Update README.md

README.md

@@ -15,7 +15,7 @@ library_name: transformers
 
 **VL-Rethinker-7B** achieves SoTA results on various multimodal reasoning benchmarks.
 
-It is trained using the **GRPO-SSR and Forced Rethinking** techniques.
+It is trained using the **GRPO-SSR and Forced Rethinking** techniques, using meticulously curated training queries from [ViRL39K](https://huggingface.co/datasets/TIGER-Lab/ViRL39K).
 
 For details of our approach and performance comparison, please see our [paper](https://github.com/TIGER-AI-Lab/VL-Rethinker/blob/main/paper.pdf).
 
@@ -23,15 +23,16 @@ For details of training and evaluation, please see our [code repo](https://githu
 
 Explore further via the following links:
 
-| [**🚀Project Page**](https://tiger-ai-lab.github.io/VL-Rethinker/) | [**📖Paper**](https://arxiv.org/abs/2504.08837) | [**🔗Github**](https://github.com/TIGER-AI-Lab/VL-Rethinker/) | [**🤗Data** (Coming Soon)]()  |
+| [**🚀Project Page**](https://tiger-ai-lab.github.io/VL-Rethinker/) | [**📖Paper**](https://arxiv.org/abs/2504.08837) | [**🔗Github**](https://github.com/TIGER-AI-Lab/VL-Rethinker/) | [**🤗Data** (ViRL39K)](https://huggingface.co/datasets/TIGER-Lab/ViRL39K)  |
 
 ## Citation
 
 If you feel this model useful, please give us a free cite:
-```
+```bibtex
 @article{vl-rethinker,
       title={VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning},
       author = {Wang, Haozhe and Qu, Chao and Huang, Zuming and Chu, Wei and Lin,Fangzhen and Chen, Wenhu},
       journal={arXiv preprint arXiv:2504.08837},
       year={2025}
-}
+}
+```