled into a sparse set of semantic centroids via a neural-parameterized mixture model. C$^2$SSM leverages this to reformulate global modeling into a novel dual-path process: it scans and reasons over a handful of cluster centers, then diffuses the global context back to all pixels through a principled similarity distribution, all while a lightweight modulator preserves fine details. This cluster-centric paradigm achieves a decisive leap in efficiency, slashing computational costs while establishing new state-of-the-art results across five UHD restoration tasks. More than a solution, C$^2$SSM charts a new course for efficient large-scale vision: scan clusters, not pixels.

comment: Aceepted by CVPR26

♻ ☆ DarkDriving: A Real-World Day and Night Aligned Dataset for Autonomous Driving in the Dark Environment

Wuqi Wang, Haochen Yang, Baolu Li, Jiaqi Sun, Xiangmo Zhao, Zhigang Xu, Qing Guo, Haigen Min, Tianyun Zhang, Hongkai Yu

The low-light conditions are challenging to the vision-centric perception systems for autonomous driving in the dark environment. In this paper, we propose a new benchmark dataset (named DarkDriving) to investigate the low-light enhancement for autonomous driving. The existing real-world low-light enhancement benchmark datasets can be collected by controlling various exposures only in small-ranges and static scenes. The dark images of the current nighttime driving datasets do not have the precisely aligned daytime counterparts. The extreme difficulty to collect a real-world day and night aligned dataset in the dynamic driving scenes significantly limited the research in this area. With a proposed automatic day-night Trajectory Tracking based Pose Matching (TTPM) method in a large real-world closed driving test field (area: 69 acres), we collected the first real-world day and night aligned dataset for autonomous driving in the dark environment. The DarkDriving dataset has 9,538 day and night image pairs precisely aligned in location and spatial contents, whose alignment error is in just several centimeters. For each pair, we also manually label the object 2D bounding boxes. DarkDriving introduces four perception related tasks, including low-light enhancement, generalized low-light enhancement, and low-light enhancement for 2D detection and 3D detection of autonomous driving in the dark environment. The experimental results show that our DarkDriving dataset provides a comprehensive benchmark for evaluating low-light enhancement for autonomous driving and it can also be generalized to enhance dark images and promote detection in some other low-light driving environment, such as nuScenes.The code and dataset will be publicly available at https://github.com/DriveMindLab/DarkDriving-ICRA-2026.

comment: 8 pages, 8 figures. Accepted to ICRA 2026

♻ ☆ EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing

Wei Chow, Linfeng Li, Lingdong Kong, Zefeng Li, Qi Xu, Hang Song, Tian Ye, Xian Wang, Jinbin Bai, Shilin Xu, Xiangtai Li, Junting Pan, Shaoteng Liu, Ran Zhou, Tianshu Yang, Songhua Liu

Recent advances in diffusion models (DMs) have achieved exceptional visual quality in image editing tasks. However, the global denoising dynamics of DMs inherently conflate local editing targets with the full-image context, leading to unintended modifications in non-target regions. In this paper, we shift our attention beyond DMs and turn to Masked Generative Transformers (MGTs) as an alternative approach to tackle this challenge. By predicting multiple masked tokens rather than holistic refinement, MGTs exhibit a localized decoding paradigm that endows them with the inherent capacity to explicitly preserve non-relevant regions during the editing process. Building upon this insight, we introduce the first MGT-based image editing framework, termed EditMGT. We first demonstrate that MGT's cross-attention maps provide informative localization signals for localizing edit-relevant regions and devise a multi-layer attention consolidation scheme that refines these maps to achieve fine-grained and precise localization. On top of these adaptive localization results, we introduce region-hold sampling, which restricts token flipping within low-attention areas to suppress spurious edits, thereby confining modifications to the intended target regions and preserving the integrity of surrounding non-target areas. To train EditMGT, we construct CrispEdit-2M, a high-resolution dataset spanning seven diverse editing categories. Without introducing additional parameters, we adapt a pre-trained text-to-image MGT into an image editing model through attention injection. Extensive experiments across four standard benchmarks demonstrate that, with fewer than 1B parameters, our model achieves similarity performance while enabling 6 times faster editing. Moreover, it delivers comparable or superior editing quality, with improvements of 3.6% and 17.6% on style change and style transfer tasks, respectively.

♻ ☆ PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment

Suhyeon Lee, Jong Chul Ye

Despite recent progress, reinforcement learning (RL)-based fine-tuning of diffusion models often struggles with generalization, composability, and robustness against reward hacking. Recent studies have explored prompt refinement as a modular alternative, but most adopt a feed-forward approach that applies a single refined prompt throughout the entire sampling trajectory, thereby failing to fully leverage the sequential nature of reinforcement learning. To address this, we introduce PromptLoop, a plug-and-play RL framework that incorporates latent feedback into step-wise prompt refinement. Rather than modifying diffusion model weights, a multimodal large language model (MLLM) is trained with RL to iteratively update prompts based on intermediate latent states of diffusion models. This design achieves a structural analogy to the Diffusion RL approach, while retaining the flexibility and generality of prompt-based alignment. Extensive experiments across diverse reward functions and diffusion backbones demonstrate that PromptLoop (i) achieves effective reward optimization, (ii) generalizes seamlessly to unseen models, (iii) composes orthogonally with existing alignment methods, and (iv) mitigates over-optimization and reward hacking while introducing only a practically negligible inference overhead.

comment: CVPR26 poster. 25 pages, 19 figures

♻ ☆ Tiny Inference-Time Scaling with Latent Verifiers

Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Inference-time scaling has emerged as an effective way to improve generative models at test time by using a verifier to score and select candidate outputs. A common choice is to employ Multimodal Large Language Models (MLLMs) as verifiers, which can improve performance but introduce substantial inference-time cost. Indeed, diffusion pipelines operate in an autoencoder latent space to reduce computation, yet MLLM verifiers still require decoding candidates to pixel space and re-encoding them into the visual embedding space, leading to redundant and costly operations. In this work, we propose Verifier on Hidden States (VHS), a verifier that operates directly on intermediate hidden representations of Diffusion Transformer (DiT) single-step generators. VHS analyzes generator features without decoding to pixel space, thereby reducing the per-candidate verification cost while improving or matching the performance of MLLM-based competitors. We show that, under tiny inference budgets with only a small number of candidates per prompt, VHS enables more efficient inference-time scaling reducing joint generation-and-verification time by 63.3%, compute FLOPs by 51% and VRAM usage by 14.5% with respect to a standard MLLM verifier, achieving a +2.7% improvement on GenEval at the same inference-time budget.

comment: Findings of CVPR 2026 - Code at: https://aimagelab.github.io/VHS/

♻ ☆ OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMs

Stefan Maria Ailuro, Mario Markov, Mohammad Mahdi, Delyan Boychev, Luc Van Gool, Danda Pani Paudel

Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling pipelines address this gap by distilling knowledge from large frontier models, but this dependence on large teachers is costly, limits scalability, and caps achievable performance at the ceiling of the teacher. We propose OSMDA: a self-contained domain adaptation framework that eliminates this dependency. Our key insight is that a capable base VLM can serve as its own annotation engine: by pairing aerial images with rendered OpenStreetMap (OSM) tiles, we leverage optical character recognition and chart comprehension capabilities of the model to generate captions enriched by OSM's vast auxiliary metadata. The model is then fine-tuned on the resulting corpus with satellite imagery alone, yielding OSMDA-VLM, a domain-adapted VLM that requires no manual labeling and no stronger external model. We conduct exhaustive evaluations spanning 10 benchmarks across image-text-to-text tasks and comparing against 9 competitive baselines. When equally mixed with real data, our method achieves state-of-the-art results, while being substantially cheaper to train than teacher-dependent alternatives. These results suggest that, given a strong foundation model, alignment with crowd-sourced geographic data is a practical and scalable path towards remote sensing domain adaptation. Dataset and model weights will be made publicly available.

♻ ☆ Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences

Julian Kaltheuner, Hannah Dröge, Markus Plack, Patrick Stotko, Reinhard Klein

Temporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. Existing methods either optimize deformations incrementally, risking drift and requiring long runtimes, or rely on complex learned models that demand category-specific training. We present Neu-PiG, a fast deformation optimization method based on a novel preconditioned latent-grid encoding that distributes spatial features parameterized on the position and normal direction of a keyframe surface. Our method encodes entire deformations across all time steps at various spatial scales into a multi-resolution latent grid, parameterized by the position and normal direction of a reference surface from a single keyframe. This latent representation is then augmented for time modulation and decoded into per-frame 6-DoF deformations via a lightweight multilayer perceptron (MLP). To achieve high-fidelity, drift-free surface reconstructions in seconds, we employ Sobolev preconditioning during gradient-based training of the latent space, completely avoiding the need for any explicit correspondences or further priors. Experiments across diverse human and animal datasets demonstrate that Neu-PiG outperforms state-the-art approaches, offering both superior accuracy and scalability to long sequences while running at least 60x faster than existing training-free methods and achieving inference speeds on the same order as heavy pretrained models.

comment: CVPR 2026, Code: https://github.com/vc-bonn/neu-pig

♻ ☆ Pro-Pose: Unpaired Full-Body Portrait Synthesis via Canonical UV Maps

Sandeep Mishra, Yasamin Jafarian, Andreas Lugmayr, Yingwei Li, Varsha Ramakrishnan, Srivatsan Varadharajan, Alan C. Bovik, Ira Kemelmacher-Shlizerman

Photographs of people taken by professional photographers typically present the person in beautiful lighting, with an interesting pose, and flattering quality. This is unlike common photos people take of themselves in uncontrolled conditions. In this paper, we explore how to canonicalize a person's 'in-the-wild' photograph into a controllable, high-fidelity avatar -- reposed in a simple environment with standardized minimal clothing. A key challenge is preserving the person's unique whole-body identity, facial features, and body shape while stripping away the complex occlusions of their original garments. While a large paired dataset of the same person in varied clothing and poses would simplify this, such data does not exist. To that end, we propose two key insights: 1) Our method transforms the input photo into a canonical full-body UV space, which we couple with a novel reposing methodology to model occlusions and synthesize novel views. Operating in UV space allows us to decouple pose from appearance and leverage massive unpaired datasets. 2) We personalize the output photo via multi-image finetuning to ensure robust identity preservation under extreme pose changes. Our approach yields high-quality, reposed portraits that achieve strong quantitative performance on real-world imagery, providing an ideal, clean biometric canvas that significantly improves the fidelity of downstream applications like Virtual Try-On (VTO).

♻ ☆ HybridSplat: Fast Reflection-baked Gaussian Tracing using Hybrid Splatting

Chang Liu, Hongliang Yuan, Lianghao Zhang, Sichao Wang, Jianwei Guo, Shi-Sheng Huang

Rendering complex reflection of real-world scenes using 3D Gaussian splatting has been a quite promising solution for photorealistic novel view synthesis, but still faces bottlenecks especially in rendering speed and memory storage. This paper proposes a new Hybrid Splatting(HybridSplat) mechanism for Gaussian primitives. Our key idea is a new reflection-baked Gaussian tracing, which bakes the view-dependent reflection within each Gaussian primitive while rendering the reflection using tile-based Gaussian splatting. Then we integrate the reflective Gaussian primitives with base Gaussian primitives using a unified hybrid splatting framework for high-fidelity scene reconstruction. Moreover, we further introduce a pipeline-level acceleration for the hybrid splatting, and reflection-sensitive Gaussian pruning to reduce the model size, thus achieving much faster rendering speed and lower memory storage while preserving the reflection rendering quality. By extensive evaluation, our HybridSplat accelerates about 7x rendering speed across complex reflective scenes from Ref-NeRF, NeRF-Casting with 4x fewer Gaussian primitives than similar ray-tracing based Gaussian splatting baselines, serving as a new state-of-the-art method especially for complex reflective scenes.

comment: The authors have decided to withdraw this manuscript to undergo a comprehensive revision of the methodology and data analysis. The current version no longer accurately reflects the final scope and quality of our ongoing research

♻ ☆ Language Models Can Explain Visual Features via Steering

Javier Ferrando, Enrique Lopez-Cuena, Pablo Agustin Martin-Torres, Daniel Hinjos, Anna Arias-Duart, Dario Garcia-Gasulla

Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations based on top activating input examples, we present a fundamentally different alternative based on causal interventions. We leverage the structure of Vision-Language Models and steer individual SAE features in the vision encoder after providing an empty image. Then, we prompt the language model to explain what it ``sees'', effectively eliciting the visual concept represented by each feature. Results show that Steering offers an scalable alternative that complements traditional approaches based on input examples, serving as a new axis for automated interpretability in vision models. Moreover, the quality of explanations improves consistently with the scale of the language model, highlighting our method as a promising direction for future research. Finally, we propose Steering-informed Top-k, a hybrid approach that combines the strengths of causal interventions and input-based approaches to achieve state-of-the-art explanation quality without additional computational cost.

comment: Accepted at CVPR 2026

♻ ☆ DriveXQA: Cross-modal Visual Question Answering for Adverse Driving Scene Understanding

Mingzhe Tao, Ruiping Liu, Junwei Zheng, Yufan Chen, Kedi Ying, M. Saquib Sarfraz, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen

Fusing sensors with complementary modalities is crucial for maintaining a stable and comprehensive understanding of abnormal driving scenes. However, Multimodal Large Language Models (MLLMs) are underexplored for leveraging multi-sensor information to understand adverse driving scenarios in autonomous vehicles. To address this gap, we propose the DriveXQA, a multimodal dataset for autonomous driving VQA. In addition to four visual modalities, five sensor failure cases, and five weather conditions, it includes $102,505$ QA pairs categorized into three types: global scene level, allocentric level, and ego-vehicle centric level. Since no existing MLLM framework adopts multiple complementary visual modalities as input, we design MVX-LLM, a token-efficient architecture with a Dual Cross-Attention (DCA) projector that fuses the modalities to alleviate information redundancy. Experiments demonstrate that our DCA achieves improved performance under challenging conditions such as foggy (GPTScore: $53.5$ vs. $25.1$ for the baseline).

comment: Accepted to CVPR DriveX Workshop. Dataset and Code: https://github.com/jtjmd/DRIVEXQA

♻ ☆ FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention

Zipeng Wang, Dan Xu

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art models like the Visual Geometry Grounding Transformer (VGGT) leverage full self-attention over all image tokens to capture global relationships. However, this approach suffers from poor scalability due to the quadratic complexity of self-attention and the large number of tokens generated in long image sequences. In this work, we introduce FlashVGGT, an efficient alternative that addresses this bottleneck through a descriptor-based attention mechanism. Instead of applying dense global attention across all tokens, FlashVGGT compresses spatial information from each frame into a compact set of descriptor tokens. Global attention is then computed as cross-attention between the full set of image tokens and this smaller descriptor set, significantly reducing computational overhead. Moreover, the compactness of the descriptors enables online inference over long sequences via a chunk-recursive mechanism that reuses cached descriptors from previous chunks. Experimental results show that FlashVGGT achieves reconstruction accuracy competitive with VGGT while reducing inference time to just 9.3% of VGGT for 1,000 images, and scaling efficiently to sequences exceeding 3,000 images. Our project page is available at https://wzpscott.github.io/flashvggt_page/.

comment: CVPR2026

♻ ☆ NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization

Yifei Li, Haoyuan He, Yu Zheng, Bingyao Yu, Wenzhao Zheng, Lei Chen, Jie Zhou, Jiwen Lu

The accessibility surge and abuse risks of user-friendly image editing models have created an urgent need for generalizable, up-to-date methods for Image Manipulation Detection and Localization (IMDL). Current IMDL research typically uses cross-dataset evaluation, where models trained on one benchmark are tested on others. However, this simplified evaluation approach conceals the fragility of existing methods when handling diverse AI-generated content, leading to misleading impressions of progress. This paper challenges this illusion by proposing NeXT-IMDL, a large-scale diagnostic benchmark designed not just to collect data, but to probe the generalization boundaries of current detectors systematically. Specifically, NeXT-IMDL categorizes AIGC-based manipulations along four fundamental axes: editing models, manipulation types, content semantics, and forgery granularity. Built upon this, NeXT-IMDL implements five rigorous cross-dimension evaluation protocols. Our extensive experiments on 11 representative models reveal a critical insight: while these models perform well in their original settings, they exhibit systemic failures and significant performance degradation when evaluated under our designed protocols that simulate real-world, various generalization scenarios. By providing this diagnostic toolkit and the new findings, we aim to advance the development towards building truly robust, next-generation IMDL models.

comment: Duplicate experiment results in Table 3 (Set-1 & Set-2)

♻ ☆ Establishing Stochastic Object Models from Noisy Data via Ambient Measurement-Integrated Diffusion

Xiaoning Lei, Jianwei Sun, Wenhao Cai, Xichen Xu, Yanshu Wang, Hu Gao

Task-based measures of image quality (IQ) are critical for evaluating medical imaging systems, which must account for randomness including anatomical variability. Stochastic object models (SOMs) provide a statistical description of such variability, but conventional mathematical SOMs fail to capture realistic anatomy, while data-driven approaches typically require clean data rarely available in clinical tasks. To address this challenge, we propose AMID, an unsupervised Ambient Measurement-Integrated Diffusion with noise decoupling, which establishes clean SOMs directly from noisy measurements. AMID introduces a measurement-integrated strategy aligning measurement noise with the diffusion trajectory, and explicitly models coupling between measurement and diffusion noise across steps, an ambient loss is thus designed base on it to learn clean SOMs. Experiments on real CT and mammography datasets show that AMID outperforms existing methods in generation fidelity and yields more reliable task-based IQ evaluation, demonstrating its potential for unsupervised medical imaging analysis.

♻ ☆ MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding

Basit Alawode, Arif Mahmood, Muaz Khalifa Al-Radi, Shahad Albastaki, Asim Khan, Muhammad Bilal, Moshira Ali Abdalla, Mohammed Bennamoun, Sajid Javed

Whole Slide Images (WSIs) exhibit hierarchical structure, where diagnostic information emerges from cellular morphology, regional tissue organization, and global context. Existing Computational Pathology (CPath) Multimodal Large Language Models (MLLMs) typically compress an entire WSI into a single embedding, which hinders fine-grained grounding and ignores how pathologists synthesize evidence across different scales. We introduce \textbf{MLLM-HWSI}, a Hierarchical WSI-level MLLM that aligns visual features with pathology language at four distinct scales, cell as word, patch as phrase, region as sentence, and WSI as paragraph to support interpretable evidence-grounded reasoning. MLLM-HWSI decomposes each WSI into multi-scale embeddings with scale-specific projectors and jointly enforces (i) a hierarchical contrastive objective and (ii) a cross-scale consistency loss, preserving semantic coherence from cells to the WSI. We compute diagnostically relevant patches and aggregate segmented cell embeddings into a compact cellular token per-patch using a lightweight \textit{Cell-Cell Attention Fusion (CCAF)} transformer. The projected multi-scale tokens are fused with text tokens and fed to an instruction-tuned LLM for open-ended reasoning, VQA, report, and caption generation tasks. Trained in three stages, MLLM-HWSI achieves new SOTA results on 13 WSI-level benchmarks across six CPath tasks. By aligning language with multi-scale visual evidence, MLLM-HWSI provides accurate, interpretable outputs that mirror diagnostic workflows and advance holistic WSI understanding. Code is available at: \href{https://github.com/BasitAlawode/HWSI-MLLM}{GitHub}.

♻ ☆ F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting

Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim

Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to redundant Gaussians across views. Moreover, they lack an effective mechanism to control the total number of Gaussians while maintaining reconstruction fidelity. To address these limitations, we present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting, introducing a densification-score-guided allocation strategy that adaptively distributes Gaussians according to spatial complexity and multi-view overlap. Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget without retraining. This spatially adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, producing compact yet high-quality 3D representations. Extensive experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods, while using significantly fewer Gaussians.

comment: Project Page: $\href{https://mlvlab.github.io/F4Splat}{\text{this http URL}}$

♻ ☆ WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation

Lianghui Zhu, Yingyue Li, Jiemin Fang, Yan Liu, Hao Xin, Wenyu Liu, Xinggang Wang

Transformer has been very successful in various computer vision tasks and understanding the working mechanism of transformer is important. As touchstones, weakly-supervised semantic segmentation (WSSS) and class activation map (CAM) are useful tasks for analyzing vision transformers (ViT). Based on the plain ViT pre-trained with ImageNet classification, we find that multi-layer, multi-head self-attention maps can provide rich and diverse information for weakly-supervised semantic segmentation and CAM generation, e.g., different attention heads of ViT focus on different image areas and object categories. Thus we propose a novel method to end-to-end estimate the importance of attention heads, where the self-attention maps are adaptively fused for high-quality CAM results that tend to have more complete objects. Besides, we propose a ViT-based gradient clipping decoder for online retraining with the CAM results efficiently and effectively. Furthermore, the gradient clipping decoder can make good use of the knowledge in large-scale pre-trained ViT and has a scalable ability. The proposed plain Transformer-based Weakly-supervised learning method (WeakTr) obtains the superior WSSS performance on standard benchmarks, i.e., 78.5% mIoU on the val set of PASCAL VOC 2012 and 51.1% mIoU on the val set of COCO 2014. Source code and checkpoints are available at https://github.com/hustvl/WeakTr.

comment: Accepted by IEEE Transactions on Image Processing, TIP. Source code and checkpoints are available at https://github.com/hustvl/WeakTr

♻ ☆ Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process

Jiayi Chen, Wenxuan Song, Pengxiang Ding, Ziyang Zhou, Han Zhao, Feilong Tang, Donglin Wang, Haoang Li

Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop, yielding unified VLAs that jointly understand, generate, and act -- reading text and images and producing future images and actions. However, these models either rely on external experts for modality unification or treat image generation and action prediction as separate processes, limiting the benefits of direct synergy between these tasks. Our core philosophy is to optimize generation and action jointly through a synchronous denoising process, where the iterative refinement enables actions to evolve from initialization, under constant and sufficient visual guidance. We ground this philosophy in our proposed Unified Diffusion VLA and Joint Discrete Denoising Diffusion Process (JD3P), which is a joint diffusion process that integrates multiple modalities into a single denoising trajectory to serve as the key mechanism enabling understanding, generation, and acting to be intrinsically synergistic. Our model and theory are built on a unified tokenized space of all modalities and a hybrid attention mechanism. We further propose a two-stage training pipeline and several inference-time techniques that optimize performance and efficiency. Our approach achieves state-of-the-art performance on benchmarks such as CALVIN, LIBERO, and SimplerEnv with 4$\times$ faster inference than autoregressive methods, and we demonstrate its effectiveness through in-depth analysis and real-world evaluations. Our project page is available at https://irpn-eai.github.io/UD-VLA.github.io/.

♻ ☆ Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach

Masashi Hatano, Saptarshi Sinha, Jacob Chalk, Wei-Hong Li, Hideo Saito, Dima Damen

Human motion generation is a challenging task that aims to create realistic motion imitating natural human behaviour. We focus on the well-studied behaviour of priming an object/location for pick up or put down - that is, the spotting of an object/location from a distance, known as gaze priming, followed by the motion of approaching and reaching the target location. To that end, we curate, for the first time, 23.7K gaze-primed human motion sequences for reaching target object locations from five publicly available datasets, i.e., HD-EPIC, MoGaze, HOT3D, ADT, and GIMO. We pre-train a text-conditioned diffusion-based motion generation model, then fine-tune it conditioned on goal pose or location, on our curated sequences. Importantly, we evaluate the ability of the generated motion to imitate natural human movement through several metrics, including the 'Reach Success' and a newly introduced 'Prime Success' metric. Tested on 5 datasets, our model generates diverse full-body motion, exhibiting both priming and reaching behaviour, and outperforming baselines and recent methods.

comment: Project Page: https://masashi-hatano.github.io/prime-and-reach/

♻ ☆ Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

Zhuo Li, Mingshuang Luo, Ruibing Hou, Xin Zhao, Hao Liu, Hong Chang, Zimo Liu, Chen Li

Human motion generation has been widely studied due to its crucial role in areas such as digital humans and humanoid robot control. However, many current motion generation approaches disregard physics constraints, frequently resulting in physically implausible motions with pronounced artifacts such as floating and foot sliding. Meanwhile, training an effective motion physics optimizer with noisy motion data remains largely unexplored. In this paper, we propose \textbf{Morph}, a \textbf{Mo}tion-F\textbf{r}ee \textbf{ph}ysics optimization framework, consisting of a Motion Generator and a Motion Physics Refinement module, for enhancing physical plausibility without relying on expensive real-world motion data. Specifically, the motion generator is responsible for providing large-scale synthetic, noisy motion data, while the motion physics refinement module utilizes these synthetic data to learn a motion imitator within a physics simulator, enforcing physical constraints to project the noisy motions into a physically-plausible space. Additionally, we introduce a prior reward module to enhance the stability of the physics optimization process and generate smoother and more stable motions. These physically refined motions are then used to fine-tune the motion generator, further enhancing its capability. This collaborative training paradigm enables mutual enhancement between the motion generator and the motion physics refinement module, significantly improving practicality and robustness in real-world applications. Experiments on both text-to-motion and music-to-dance generation tasks demonstrate that our framework achieves state-of-the-art motion quality while improving physical plausibility drastically. Project page: https://interestingzhuo.github.io/Morph-Page/.

comment: Accepted by ICCV 2025, 15 pages, 6 figures

♻ ☆ Natural Adversaries: Fuzzing Autonomous Vehicles with Realistic Roadside Object Placements

Yang Sun, Haoyu Wang, Christopher M. Poskitt, Jun Sun

The emergence of Autonomous Vehicles (AVs) has spurred research into testing the resilience of their perception systems, i.e., ensuring that they are not susceptible to critical misjudgements. It is important that these systems are tested not only with respect to other vehicles on the road, but also with respect to objects placed on the roadside. Trash bins, billboards, and greenery are examples of such objects, typically positioned according to guidelines developed for the human visual system, which may not align perfectly with the needs of AVs. Existing tests, however, usually focus on adversarial objects with conspicuous shapes or patches, which are ultimately unrealistic due to their unnatural appearance and reliance on white-box knowledge. In this work, we introduce a black-box attack on AV perception systems that creates realistic adversarial scenarios (i.e., satisfying road design guidelines) by manipulating the positions of common roadside objects and without resorting to "unnatural" adversarial patches. In particular, we propose TrashFuzz, a fuzzing algorithm that finds scenarios in which the placement of these objects leads to substantial AV misperceptions -- such as mistaking a traffic light's colour -- with the overall goal of causing traffic-law violations. To ensure realism, these scenarios must satisfy several rules encoding regulatory guidelines governing the placement of objects on public streets. We implemented and evaluated these attacks on the Apollo autonomous driving system, finding that TrashFuzz induced violations of 15 out of 24 traffic laws.

comment: Accepted by the 19th IEEE International Conference on Software Testing, Verification and Validation (ICST 2026)

♻ ☆ TopoSculpt: Betti-Steered Topological Sculpting of 3D Fine-grained Tubular Shapes

Minghui Zhang, Yaoyu Liu, Junyang Wu, Xin You, Hanxiao Zhang, Junjun He, Yun Gu

Medical tubular anatomical structures are inherently three-dimensional conduits with lumens, enclosing walls, and complex branching topologies. Accurate reconstruction of their geometry and topology is crucial for applications such as bronchoscopic navigation and cerebral arterial connectivity assessment. Existing methods often rely on voxel-wise overlap measures, which fail to capture topological correctness and completeness. Although topology-aware losses and persistent homology constraints have shown promise, they are usually applied patch-wise and cannot guarantee global preservation or correct geometric errors at inference. To address these limitations, we propose a novel TopoSculpt, a framework for topological refinement of 3D fine-grained tubular structures. TopoSculpt (i) adopts a holistic whole-region modeling strategy to capture full spatial context, (ii) first introduces a Topological Integrity Betti (TIB) constraint that jointly enforces Betti number priors and global integrity, and (iii) employs a curriculum refinement scheme with persistent homology to progressively correct errors from coarse to fine scales. Extensive experiments on challenging pulmonary airway and Circle of Willis datasets demonstrate substantial improvements in both geometry and topology. For instance, $β_{0}$ errors are reduced from 69.00 to 3.40 on the airway dataset and from 1.65 to 0.30 on the CoW dataset, with Tree length detected and branch detected rates improving by nearly 10\%. These results highlight the effectiveness of TopoSculpt in correcting critical topological errors and advancing the high-fidelity modeling of complex 3D tubular anatomy. The project homepage is available at: https://github.com/Puzzled-Hui/TopoSculpt.