Guangzhao He, Rundong Luo, Wei-Chiu Ma, Hadar Averbuch-Elor: Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models https://arxiv.org/abs/2606.02580 https://arxiv.org/pdf/2606.02580 https://arxiv.org/html/2606.02580

Seojeong Park, Jiho Choi, Junyong Kang, Seonho Lee, Jaeyo Shin, Hyunjung Shim: Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling https://arxiv.org/abs/2606.02578 https://arxiv.org/pdf/2606.02578 https://arxiv.org/html/2606.02578

Yu-Cheng Shi, Zhen-Hao Xie, Jun-Tao Tang, Da-Wei Zhou: ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning https://arxiv.org/abs/2606.02576 https://arxiv.org/pdf/2606.02576 https://arxiv.org/html/2606.02576

Kiymet Akdemir, Pinar Yanardag: From Zero to Hero: Training-Free Custom Concept Spawning in World Models https://arxiv.org/abs/2606.02575 https://arxiv.org/pdf/2606.02575 https://arxiv.org/html/2606.02575

Hu, Zhao, Guo, Jiang, Liu, Fan, Wang, Wang, Pavlakos: HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image https://arxiv.org/abs/2606.02573 https://arxiv.org/pdf/2606.02573 https://arxiv.org/html/2606.02573

Haiyu Wu, Randall Balestriero, Morgan Levine: VISReg: Variance-Invariance-Sketching Regularization for JEPA training https://arxiv.org/abs/2606.02572 https://arxiv.org/pdf/2606.02572 https://arxiv.org/html/2606.02572

Haowen Hou, Zhen Huang, Zheming Liang, Qingyi Si, Chenglin Li, Shuai Dong, Kele Shao, Ruilin Li, Dianyi Wang, Nan Duan, Jiaqi Wang: AdaCodec: A Predictive Visual Code for Video MLLMs https://arxiv.org/abs/2606.02569 https://arxiv.org/pdf/2606.02569 https://arxiv.org/html/2606.02569

Howard Xiao, Jan Ackermann, Boyang Deng, Gordon Wetzstein: Policy-based Foveated Imaging and Perception https://arxiv.org/abs/2606.02565 https://arxiv.org/pdf/2606.02565 https://arxiv.org/html/2606.02565

Junhao Cheng, Liang Hou, Tianxiong Zhong, Xin Tao, Pengfei Wan, Kun Gai, Jing Liao: VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization https://arxiv.org/abs/2606.02564 https://arxiv.org/pdf/2606.02564 https://arxiv.org/html/2606.02564

Qixin Hu, Shuai Yang, Wei Huang, Song Han, Yukang Chen: LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation https://arxiv.org/abs/2606.02553 https://arxiv.org/pdf/2606.02553 https://arxiv.org/html/2606.02553

Siyuan Bian, Congrong Xu, Jun Gao: Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation https://arxiv.org/abs/2606.02552 https://arxiv.org/pdf/2606.02552 https://arxiv.org/html/2606.02552

Liu, Duan, Zhu, Lu, Jiang, Yang, Hu, Zhai, Zhang: LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models https://arxiv.org/abs/2606.02535 https://arxiv.org/pdf/2606.02535 https://arxiv.org/html/2606.02535

Li, Liu, Jacobs, Annamareddy, Polak, Field, Szlufarska, Morgan: Improving Combined Detection and Classification of TEM Defects via Mask-Conditioned Latent Diffusion Augmentation https://arxiv.org/abs/2606.02532 https://arxiv.org/pdf/2606.02532 https://arxiv.org/html/2606.02532

Shuo Zhang, Chenqi Li, Tingting Zhu: Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition https://arxiv.org/abs/2606.02526 https://arxiv.org/pdf/2606.02526 https://arxiv.org/html/2606.02526

Liu, Zhu, Zhao, Wang, Li, Li, Cao, Sun, Zhang, Yang, Zhong, Yang: Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events https://arxiv.org/abs/2606.02522 https://arxiv.org/pdf/2606.02522 https://arxiv.org/html/2606.02522

Yu Xue, Haoxuan Qu, Zhuoling Li, Yihang Lou, Yan Bai, Hossein Rahmani, Jun Liu: ToolFG: Towards Well-Grounded Fine-Grained Image Classification https://arxiv.org/abs/2606.02518 https://arxiv.org/pdf/2606.02518 https://arxiv.org/html/2606.02518

Xiang Xu, Alan Liang, Youquan Liu, Xian Sun, Linfeng Li, Lingdong Kong, Ziwei Liu, Qingshan Liu: Not All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis https://arxiv.org/abs/2606.02510 https://arxiv.org/pdf/2606.02510 https://arxiv.org/html/2606.02510

Yilin Ou, Mengshi Qi, Huadong Ma: Question-Aware Evidence Ledgers for Video Relational Reasoning https://arxiv.org/abs/2606.02506 https://arxiv.org/pdf/2606.02506 https://arxiv.org/html/2606.02506

Yuan, Lu, Zhang, Wu, Wang, Wang, Sun, Guo: GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction https://arxiv.org/abs/2606.02498 https://arxiv.org/pdf/2606.02498 https://arxiv.org/html/2606.02498

Minkyung Kwon, Jinhyeok Choi, Youngjin Shin, Jaeyeong Kim, JongMin Lee, Seungryong Kim: MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents https://arxiv.org/abs/2606.02491 https://arxiv.org/pdf/2606.02491 https://arxiv.org/html/2606.02491

Sun, Lu, Liu, Bo, Wu, Guan, Cai, Chen, Guo, Li, Liu, Yue: X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding https://arxiv.org/abs/2606.02482 https://arxiv.org/pdf/2606.02482 https://arxiv.org/html/2606.02482

Michelle R. Greene: Places in the Wild: A Large, High-Resolution RAW Photograph Dataset for Ecologically Valid Vision Research https://arxiv.org/abs/2606.02481 https://arxiv.org/pdf/2606.02481 https://arxiv.org/html/2606.02481

Minseok Joo, Dogyun Park, Taehoon Lee, Kyujin Lee, Hyunwoo J. Kim: Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation https://arxiv.org/abs/2606.02479 https://arxiv.org/pdf/2606.02479 https://arxiv.org/html/2606.02479

Hilton Raj, Vishnuram AV: MASER: Modality-Adaptive Specialist Routing for Embodied 3D Spatial Intelligence https://arxiv.org/abs/2606.02463 https://arxiv.org/pdf/2606.02463 https://arxiv.org/html/2606.02463

Wei Deng, Xianlin Zhang, Mengshi Qi: Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models https://arxiv.org/abs/2606.02459 https://arxiv.org/pdf/2606.02459 https://arxiv.org/html/2606.02459

Xiang Li, Dianbo Liu, Kenji Kawaguchi: Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior https://arxiv.org/abs/2606.02453 https://arxiv.org/pdf/2606.02453 https://arxiv.org/html/2606.02453

DongQing Liu, MengShi Qi, HongWei Ji: Reason-Then-Retrieve for CoVR-R with Structured Edit Prompts and Dense-Sparse Fusion https://arxiv.org/abs/2606.02450 https://arxiv.org/pdf/2606.02450 https://arxiv.org/html/2606.02450

Yuheng Chen, Teng Hu, Yuji Wang, Qingdong He, Lizhuang Ma, Jiangning Zhang: Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation https://arxiv.org/abs/2606.02441 https://arxiv.org/pdf/2606.02441 https://arxiv.org/html/2606.02441

Zhengxuan Wei, Xu Guo, Xinghui Li, Xunzhi Xiang, Min Wei, Yiran Zhu, Qiulin Wang, Xintao Wang, Pengfei Wan, Xiangwang Hou, Qi Fan: Geometry-Aware Implicit Memory for Video World Models https://arxiv.org/abs/2606.02436 https://arxiv.org/pdf/2606.02436 https://arxiv.org/html/2606.02436

Shiku, Abbasi, Bise, Iwashita, Nishimura, Dengel, Asim: GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial Transcriptomics https://arxiv.org/abs/2606.02424 https://arxiv.org/pdf/2606.02424 https://arxiv.org/html/2606.02424

Gustav Hanning, Ludvig Dill\'en, Jonathan Astermark, Johanna Lidholm, Viktor Larsson: Edge Prediction for Roof Wireframe Reconstruction with Transformers https://arxiv.org/abs/2606.02406 https://arxiv.org/pdf/2606.02406 https://arxiv.org/html/2606.02406

Feng, Li, Lu, Ji, Zhang, Shen, Li, Jia, Chen, Wang, Li, Qin: Explainable Forensics of Manipulated Segments in Untrimmed Long Videos https://arxiv.org/abs/2606.02402 https://arxiv.org/pdf/2606.02402 https://arxiv.org/html/2606.02402

Yuanbo Xiangli, Hanyu Chen, Xueqing Tsang, Noah Snavely: Honey, I Shrunk the Arc de Triomphe! https://arxiv.org/abs/2606.02379 https://arxiv.org/pdf/2606.02379 https://arxiv.org/html/2606.02379

Xiaohang Yu, Ti Wang, Mackenzie Weygandt Mathis: PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation https://arxiv.org/abs/2606.02366 https://arxiv.org/pdf/2606.02366 https://arxiv.org/html/2606.02366

Guo, Yu, Chen, Wang, Li, Zhao, Liu, Wang, Liao: Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains https://arxiv.org/abs/2606.02357 https://arxiv.org/pdf/2606.02357 https://arxiv.org/html/2606.02357

Lerch, Majer, Zhong, Martin, Diederichs, Stiefelhagen: Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection https://arxiv.org/abs/2606.02352 https://arxiv.org/pdf/2606.02352 https://arxiv.org/html/2606.02352

Jinpeng Liu, Yukang Xu, Yutong Li, Xingyu Liu: TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos https://arxiv.org/abs/2606.02350 https://arxiv.org/pdf/2606.02350 https://arxiv.org/html/2606.02350

Aoduo Li, Jiancheng Li, Huan Ye, Hongjian Xu, Shiting Wu, Xiujun Zhang, Zimeng Li, Xuhang Chen: VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning https://arxiv.org/abs/2606.02346 https://arxiv.org/pdf/2606.02346 https://arxiv.org/html/2606.02346

Lauren Sismeiro, Remy Plastre, Binbin Xu, Frederic Puyjarinet, Gerard Dray: Detecting Pen-In-Air States from Video: A Proof-of-Concept Toward Complementary Handwriting Analysis https://arxiv.org/abs/2606.02342 https://arxiv.org/pdf/2606.02342 https://arxiv.org/html/2606.02342

Pengfei Jin, Yiqi Tian, Kailong Fan, Bingjie Qi, Quanzheng Li: Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates https://arxiv.org/abs/2606.02331 https://arxiv.org/pdf/2606.02331 https://arxiv.org/html/2606.02331

Yang Liu, Qianqian Xu, Peisong Wen, Siran Dai, Qingming Huang: Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning https://arxiv.org/abs/2606.02321 https://arxiv.org/pdf/2606.02321 https://arxiv.org/html/2606.02321

Yogesh Bhattarai, Vijay Chaudhary, Wai Lim Kim, Sanjib Sharma: Deep Learning for Remote Sensing to Improve Flood Inundation Mapping https://arxiv.org/abs/2606.02310 https://arxiv.org/pdf/2606.02310 https://arxiv.org/html/2606.02310

Anis Ur Rahman, Mete Ahishali, Einari Heinaro, Samuli Junttila: Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial Imagery https://arxiv.org/abs/2606.02303 https://arxiv.org/pdf/2606.02303 https://arxiv.org/html/2606.02303

Arjun Majumdar, Raphael Braun, Hendrik Lensch: Neural Acquisition & Representation of Subsurface Scattering https://arxiv.org/abs/2606.02292 https://arxiv.org/pdf/2606.02292 https://arxiv.org/html/2606.02292

Soroosh Tayebi Arasteh, Mahshad Lotfinia, Sven Nebelung, Daniel Truhn: Cross-modal linkage risk in clinical vision-language models https://arxiv.org/abs/2606.02276 https://arxiv.org/pdf/2606.02276 https://arxiv.org/html/2606.02276

David J. Lerch, Sarath Mulugurthi, Manuel Martin, Frederik Diederichs, Rainer Stiefelhagen: Vision-language Models for Driver Monitoring Systems: A Driver Activity Description Dataset https://arxiv.org/abs/2606.02273 https://arxiv.org/pdf/2606.02273 https://arxiv.org/html/2606.02273

Yuming Zhao, Junhui Hou, Qijian Zhang, Jia Qin, Ying He: From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data https://arxiv.org/abs/2606.02268 https://arxiv.org/pdf/2606.02268 https://arxiv.org/html/2606.02268

Santos-Villafranca, Bermudez-cameo, Perez-Yus, Farinella, Furnari: Ego-METAS: Egocentric online Multimodal Energy-efficient Temporal Action Segmentation benchmark https://arxiv.org/abs/2606.02246 https://arxiv.org/pdf/2606.02246 https://arxiv.org/html/2606.02246

Karina Kvanchiani, Timur Mamedov: Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identification https://arxiv.org/abs/2606.02242 https://arxiv.org/pdf/2606.02242 https://arxiv.org/html/2606.02242

Lea Uhlenbrock, Davide Cozzolino, Christian Riess: Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images https://arxiv.org/abs/2606.02224 https://arxiv.org/pdf/2606.02224 https://arxiv.org/html/2606.02224