Update README.md

README.md

@@ -93,4 +93,30 @@ pipeline_tag: image-to-video
       <td style="vertical-align: middle;">Fine-tuned LoRA for <a href="https://huggingface.co/datasets/amagipeng/VR-Bench">TrapField</a> tasks (easy, medium, and hard) from base model <a href="https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B">Wan2.2-TI2V-5B</a>.</td>
     </tr>
   </tbody>
-</table>
+</table>
+
+<h2 align="center">📑 Citation</h2>
+
+<p align="center">
+  If you use this model or the VR-Bench dataset in your work, please cite:
+</p>
+
+<p align="center">
+  📄 <a href="https://arxiv.org/abs/2511.15065">
+    Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks
+  </a>
+</p>
+
+<pre>
+<code>
+@misc{yang2025reasoningvideoevaluationvideo,
+      title={Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks}, 
+      author={Cheng Yang and Haiyuan Wan and Yiran Peng and Xin Cheng and Zhaoyang Yu and Jiayi Zhang and Junchi Yu and Xinlei Yu and Xiawu Zheng and Dongzhan Zhou and Chenglin Wu},
+      year={2025},
+      eprint={2511.15065},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2511.15065}, 
+}
+</code>
+</pre>