Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Yang Liu, Xilin Zhao, Peisong Wen, Siran Dai, Qingming Huang
备注：
ICCV 2025 Physics-IQ Challenge Third Place Solution
Recent progress in video generation has led to impressive visual quality, yet current models still struggle to produce results that align with real-world physical principles. To this end, we propose an iterative self-refinement framework that leverages large language models and vision-language models to provide physics-aware guidance for video generation. Specifically, we introduce a multimodal chain-of-thought (MM-CoT) process that refines prompts based on feedback from physical inconsistencies, progressively enhancing generation quality. This method is training-free and plug-and-play, making it readily applicable to a wide range of video generation models. Experiments on the PhyIQ benchmark show that our method improves the Physics-IQ score from 56.31 to 62.38. We hope this work serves as a preliminary exploration of physics-consistent video generation and may offer insights for future research.
Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics
Institute for Language, Cognition and Computation, University of Edinburgh（语言、认知与计算研究所，爱丁堡大学）；Language Technology Lab, University of Cambridge（语言技术实验室，剑桥大学）；NVIDIA（NVIDIA公司）；University of Groningen（格罗宁根大学）
WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Models
Harbin Institute of Technology（哈尔滨工业大学）；Shandong University（山东大学）；Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Zhongguancun Academy（中关村学院）
Bootstrapping Vision-language Models for Self-supervised Remote Physiological Measurement
College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Shanghai Institute of Intelligent Science and Technology, Tongji University（同济大学上海智能科学与技术研究院）；School of Management, Hefei University of Technology（合肥工业大学管理学院）
Messages, Not Tokens: Grounded Coresets for Faithful VLM Compression
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Wuhan AI Research（武汉人工智能研究院）；Cardiff University（卡迪夫大学）
SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy
Department of Computer Science and Engineering, The American University in Cairo（美国亚历山大大学计算机科学与工程系）；Image And Visual Understanding Lab (IVUL), KAUST（卡塔尔大学图像与视觉理解实验室）
AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
Ant Group（蚂蚁集团）；University of Science and Technology of China（中国科学技术大学）；Westlake University（西湖大学）；University of Michigan - Ann Arbor（密歇根大学-安娜堡分校）；Sun Yat-sen University（中山大学）
Think Proprioceptively: State-Grounded Visual Token Selection for VLA Policies
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute of Technology（东区技术研究所）；Great Bay University（大湾大学）；Northeast Forestry University（东北林业大学）；National University of Singapore（新加坡国立大学）
RAPTOR+: A Visually Grounded Vision-Language Framework to Improve Clinical Trust and Auditability in Automated Cancer Referral Processing
Birmingham City University（伯明翰城市大学）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；University Hospitals Birmingham NHS Foundation Trust（伯明翰大学医院 NHS 基础信托）；NHS England（英格兰国家卫生服务体系）
Which Way Does Time Flow? A Psychophysics-Grounded Evaluation for Vision-Language Models
Kyoto University（京都大学）；Center for Information and Neural Networks（信息与神经网络中心）；National Institute of Information and Communications Technology（国立信息通信技术研究所）；The University of Osaka（大阪大学）
Watch Before You Answer: Learning from Visually Grounded Post-Training
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute（向量研究所）；Etude AI；Kolors Team, Kuaishou Technology（快手科技Kolors团队）；University of Toronto（多伦多大学）；University of Waterloo（滑铁卢大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
