Add pipeline tag, paper link, and citation

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: diffusers
 license: apache-2.0
+pipeline_tag: any-to-any
 tags:
 - image-to-video
 - image-text-to-video
@@ -39,10 +40,11 @@ MOVA addresses the limitations of proprietary systems like Sora 2 and Veo 3 by o
 ### Model Sources
 
 - **Github:** https://github.com/OpenMOSS/MOVA
-- **Paper:** Coming soon.
+- **Paper:** [MOVA: Towards Scalable and Synchronized Video-Audio Generation](https://huggingface.co/papers/2602.08794)
+- **Project Page:** https://mosi.cn/models/mova
 
 ### Model Usage
-Please refer to the github page for model usage.
+Please refer to the [Quick Start](https://github.com/OpenMOSS/MOVA#quick-start) section on the GitHub page for model usage and inference scripts.
 
 ## Evaluation
 We evaluate our model through both objective benchmarks and subjective human evaluations. Below are the Elo scores and win rates comparing MOVA to existing open-source models.
@@ -55,3 +57,13 @@ We evaluate our model through both objective benchmarks and subjective human eva
     <img src="https://cdn-uploads.huggingface.co/production/uploads/64817b8550b759c75d5d1eeb/i5lgZI3NmxLXdJIxndcOp.png" width="1000"/>
 <p>
 
+## Citation
+
+```bibtex
+@article{yu2026mova,
+  title={MOVA: Towards Scalable and Synchronized Video-Audio Generation},
+  author={Yu, Donghua and Chen, Mingshu and Chen, Qi and Luo, Qi and Wu, Qianyi and Cheng, Qinyuan and Li, Ruixiao and Liang, Tianyi and Zhang, Wenbo and Tu, Wenming and others},
+  journal={arXiv preprint arXiv:2602.08794},
+  year={2026}
+}
+```