# PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.13809 · HTML: https://mlsanity.com/paper/2510.13809/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 44 of its 45 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 44)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation](https://mlsanity.com/paper/2404.13026/) (2024)
- [PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation](https://mlsanity.com/paper/2409.18964/) (2024)
- [VideoDPO: Omni-Preference Alignment for Video Diffusion Generation](https://mlsanity.com/paper/2412.14167/) (2024)
- [Video Diffusion Alignment via Reward Gradients](https://mlsanity.com/paper/2407.08737/) (2024)

## Built on by (most cited first, 12 of 12)

- [What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards](https://mlsanity.com/paper/2512.00425/) (2025)
- [Simulating the Visual World with Artificial Intelligence: A Roadmap](https://mlsanity.com/paper/2511.08585/) (2025)
- [ProPhy: Progressive Physical Alignment for Dynamic World Simulation](https://mlsanity.com/paper/2512.05564/) (2025)
- [UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation](https://mlsanity.com/paper/2512.07831/) (2025)
- [Evolution of Video Generative Foundations](https://mlsanity.com/paper/2604.06339/) (2026)
- [CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation](https://mlsanity.com/paper/2601.11096/) (2026)
- [DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation](https://mlsanity.com/paper/2603.25931/) (2026)
- [MotiMotion: Motion-Controlled Video Generation with Visual Reasoning](https://mlsanity.com/paper/2605.22818/) (2026)
- [Distilling Physical Priors into Streaming World Models](https://mlsanity.com/paper/2608.07981/) (2026)
- [PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.26916/) (2026)
- [Video Generation Models: A Survey of Post-Training and Alignment](https://mlsanity.com/paper/2610.00812/) (2026)
- [World Models' Last Exam in Physics](https://mlsanity.com/paper/2610.08791/) (2026)

## Abstract (arXiv)

Video generation models nowadays are capable of generating visually realistic videos, but often fail to adhere to physical laws, limiting their ability to generate physically plausible videos and serve as ''world models''. To address this issue, we propose PhysMaster, which captures physical knowledge as a representation for guiding video generation models to enhance their physics-awareness. Specifically, PhysMaster is based on the image-to-video task where the model is expected to predict physically plausible dynamics from the input image. Since the input image provides physical priors like relative positions and potential interactions of objects in the scenario, we devise PhysEncoder to encode physical information from it as an extra condition to inject physical knowledge into the video generation process. The lack of proper supervision on the model's physical performance beyond mere appearance motivates PhysEncoder to apply reinforcement learning with human feedback to physical representation learning, which leverages feedback from generation models to optimize physical representations with Direct Preference Optimization (DPO) in an end-to-end manner. PhysMaster provides a feasible solution for improving physics-awareness of PhysEncoder and thus of video generation, proving its ability on a simple proxy task and generalizability to wide-ranging physical scenarios. This implies that our PhysMaster, which unifies solutions for various physical processes via representation learning in the reinforcement learning paradigm, can act as a generic and plug-in solution for physics-aware video generation and broader applications.