Improve model card with paper and project links

README.md

@@ -1,9 +1,10 @@
 ---
 license: apache-2.0
+pipeline_tag: other
 tags:
-  - video-evaluation
-  - world-model
-  - benchmark
+- video-evaluation
+- world-model
+- benchmark
 ---
 
 <div align="center">
@@ -11,6 +12,8 @@ tags:
   <h1>WBench Weights</h1>
   <p>Pre-trained model weights for WBench evaluation.</p>
 
+[![Paper](https://img.shields.io/badge/Paper-red?style=for-the-badge&logo=arxiv&logoColor=white)](https://huggingface.co/papers/2605.25874)
+[![Project Page](https://img.shields.io/badge/Homepage-blue?style=for-the-badge&logo=google-chrome&logoColor=white)](https://meituan-longcat.github.io/WBench/)
 [![Code](https://img.shields.io/badge/Code-black?style=for-the-badge&logo=github&logoColor=white)](https://github.com/meituan-longcat/WBench)
 [![Dataset](https://img.shields.io/badge/Dataset-4285F4?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/datasets/meituan-longcat/WBench)
 
@@ -18,9 +21,15 @@ tags:
 
 ---
 
+This repository contains the consolidated model weights for **WBench**, a comprehensive multi-turn benchmark for interactive video world model evaluation. WBench evaluates world models along five dimensions: video quality, setting adherence, interaction adherence, consistency, and physics compliance. It contains 289 test cases and 1,058 interaction turns covering diverse scenes, styles, subjects, and perspectives.
+
 ## Usage
 
-Please refer to [WBench GitHub](https://github.com/meituan-longcat/WBench) for installation and evaluation instructions.
+Please refer to the [WBench GitHub repository](https://github.com/meituan-longcat/WBench) for installation and evaluation instructions. You can download the weights using the Hugging Face CLI:
+
+```bash
+huggingface-cli download meituan-longcat/WBench-weights --local-dir weights/
+```
 
 ## Disclaimer
 
@@ -29,3 +38,13 @@ We consolidate these weights into a single repository to help the community quic
 - **Kaining Ying**: kaining.ying.cv@gmail.com
 - **Siyu Ren**: rensiyu07@meituan.com
 
+## Citation
+
+```bibtex
+@article{ying2025wbench,
+  title={WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation},
+  author={Ying, Kaining and Hu, Hengrui and Ren, Siyu and Li, Jiamu and Chen, Fengjiao and Wang, Ziwen and Cao, Xuezhi and Cai, Xunliang and Ding, Henghui},
+  journal={arXiv preprint arXiv:2605.25874},
+  year={2025}
+}
+```