Upload README.md with huggingface_hub

README.md

@@ -146,11 +146,14 @@ similarities = torch.einsum("btd,bd->bt", audio_embeds, text_embeds)
 ## Citation
 
 ```bibtex
-@article{pe-av2025,
-  title={PEAV: An Audiovisual Perception Encoder via Large-Scale Multimodal Correspondence Learning},
-  author={Apoorv Vyas, Heng-Jui Chang, Cheng-Fu Yang, Po-Yao Huang, Luya Gao, Julius Richter, Sanyuan Chen, Matt Le, Piotr Dollár, Christoph Feichtenhofer, Ann Lee, Wei-Ning Hsu},
-  url={arxiv link coming soon}
-  year={2025}
+@misc{vyas2025pushingfrontieraudiovisualperception,
+      title={Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning},
+      author={Apoorv Vyas and Heng-Jui Chang and Cheng-Fu Yang and Po-Yao Huang and Luya Gao and Julius Richter and Sanyuan Chen and Matt Le and Piotr Dollár and Christoph Feichtenhofer and Ann Lee and Wei-Ning Hsu},
+      year={2025},
+      eprint={2512.19687},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2512.19687},
 }
 ```