RL for Video Generation

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 24

All topics

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
Token-Level Video Reinforcement Learning
Oct 1, 2026Yifan Wang, Gordon Guocheng Qian, Yanyu Li +2Video Diffusion Models RL for Video Generation
Northeastern University
VideoGen-Agent: Reinforcing Video Generation Agents
Sep 21, 2026Binxu Li, Haoyi Duan, Yuhui Zhang +9RL for Video Generation Agentic Video Generation
Princeton University · Stanford University · UC Davis +4
AgenticGen: Reward-Guided Agentic Video Generation for Advertising
Sep 10, 2026Xingyuan Bu, Chengru Song, Hao Zhou +9Reward Modeling Agentic RL
ByteDance · Tsinghua University · The Chinese University of Hong Kong
WorldReward: Reward Modeling for Camera-Conditioned World Models
Sep 3, 2026Yibin Wang, Zehan Wang, Junshu Tang +13Reward Modeling Camera-Conditioned Video Generation
Fudan University · Tencent Hunyuan · Shanghai Innovation Institute +3
VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation
Aug 19, 2026Yinming Huang, Shuyuan Tu, Xi Yan +6Reward Modeling Audio-Video Generation
Fudan University · Shanghai Innovation Institution · Yinwang Intelligent Technology Co., Ltd +1
LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
Aug 6, 2026Yingqing Guo, Hui Yuan, Zijian He +2RL for Video Generation RL for Image Generation
Reinforcement Learning: From Algorithms To Foundation Models
Jul 20, 2026Zihan DingReinforcement Learning RL for Video Generation
Department of Electrical Computer Engineering, Princeton University
TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
Jun 26, 2026Jing Wang, Xiangxin Zhou, Jiajun Liang +5Autoregressive Diffusion RL for Video Generation
Shenzhen Campus of Sun Yat-Sen University · Tencent Hunyuan · Tsinghua University +2
ReFree: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech Guidance
Jun 11, 2026Salaheldin Mohamed, M. Hamza Mughal, Rishabh Dabral +1Audio-Video Generation RL for Video Generation
Télécom Paris, Institut Polytechnique de Paris · Max Planck Institute for Informatics
World Model Self-Distillation: Training World Models to Solve General Tasks
Jun 10, 2026Sebastian Stapf, Pablo Acuaviva Huertos, Aram Davtyan +1Video Diffusion Models RL for Video Generation
Department of Computer Science UNIVERSITY OF BERN
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
Jun 9, 2026Bowen Ping, Xiangxin Zhou, Penghui Qi +3RL for Video Generation RL for Image Generation
Xi’an Jiaotong University · Tencent Hunyuan · National University of Singapore
Geo-Align: Video Generation Alignment via Metric Geometry Reward
May 22, 2026Zizun Li, Haoyu Guo, Runzhe Teng +2Camera-Controlled Video Generation Reinforcement Learning
1USTC · 2Shanghai AI Lab · 3ZJU
CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition
May 19, 2026Hongji Yang, Songlian Li, Yucheng Zhou +4Video Diffusion Models RL for Video Generation
1SKL-IOTSC, CIS, University of Macau · 2Online-Video BU, Tencent
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
GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
May 18, 2026Jan Ackermann, Shengqu Cai, Boyang Deng +3Physical Consistency in Video Generation Video Diffusion Models
Stanford University · Google DeepMind
Video Models Can Reason with Verifiable Rewards
May 14, 2026Tinghui Zhu, Sheng Zhang, James Y. Huang +5Video Diffusion Models RL for Video Generation
University of California, Davis · Microsoft Research · University of Southern California +1
KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration
May 14, 2026Ruicheng Zhang, Kaixi Cong, Jun Zhou +5RL for Video Generation Long Video Generation
Tsinghua University · Video Rebirth · HKUST
CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL
May 14, 2026Zhenyang Ni, Yijiang Li, Ruochen Jiao +7Video Diffusion Models Reinforcement Learning
Northwestern University · University of California, San Diego · University of Oxford
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
May 14, 2026Yidong Huang, Zun Wang, Han Lin +6Physical Consistency in Video Generation RL for Video Generation
1UNC Chapel Hill · 2FieldAI · 3NTU Singapore +2
Generate Your Talking Avatar from Video Reference
Apr 30, 2026Zujin Guo, Zhenhui Ye, Yi Ren +4Video-Reference Video Generation Audio-Video Generation
Nanyang Technological University · HeyGen Research · University of Melbourne
AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization
Mar 18, 2026Dailan He, Guanlin Feng, Xingtong Ge +5RL for Video Generation Streaming Video Generation
CUHK MMLab, China · Vivix Group Limited, China · HKUST, China +1
MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignment
Dec 7, 2025Ruicheng Zhang, Mingyang Zhang, Jun Zhou +6Physical Consistency in Video Generation Long-Horizon Robotic Manipulation
Tsinghua University · Sun Yat-sen University · X Square Robot +1
Rethinking Reward Signals in Video GRPO: When Scores Become Targets
Nov 24, 2025Rui Li, Yuanzhi Liang, Ziqi Ni +3Reward Hacking RL for Video Generation
University of Science and Technology of China, Hefei, China · Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China · Southeast University, Nanjing, China

Oct 1, 2026, cs.CVJ/K move · Enter open · S save

HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation

Tahira Kazimi, Shubhankar Borse, Munawar Hayat, Fatih Porikli+1

Virginia Tech · Qualcomm AI Research

Physics-Informed Generative Modeling Physical Consistency in Video Generation RL for Video Generation

Open paper AskPDF arXiv

Video generation models have achieved remarkable visual fidelity and have strong potential to become general-purpose world simulators. Despite this progress, they still fail to generate videos which adhere to laws of physics. The problem becomes even more apparent in realistic settings where multiple physical principles must work together within the same video; for example, "a balloon floating upward while steam rises from a pot" requires buoyancy and fluid dynamics to unfold coherently and simultaneously. Yet existing methods largely ignore multi-principle interactions, focusing on a single principle per video. We propose HiPhy (Hierarchical Physical Alignment), a reinforcement learning framework that grounds video generation in physical laws through a dual-level objective: locally enforcing the temporal dynamics of individual physical principles, and globally ensuring the physical and semantic coherence of the entire scene. To support multi-principle generation, we construct a 50K-prompt dataset and introduce a prompt benchmark MultiPhyBench, spanning a diverse range of co-occurring physical events. Our experiments show that HiPhy significantly outperforms prior methods and baselines, improving physical commonsense and semantic alignment significantly across various benchmarks, with the largest gains on scenes involving multiple concurrent physical principles where competing methods degrade most sharply.

Momentum

Related topics

Latest papers 24