Update README.md

README.md

@@ -22,7 +22,7 @@ Med-R1 is a reinforcement learning (RL)-enhanced vision-language model (VLM) des
   - **Anatomy Identification**, **Disease Diagnosis**, **Lesion Grading**, **Modality Recognition**, and **Biological Attribute Analysis**.
 
 ## Use of Models
-```
+```python
 from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
 
 MODEL_PATH = "yuxianglai117/Med-R1"
@@ -37,4 +37,15 @@ model = Qwen2VLForConditionalGeneration.from_pretrained(
 processor = AutoProcessor.from_pretrained(MODEL_PATH)
 ```
 
-## Citation
+## Citation
+```
+@misc{lai2025medr1reinforcementlearninggeneralizable,
+      title={Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models}, 
+      author={Yuxiang Lai and Jike Zhong and Ming Li and Shitian Zhao and Xiaofeng Yang},
+      year={2025},
+      eprint={2503.13939},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2503.13939}, 
+}
+```