Update README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ language:
|
|
21 |
<p>
|
22 |
<a href="https://zhuohaoyu.github.io/RewardAnything"><img alt="Website" src="https://img.shields.io/badge/π_Project-Website-A593C2?style=flat-square&labelColor=8A7AA8"></a>
|
23 |
<a href="https://huggingface.co/WisdomShell/RewardAnything-8B-v1"><img alt="Model Weights" src="https://img.shields.io/badge/π€_HuggingFace-Model_Weights-D4A574?style=flat-square&labelColor=B8956A"></a>
|
24 |
-
<a href="https://arxiv.org/abs/
|
25 |
<a href="https://pypi.org/project/rewardanything/"><img alt="PyPI" src="https://img.shields.io/pypi/v/rewardanything.svg?style=flat-square&color=7B9BB3&labelColor=5A7A94"></a>
|
26 |
</p>
|
27 |
<h1> RewardAnything: Generalizable Principle-Following Reward Models </h1>
|
@@ -331,7 +331,7 @@ We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
|
|
331 |
@article{yu2025rewardanything,
|
332 |
title={RewardAnything: Generalizable Principle-Following Reward Models},
|
333 |
author={Yu, Zhuohao and Zeng, Jiali and Gu, Weizheng and Wang, Yidong and Wang, Jindong and Meng, Fandong and Zhou, Jie and Zhang, Yue and Zhang, Shikun and Ye, Wei},
|
334 |
-
journal={arXiv preprint arXiv:
|
335 |
year={2025}
|
336 |
}
|
337 |
```
|
|
|
21 |
<p>
|
22 |
<a href="https://zhuohaoyu.github.io/RewardAnything"><img alt="Website" src="https://img.shields.io/badge/π_Project-Website-A593C2?style=flat-square&labelColor=8A7AA8"></a>
|
23 |
<a href="https://huggingface.co/WisdomShell/RewardAnything-8B-v1"><img alt="Model Weights" src="https://img.shields.io/badge/π€_HuggingFace-Model_Weights-D4A574?style=flat-square&labelColor=B8956A"></a>
|
24 |
+
<a href="https://arxiv.org/abs/2506.03637"><img alt="Paper" src="https://img.shields.io/badge/π_arXiv-Paper-C7969C?style=flat-square&labelColor=A8798A"></a>
|
25 |
<a href="https://pypi.org/project/rewardanything/"><img alt="PyPI" src="https://img.shields.io/pypi/v/rewardanything.svg?style=flat-square&color=7B9BB3&labelColor=5A7A94"></a>
|
26 |
</p>
|
27 |
<h1> RewardAnything: Generalizable Principle-Following Reward Models </h1>
|
|
|
331 |
@article{yu2025rewardanything,
|
332 |
title={RewardAnything: Generalizable Principle-Following Reward Models},
|
333 |
author={Yu, Zhuohao and Zeng, Jiali and Gu, Weizheng and Wang, Yidong and Wang, Jindong and Meng, Fandong and Zhou, Jie and Zhang, Yue and Zhang, Shikun and Ye, Wei},
|
334 |
+
journal={arXiv preprint arXiv:2506.03637},
|
335 |
year={2025}
|
336 |
}
|
337 |
```
|