Improve model card: Add metadata, paper link, and correct GitHub URL

README.md

@@ -1,16 +1,21 @@
 ---
 license: mit
+pipeline_tag: text-generation
+library_name: transformers
 ---
+
 ## TMLR-Group-HF/Majority-Voting-Qwen3-8B-Base
 
-This is the Qwen3-8B-Base model trained by Majority-Voting method using MATH training set.
+This is the Qwen3-8B-Base model trained by the Majority-Voting method using the MATH training set, as presented in the paper [Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models](https://huggingface.co/papers/2508.00410).
+
+Co-rewarding is a novel self-supervised RL framework that improves training stability by seeking complementary supervision from another views. It addresses the training collapse issue in self-rewarding methods by instantiating in two ways: Co-rewarding-I, which uses contrastive agreement across semantically analogous questions, and Co-rewarding-II, which employs a slowly-updated reference teacher for self-distillation. This approach introduces discrepancies to prevent training collapse on trivial reasoning solutions.
 
-If you are interested in Co-Reward, you can find more details on our Github Repo [https://github.com/tmlr-group/Co-Reward].
+For more details on the Co-rewarding framework, training procedures, and other checkpoints, you can find the project's official GitHub repository here: [https://github.com/tmlr-group/Co-rewarding](https://github.com/tmlr-group/Co-rewarding).
 
 ## Citation
 ```
 @article{zhang2025coreward,
-      title={Co-Reward: Self-supervised Reinforcement Learning for Large Language Model Reasoning via Contrastive Agreement}, 
+      title={Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models},
       author={Zizhuo Zhang and Jianing Zhu and Xinmu Ge and Zihua Zhao and Zhanke Zhou and Xuan Li and Xiao Feng and Jiangchao Yao and Bo Han},
       journal={arXiv preprint arXiv:2508.00410}
       year={2025},