---
license: apache-2.0
library_name: transformers
pipeline_tag: video-text-to-text
---

This repository contains **VA-Judger**, a chain-of-thought omni-reward model for joint video-audio generation, presented in the paper [VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation](https://huggingface.co/papers/2608.18607).

- Project page: https://sharelab-sii.github.io/VA-Judger/
- Code: https://github.com/ShareLab-SII/VA-Judger