Update README.md

README.md

@@ -32,10 +32,10 @@ license: apache-2.0
 
 If you find it useful for your research and applications, please cite related papers/blogs using this BibTeX:
 ```bibtex
-@article{zhang2025mm,
-  title={MM-RLHF: The Next Step Forward in Multimodal LLM Alignment},
-  author={Zhang, Yi-Fan and Yu, Tao and Tian, Haochen and Fu, Chaoyou and Li, Peiyan and Zeng, Jianshu and Xie, Wulin and Shi, Yang and Zhang, Huanyu and Wu, Junkang and others},
-  journal={arXiv preprint arXiv:2502.10391},
+@article{zhang2025r1,
+  title={R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning},
+  author={Zhang, Yi-Fan and Lu, Xingyu and Hu, Xiao and Fu, Chaoyou and Wen, Bin and Zhang, Tianke and Liu, Changyi and Jiang, Kaiyu and Chen, Kaibing and Tang, Kaiyu and others},
+  journal={arXiv preprint arXiv:2505.02835},
   year={2025}
 }
 ```