|
--- |
|
license: mit |
|
--- |
|
|
|
<p align="center"> |
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/623d8ca4c29adf5ef6175615/bp_DZR79-mTj8Z6GJe9B0.png" width="80%" /> |
|
</p> |
|
|
|
<font size=3><div align='center' > |
|
[[📖 arXiv Paper](https://arxiv.org/abs/2406.08487)] |
|
[[📊 MM-RLHF Data](https://huggingface.co/datasets/yifanzhang114/MM-RLHF)] |
|
[[📝 Homepage](https://mm-rlhf.github.io/)] |
|
[[🏆 Reward Model](https://huggingface.co/yifanzhang114/MM-RLHF-Reward-7B-llava-ov-qwen)] |
|
[[🔮 MM-RewardBench](https://huggingface.co/datasets/yifanzhang114/MM-RLHF-RewardBench)] |
|
[[🔮 MM-SafetyBench](https://github.com/yfzhang114/mmrlhf-eval)] |
|
[[📈 Evaluation Suite](https://github.com/yfzhang114/mmrlhf-eval)] |
|
</div></font> |
|
|
|
|
|
# The Next Step Forward in Multimodal LLM Alignment |
|
|
|
**[2025/02/10]** 🔥 We are proud to open-source **MM-RLHF**, a comprehensive project for aligning Multimodal Large Language Models (MLLMs) with human preferences. This release includes: |
|
|
|
- A **high-quality MLLM alignment dataset**. |
|
- A **strong Critique-Based MLLM reward model** and its training algorithm. |
|
- A **novel alignment algorithm MM-DPO**. |
|
- **Two new benchmarks**. |
|
|
|
Our dataset and algorithms enable consistent performance improvements across **10 dimensions** and **27 benchmarks** for open-source MLLMs. |
|
<p align="center"> |
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/623d8ca4c29adf5ef6175615/8nVZQd8bfB6NJIixCv6_X.png" width="80%" /> |
|
</p> |
|
|
|
## Citation |
|
|
|
If you find it useful for your research and applications, please cite related papers/blogs using this BibTeX: |
|
```bibtex |
|
|
|
``` |
|
|
