---
license: apache-2.0
library_name: diffusers
pipeline_tag: image-to-video
base_model: Wan-AI/Wan2.2-TI2V-5B-Diffusers
tags:
  - video-generation
  - reinforcement-learning
  - physics
  - diffusion
---

# PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

[![arXiv](https://img.shields.io/badge/arXiv-PhysRVG-red)](https://arxiv.org/abs/2601.11087)
[![Project Page](https://img.shields.io/badge/Project_Page-PhysRVG-blue)](https://lucaria-academy.github.io/PhysRVG/)
[![GitHub](https://img.shields.io/badge/Code-GitHub-black?logo=github)](https://github.com/ant-research/PhysRVG)

This repository hosts the **model weights** for PhysRVG (ECCV 2026). PhysRVG leverages a unified reinforcement learning framework with verifiable rewards to improve rigid-body motion generation in video synthesis.

> 📌 Demos, training, and inference code are in the [**GitHub repository**](https://github.com/ant-research/PhysRVG). This page only provides the checkpoints.

## Contents

```
PhysRVG/
├── dit                       # PhysRVG DiT weights (used with --resume_from_checkpoint)
├── lora                      # LoRA weights for memory-efficient fine-tuning / inference
├── sam2.1-hiera-large        # SAM 2 model used to compute the verifiable reward
└── Wan2.2-TI2V-5B-Diffusers  # base text/image-to-video diffusion model
```

## Usage

Download the weights into the `./models` directory of the [code repository](https://github.com/ant-research/PhysRVG):

```bash
huggingface-cli download HappyP4nda/PhysRVG --local-dir ./models
```

Then run inference (see the GitHub README for setup):

```bash
python inference.py --video_path data/example_videos/2/video.mp4
```

## Citation

```bibtex
@article{PhysRVG2026,
  title={PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models},
  author={Zhang, Qiyuan and Gong, Biao and Tan, Shuai and Zhang, Zheng and Shen, Yujun and Zhu, Xing and Li, Yuyuan and Yao, Kelu and Shen, Chunhua and Zou, Changqing},
  journal={ECCV 2026},
  year={2026}
}
```