Physics-Guided Video Generation

Latest papers

16 papers5 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

PhyEvolve: Multi-Agent State-Evolution Planning for Physics-Aware Video Generation
Oct 22, 2026Yang-Hao Zhou, Lixing Tan, Zhiqi Li +2Physics-Guided Video Generation Video Generation
Canva Research
Risk Decomposition for Hallucination-Aware Video Sampling
Oct 19, 2026Chenyan Zheng, Fan Wu, Ruibo Li +4Physics-Guided Video Generation Physical Consistency in Video Generation
Zhejiang University · Nanyang Technological University · Tsinghua University +1
FluidGen: Physics-Aware Fluid Video Generation via Motion-Guided Post-Training
Oct 19, 2026Yang Zheng, Zizhang Li, Boyang Deng +6Video Generation Physics-Guided Video Generation
Stanford University
Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training
Oct 7, 2026Hong Huang, Yuqiu Liu, Chenyu You +3Video Generation Physics-Guided Video Generation
Simon Fraser University · Stony Brook University · Lawrence Berkeley National Laboratory +1
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
VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation
Jul 26, 2026Tianxiao Chen, Hanmo Chen, Huajin Chen +3Video-Reference Video Generation Physical Consistency in Video Generation
Zhejiang University · vivo BlueImage Lab, vivo Mobile Communication Co., Ltd.
PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation
Jul 17, 2026Qirui Li, Jinkun Hao, Yibo Li +3Physical Consistency in Video Generation Agentic Video Generation
Shanghai Jiao Tong University · Cardiff University
OptiWorld: Optimal Control for Video World Generation under Physical Constraints
May 30, 2026Yu Yuan, Jianhao Yuan, Xijun Wang +4Controllable Video Generation Image-to-Video Generation
Purdue University · University of Oxford · SixteenMiles Labs
NEWTON: Agentic Planning for Physically Grounded Video Generation
May 18, 2026Yuxiang Feng, Juncheng Wang, Chao Xu +7Physics-Informed Generative Modeling Physical Consistency in Video Generation
Zhejiang University · The Hong Kong Polytechnic University · IROOTECH TECHNOLOGY +1
3DPhysVideo: Consistency-Guided Flow SDE for Video Generation via 3D Scene Reconstruction and Physical Simulation
May 16, 2026Hwidong Kim, Yunho Kim, Tae-Kyun KimPhysical Consistency in Video Generation Image-to-Video Generation
KAIST
Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation
Apr 30, 2026Yajvan Ravan, Adam Rashid, Alan Yu +8Robotic Data Collection Robotics Simulation
MIT CSAIL · 2FortyFive Labs · 3Caltech +3
PhysLayer: Language-Guided Layered Animation with Depth-Aware Physics
Apr 26, 2026Tianyidan Xie, Zhentao Huang, Mingjie Wang +4Physical Consistency in Video Generation Image-to-Video Generation
Nanjing University · University of Guelph · Zhejiang Sci-Tech University +1
PhysVid: Physics Aware Local Conditioning for Generative Video Models
Mar 27, 2026Saurabh Pathak, Elahe Arani, Mykola Pechenizkiy +1Physics-Guided Video Generation Physical Consistency in Video Generation
Eindhoven University of Technology
Physical Simulator In-the-Loop Video Generation
Mar 6, 2026Lin Geng Foo, Mark He Huang, Alexandros Lattas +3Physics-Guided Video Generation Physical Consistency in Video Generation
Max Planck Institute for Informatics, Saarland Informatics Campus · Saarbrücken Research Center for Visual Computing, Interaction and Artificial Intelligence · Singapore University of Technology and Design +2
RealWonder: Real-Time Physical Action-Conditioned Video Generation
Mar 5, 2026Wei Liu, Ziyu Chen, Zizhang Li +3Physics-Guided Video Generation Action-Conditioned Video Generation
Stanford University · University of Southern California
PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
Mar 3, 2026Shang Wu, Chenwei Xu, Zhuofan Xia +6Prompt Optimization for T2V Generation Physical Consistency in Video Generation
Northwestern University · Dolby Laboratories

Oct 22, 2026J/K move · Enter open · S save

PhyEvolve: Multi-Agent State-Evolution Planning for Physics-Aware Video Generation

Yang-Hao Zhou, Lixing Tan, Zhiqi Li, Guang Yang+1

Canva Research

Physics-Guided Video Generation Video Generation Physical Consistency in Video Generation Agentic Video Generation Prompt Optimization for T2V Generation Multi-Agent Planning

Open paper AskPDF arXiv

Recent advances in text-to-video generation have substantially improved visual fidelity, yet existing models still struggle to understand the physical evolution implicit in user prompts, making it difficult to generate videos with continuous physical state evolution. Here, we propose PhyEvolve, a multi-agent framework that enhances natural-language prompts through structured state-evolution planning. PhyEvolve consists of three agents: a Director, a Physical Evolver, and a Composer. Given a user prompt and an optional first frame, the Director grounds the scene and disentangles physical events from observation changes. The Physical Evolver uses scene evidence to identify physical mechanisms then constructs causally linked state transitions that unfold throughout the video, whether visible or not. The Composer utilizes these transitions to enhance the original prompts. Without retraining or model modification, PhyEvolve works directly with existing generators through prompt replacement. Extensive experiments on four major benchmarks show that PhyEvolve achieves state-of-the-art performance, outperforming the cutting-edge prior agentic baseline by 7.9 percentage points on average. These results demonstrate that explicit causal state-evolution planning improves physical consistency and state continuity in generated videos through natural-language prompt enhancement.