Xiaoben Li, Jingyi Wu, Zeyu Cai, Yu Siyuan, Boqian Li, Yuliang Xiu: ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Datasets https://arxiv.org/abs/2604.08548 https://arxiv.org/pdf/2604.08548 https://arxiv.org/html/2604.08548

Jiaxin Wang, Dongxin Lyu, Zeyu Cai, Zhiyang Dou, Cheng Lin, Anpei Chen, Yuliang Xiu: GaussiAnimate: Reconstruct and Rig Animatable Categories with Level of Dynamics https://arxiv.org/abs/2604.08547 https://arxiv.org/pdf/2604.08547 https://arxiv.org/html/2604.08547

Zhengyang Sun, Yu Chen, Xin Zhou, Xiaofan Li, Xiwu Chen, Dingkang Liang, Xiang Bai: When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models https://arxiv.org/abs/2604.08546 https://arxiv.org/pdf/2604.08546 https://arxiv.org/html/2604.08546

Shilin Yan, Jintao Tong, Hongwei Xue, Xiaojun Tang, Yangyang Wang, Kunyu Shi, Guannan Zhang, Ruixuan Li, Yixiong Zou: Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models https://arxiv.org/abs/2604.08545 https://arxiv.org/pdf/2604.08545 https://arxiv.org/html/2604.08545

Mayur Deshmukh, Hiroyasu Akada, Helge Rhodin, Christian Theobalt, Vladislav Golyanik: E-3DPSM: A State Machine for Event-Based Egocentric 3D Human Pose Estimation https://arxiv.org/abs/2604.08543 https://arxiv.org/pdf/2604.08543 https://arxiv.org/html/2604.08543

Xie, Yang, Jin, Cai, Yin, Ren, Zhang, Hua, Peng, Guo, Zhou: Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction https://arxiv.org/abs/2604.08542 https://arxiv.org/pdf/2604.08542 https://arxiv.org/html/2604.08542

Xu, Hong, Li, Zhou, Zhang, Huang, Xue, Shen, Lu, Zhuang: Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts https://arxiv.org/abs/2604.08541 https://arxiv.org/pdf/2604.08541 https://arxiv.org/html/2604.08541

Zhou, Lai, Wang, Yang, Xing, Yang, Dai, Qiu, Luo: AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation https://arxiv.org/abs/2604.08540 https://arxiv.org/pdf/2604.08540 https://arxiv.org/html/2604.08540

Wenbo Hu, Xin Chen, Yan Gao-Tian, Yihe Deng, Nanyun Peng, Kai-Wei Chang: OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks https://arxiv.org/abs/2604.08539 https://arxiv.org/pdf/2604.08539 https://arxiv.org/html/2604.08539

Boyang Zhang, Sebasti\'an G. Acosta, Preston Carlson, Sacha Bron, Pierre-Lo\"ic Doulcet, Simon Suo: ParseBench: A Document Parsing Benchmark for AI Agents https://arxiv.org/abs/2604.08538 https://arxiv.org/pdf/2604.08538 https://arxiv.org/html/2604.08538

Susladkar, Jang, Prakash, Juvekar, Shah, Barik, Bashir, Wahed, Shrirao, Lourentzou: RewardFlow: Generate Images by Optimizing What You Reward https://arxiv.org/abs/2604.08536 https://arxiv.org/pdf/2604.08536 https://arxiv.org/html/2604.08536

Nan Huang, Pengcheng Yu, Weijia Zeng, James M. Rehg, Angjoo Kanazawa, Haiwen Feng, Qianqian Wang: Self-Improving 4D Perception via Self-Distillation https://arxiv.org/abs/2604.08532 https://arxiv.org/pdf/2604.08532 https://arxiv.org/html/2604.08532

Johanna Karras, Yuanhao Wang, Yingwei Li, Ira Kemelmacher-Shlizerman: FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On https://arxiv.org/abs/2604.08526 https://arxiv.org/pdf/2604.08526 https://arxiv.org/html/2604.08526

Joungbin An, Agrim Jain, Kristen Grauman: UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding https://arxiv.org/abs/2604.08522 https://arxiv.org/pdf/2604.08522 https://arxiv.org/html/2604.08522

Gupta, Wolters, Ma, Sushko, Pang, Llanes, Yang, Anderson, Zheng, Ren, Trivedi, Blanton, Ouellette, Han, Farhadi, Krishna: MolmoWeb: Open Visual Web Agent and Open Data for the Open Web https://arxiv.org/abs/2604.08516 https://arxiv.org/pdf/2604.08516 https://arxiv.org/html/2604.08516

Kabilan Elangovan, Daniel Ting: When Fine-Tuning Changes the Evidence: Architecture-Dependent Semantic Drift in Chest X-Ray Explanations https://arxiv.org/abs/2604.08513 https://arxiv.org/pdf/2604.08513 https://arxiv.org/html/2604.08513

Hang Ye, Xiaoxuan Ma, Fan Lu, Wayne Wu, Kwan-Yee Lin, Yizhou Wang: Visually-grounded Humanoid Agents https://arxiv.org/abs/2604.08509 https://arxiv.org/pdf/2604.08509 https://arxiv.org/html/2604.08509

Ying Shen, Jerry Xiong, Tianjiao Yu, Ismini Lourentzou: Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics https://arxiv.org/abs/2604.08503 https://arxiv.org/pdf/2604.08503 https://arxiv.org/html/2604.08503

Kabilan Elangovan, Daniel Ting: Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification https://arxiv.org/abs/2604.08502 https://arxiv.org/pdf/2604.08502 https://arxiv.org/html/2604.08502

Qi Wu, Khiem Vuong, Minsik Jeon, Srinivasa Narasimhan, Deva Ramanan: Novel View Synthesis as Video Completion https://arxiv.org/abs/2604.08500 https://arxiv.org/pdf/2604.08500 https://arxiv.org/html/2604.08500

Mohamed Amine Kerkouri, Marouane Tliba, Bin Wang, Aladine Chetouani, Ulas Bagci, Alessandro Bruno: What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metric https://arxiv.org/abs/2604.08494 https://arxiv.org/pdf/2604.08494 https://arxiv.org/html/2604.08494

Kancheti, Kanade, Sinha, Balasubramanian, Ganu: Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization https://arxiv.org/abs/2604.08476 https://arxiv.org/pdf/2604.08476 https://arxiv.org/html/2604.08476

Jingjing Wang, Zhengdong Hong, Chong Bao, Yuke Zhu, Junhan Sun, Guofeng Zhang: LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation https://arxiv.org/abs/2604.08475 https://arxiv.org/pdf/2604.08475 https://arxiv.org/html/2604.08475

Zeng, Liu, Bin, Zhang, Ding, Wang, Ouyang, Shen: OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance https://arxiv.org/abs/2604.08461 https://arxiv.org/pdf/2604.08461 https://arxiv.org/html/2604.08461

Rui Gan, Junyi Ma, Pei Li, Xingyou Yang, Kai Chen, Sikai Chen, Bin Ran: CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning https://arxiv.org/abs/2604.08457 https://arxiv.org/pdf/2604.08457 https://arxiv.org/html/2604.08457

Marcel Gr\"opl, Jaewoo Jung, Seungryong Kim, Marc Pollefeys, Sunghwan Hong: Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models https://arxiv.org/abs/2604.08456 https://arxiv.org/pdf/2604.08456 https://arxiv.org/html/2604.08456

Changdao Chen: HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessment https://arxiv.org/abs/2604.08435 https://arxiv.org/pdf/2604.08435 https://arxiv.org/html/2604.08435

Fan Yang, Wenrui Chen, Guorun Yan, Ruize Liao, Wanjun Jia, Dongsheng Luo, Kailun Yang, Zhiyong Li, Yaonan Wang: BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields https://arxiv.org/abs/2604.08410 https://arxiv.org/pdf/2604.08410 https://arxiv.org/html/2604.08410

Wenli Zhang, Xianglong Shi, Sirui Zhao, Xinqi Chen, Guo Cheng, Yifan Xu, Tong Xu, Yong Liao: SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation https://arxiv.org/abs/2604.08405 https://arxiv.org/pdf/2604.08405 https://arxiv.org/html/2604.08405

Nam Duong Tran, Phi Le Nguyen: Phantasia: Context-Adaptive Backdoors in Vision Language Models https://arxiv.org/abs/2604.08395 https://arxiv.org/pdf/2604.08395 https://arxiv.org/html/2604.08395

Chensheng Dai, Shengjun Zhang, Min Chen, Yueqi Duan: SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction https://arxiv.org/abs/2604.08370 https://arxiv.org/pdf/2604.08370 https://arxiv.org/html/2604.08370

Gao, Liu, Li, Sun, Tu, Shen, Zhang, Zhao, Zhang: MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping https://arxiv.org/abs/2604.08364 https://arxiv.org/pdf/2604.08364 https://arxiv.org/html/2604.08364

Ruizhi Zhang, Ye Huang, Yuangang Pan, Chuanfu Shen, Zhilin Liu, Ting Xie, Wen Li, Lixin Duan: PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models https://arxiv.org/abs/2604.08340 https://arxiv.org/pdf/2604.08340 https://arxiv.org/html/2604.08340

Kumar, Saini, Pan, Erdogan, Zhang, Le Dem, Kobori, Kong: InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding https://arxiv.org/abs/2604.08337 https://arxiv.org/pdf/2604.08337 https://arxiv.org/html/2604.08337

Zhu, Mo, Chen, Zheng, Yang, Shi, Gao, Li, Wu: Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification https://arxiv.org/abs/2604.08333 https://arxiv.org/pdf/2604.08333 https://arxiv.org/html/2604.08333

Deng, Wei, Qian, Liu, Xin, Lan, Liu, Dong, Li: Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data https://arxiv.org/abs/2604.08322 https://arxiv.org/pdf/2604.08322 https://arxiv.org/html/2604.08322

Richard Petersen, Fredrik Kahl, Jennifer Alv\'en: Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow https://arxiv.org/abs/2604.08313 https://arxiv.org/pdf/2604.08313 https://arxiv.org/html/2604.08313

Liu, Chen, Zhao, Bao, Tian, Zhang, Chen, Zhi, Liu, Li, Cao: GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis https://arxiv.org/abs/2604.08301 https://arxiv.org/pdf/2604.08301 https://arxiv.org/html/2604.08301

Miguel Monte e Freitas, Rui Henriques, Ricardo Rei, Pedro Henrique Martins: Can Vision Language Models Judge Action Quality? An Empirical Evaluation https://arxiv.org/abs/2604.08294 https://arxiv.org/pdf/2604.08294 https://arxiv.org/html/2604.08294

Siyuan Yao, Hao Sun, Ruiqi Yu, Xiwei Jiang, Wenqi Ren, Xiaochun Cao: CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild https://arxiv.org/abs/2604.08287 https://arxiv.org/pdf/2604.08287 https://arxiv.org/html/2604.08287

Hamza Alsharif, Jing Gu, Pavol Jancura, Satish Ravindran, Gijs Dubbelman: Revisiting Radar Perception With Spectral Point Clouds https://arxiv.org/abs/2604.08282 https://arxiv.org/pdf/2604.08282 https://arxiv.org/html/2604.08282

Panagiotis Gkotsis, Athanasios A. Rontogiannis: Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising https://arxiv.org/abs/2604.08272 https://arxiv.org/pdf/2604.08272 https://arxiv.org/html/2604.08272

Jing Gu, Niccol\`o Cavagnero, Gijs Dubbelman: Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models https://arxiv.org/abs/2604.08266 https://arxiv.org/pdf/2604.08266 https://arxiv.org/html/2604.08266

Jiangbei Yue, Sharib Ali: DBMF: A Dual-Branch Multimodal Framework for Out-of-Distribution Detection https://arxiv.org/abs/2604.08261 https://arxiv.org/pdf/2604.08261 https://arxiv.org/html/2604.08261

Devalapally, Jain, Srinivas, Balasubramanian: $\oslash$ Source Models Leak What They Shouldn't $\nrightarrow$: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization https://arxiv.org/abs/2604.08238 https://arxiv.org/pdf/2604.08238 https://arxiv.org/html/2604.08238

Saniya M. Deshmukh, Kailash A. Hambarde, Hugo Proen\c{c}a: Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges https://arxiv.org/abs/2604.08230 https://arxiv.org/pdf/2604.08230 https://arxiv.org/html/2604.08230

Wang, Cai, Bai, Zhou, Chen, Hu, Tang, Chen, Zhu: EditCaption: Human-Aligned Instruction Synthesis for Image Editing via Supervised Fine-Tuning and Direct Preference Optimization https://arxiv.org/abs/2604.08213 https://arxiv.org/pdf/2604.08213 https://arxiv.org/html/2604.08213

Blessing Agyei Kyem, Joshua Kofi Asamoah, Anthony Dontoh, Armstrong Aboah: Vision-Language Foundation Models for Comprehensive Automated Pavement Condition Assessment https://arxiv.org/abs/2604.08212 https://arxiv.org/pdf/2604.08212 https://arxiv.org/html/2604.08212

You Hu, Chenzhuo Zhao, Changfa Mo, Haotian Liu, Xiaobai Li: SciFigDetect: A Benchmark for AI-Generated Scientific Figure Detection https://arxiv.org/abs/2604.08211 https://arxiv.org/pdf/2604.08211 https://arxiv.org/html/2604.08211

Yiduo Jia, Muzhi Zhu, Hao Zhong, Mingyu Liu, Yuling Xi, Hao Chen, Bin Qin, Yongjie Yang, Zhenbo Luo, Chunhua Shen: OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering https://arxiv.org/abs/2604.08209 https://arxiv.org/pdf/2604.08209 https://arxiv.org/html/2604.08209