Update README.md

README.md

@@ -114,9 +114,9 @@ print(output)
 ## Citation
 
 ```
-@article{UnifiedReward-Think,
-  title={Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning.},
-  author={Wang, Yibin and Li, Zhimin and Zang, Yuhang and Wang, Chunyu and Lu, Qinglin, and Jin, Cheng and Wang, Jiaqi},
+@article{unifiedreward-think,
+  title={Unified multimodal chain-of-thought reward model through reinforcement fine-tuning},
+  author={Wang, Yibin and Li, Zhimin and Zang, Yuhang and Wang, Chunyu and Lu, Qinglin and Jin, Cheng and Wang, Jiaqi},
   journal={arXiv preprint arXiv:2505.03318},
   year={2025}
 }