Physical Consistency in Video Generation

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 229% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 134

All topics

STRIKE: Learning Visual State Transitions for Physical World Modeling
Oct 7, 2026Wenbin Teng, Tianshuo Xu, Depu Meng +5World Models Video World Models
Applied Intuition · University of Southern California · University of California, Berkeley
RobotAPO: Adversarial Physics Preference Optimization for Robotic Manipulation Video Generation
Oct 7, 2026Kerui Li, Zhe Jing, Chenyi Huang +4Physical Consistency in Video Generation Robotic Manipulation
Institute of Automation, Chinese Academy of Sciences · GigaAI · Beijing Institute of Technology
World Models' Last Exam in Physics
Oct 6, 2026Mingju Gao, Qingle Liu, Yuzhao Peng +8Physical Consistency in Video Generation World Model Evaluation
Navers Lab, Einsia.AI · Peking University · Tsinghua University
S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
Oct 5, 2026Jeffrey Hu, Daniel Olmeda Reino, Ayush TewariPhysical Consistency in Video Generation Video Diffusion Models
University of Cambridge · Toyota Motor Europe
How Does Geometry Enter Generated Motion?
Oct 4, 2026Weihan Li, Junhao Wu, Yuhan Song +2Physical Consistency in Video Generation Image-to-Video Generation
The University of Tokyo · RWTH Aachen University · Harbin Institute of Technology, Shenzhen
HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation
Oct 1, 2026Tahira Kazimi, Shubhankar Borse, Munawar Hayat +2Physics-Informed Generative Modeling Physical Consistency in Video Generation
Virginia Tech · Qualcomm AI Research
PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation Models
Oct 1, 2026Isaiah Milkey, Som Sagar, Aditya Taparia +3Physical Consistency in Video Generation Physical Reasoning in Video
School of Computing and Augmented Intelligence Arizona State University Tempe, AZ, USA
Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation
Oct 1, 2026Patrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana +10Physical Consistency in Video Generation Robot Manipulation Benchmarks
Mohamed bin Zayed University of Artificial Intelligence · Independent Researcher · Nanyang Technological University +1
Bootstrapping Video Interaction Generation with Synthetic State Transitions
Oct 1, 2026Jiho Jang, Jinyoung Kim, Nojun Kwak +1Physical Consistency in Video Generation Synthetic Data Generation for Robotics
Seoul National University · Independent Researcher · Sejong University
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Sep 30, 2026Xinge Peng, Yiting Lu, Tianwu Zhi +4VLM Evaluation Physical Consistency in Video Generation
University of Science and Technology of China · ByteDance · City University of Hong Kong
Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model
Sep 30, 2026Liming Lu, Xianzheng Ma, Wenkun He +14Physical Consistency in Video Generation Video Captioning
MIT · University of Oxford · NVIDIA
VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning
Sep 30, 2026Zehua Ma, Kun Xiang, Yunshuang Nie +9Contrastive Learning Physical Consistency in Video Generation
Shenzhen Campus of Sun Yat-sen University · Tsinghua Shenzhen International Graduate School · Shenzhen Loop Area Institute +3
PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos
Sep 29, 2026Max Ku, Jiaojiao Fan, Zekun Hao +5Physical Consistency in Video Generation Video Quality Assessment
NVIDIA · University of Waterloo · Vector Institute
FracGen: Learning How Objects Stretch and Tear with Physics-Informed Video Generation
Sep 29, 2026Trong-Tung Nguyen, Jiahan Zhang, Anand BhattadPhysics-Informed Generative Modeling Physical Consistency in Video Generation
Johns Hopkins University
MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos
Sep 29, 2026Jiahao Zhan, Yongrui Ma, Qunliang Xing +6Physical Consistency in Video Generation Video Quality Assessment
Foresight at the Event Boundary: Evaluating Physical Prediction in Video World Models
Sep 29, 2026Estela Monserrat Arriaga Santana, Julian Rosas Scull, Ehécatl Sacamch'en Núñez Rico +1Physical Consistency in Video Generation World Model Evaluation
National Autonomous University of Mexico · National Autonomous University of Mexico, Mexico · University of Texas at El Paso +1
VideoPhysEdit: Physical Counterfactual Video Editing via Rigid-Body Physical Scene Reconstruction
Sep 28, 2026Conghan Yue, Yuanjie Chen, Yue Han +4Physical Consistency in Video Generation Video Editing
Institute of Trustworthy Embodied AI, Fudan University
VehDyn: A Driving World Model Benchmark for Vehicle Dynamics
Sep 27, 2026Tianyi Wang, Wangsheng Du, Jiazhou Chen +12Autonomous Driving Benchmarks Physical Consistency in Video Generation
Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms
Sep 20, 2026Yueyan Li, Haibo Wang, Caixia Yuan +1Rotary Positional Embeddings Physical Consistency in Video Generation
Beijing University of Posts and Telecommunications
CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation
Sep 18, 2026Haoran Qin, Renlong Wu, Tianyu Huang +3Physical Consistency in Video Generation Text-to-Video Generation
Harbin Institute of Technology, China · Taobao, Alibaba Group, China
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
Sep 15, 2026Chuhao Chen, Peter Wonka, Chaoyang Wang +4Physical Consistency in Video Generation Image-to-Video Generation
University of Pennsylvania, Philadelphia, USA · Snap Inc., Santa Monica, USA · KAUST, Thuwal, Saudi Arabia
A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models
Sep 14, 2026Xingyun Wang, Haomin Zheng, Man Yuan +2Physical Consistency in Video Generation
Tsinghua University · MetaCircle · Peking University +2
One Model, Two Physical Stories: Auditing Misalignment in Multi-Modal World Modeling
Sep 13, 2026Geigh Zollicoffer, Minh Vu, Rajiv Ranasinghe +1Physical Consistency in Video Generation World Model Learning
1Theoretical Division, Los Alamos National Laboratory · 2Computing and Artificial Intelligence Division, Los Alamos National Laboratory · 3Earth and Environmental Sciences Division, Los Alamos National Laboratory
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
Sep 12, 2026Yilin Long, Chenming Zhu, Zitang Gou +2Physical Consistency in Video Generation Camera-Controlled Video Generation
Shanghai AI Laboratory · Fudan University · The University of Hong Kong +1
VeriScene: Reconstructing Crime Scenes from Legal Evidence via World-Model Agent
Sep 8, 2026Kevin Chuanpu Fu, Yongsen Zheng, Zee Kin Yeong +1Physical Consistency in Video Generation Digital Forensics
Nanyang Technological University, Singapore · Singapore Academy of Law, Singapore
PhysFlow: Physics-Aware Optical Flow for Motion Controllable Video Generation
Sep 8, 2026Cong Wang, Hanxin Zhu, Yonglin Tian +5Optical Flow Physical Consistency in Video Generation
State Key Laboratory of Multi-modal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · Zhongguancun Academy, Beijing 100094, China +2
SynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation
Sep 8, 2026Soroush Mehraban, Xin Lei Lin, Vida Adeli +5Synthetic-to-Real Domain Adaptation Physical Consistency in Video Generation
1KITE Research Institute · University of Toronto · 3Vector Institute +2
Principia: Relational Physics Tests for Video Models
Sep 3, 2026Varun Varma Thozhiyoor, Shivam Tripathi, Venkatesh Babu Radhakrishnan +1VLM Evaluation Physical Consistency in Video Generation
Indian Institute of Science · Johns Hopkins University
VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement
Sep 2, 2026Wenzhuo Xu, Yuchen Zhu, Chongjian Ge +8Physical Consistency in Video Generation LLM Agent Verification
1Carnegie Mellon University · 2Georgia Institute of Technology · 4Adobe Research +1
Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning
Sep 1, 2026Zixuan Wang, Yixin Hu, Wen Li +4Physical Consistency in Video Generation Video Diffusion Models
College of Electronics and Information Engineering, Sichuan University, Chengdu, 610064, China · School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731 · School of Computer Science, University of Adelaide, 5005, Adelaide, Australia +2

Oct 7, 2026, cs.CVJ/K move · Enter open · S save

STRIKE: Learning Visual State Transitions for Physical World Modeling

Wenbin Teng, Tianshuo Xu, Depu Meng, Yuelei Li+4

Applied Intuition · University of Southern California · University of California, Berkeley

World Models Video World Models Physical Consistency in Video Generation

Open paper AskPDF arXiv

Physical world modeling requires predicting how interactions change a scene, not merely generating coherent motion. We propose STRIKE, a framework that separates visual state transition learning from dense video generation. We construct event-aligned supervision by extracting observed states from training videos and pairing them with transition descriptions and temporal offsets. An image-based transition model learns to predict the next scene configuration from the current image, a local transition specification, and elapsed time. At inference, a pretrained vision-language planner predicts time transition specifications, and recursive application of the learned transition model produces a sequence of future visual states. A separately trained dynamic model then generates the complete rollout conditioned on these states and their temporal locations. Experiments on Physics-IQ Verified, PhyGenBench, Pisa-Experiments, and RoboTwin2.0 show improvements of STRIKE over the corresponding video-backbone baselines in benchmark measures of physical consistency and manipulation-video fidelity. These results support learned visual state transitions as an effective intermediate representation for physical world modeling.

Momentum

Related topics

Latest papers 134