Update README.md

README.md

@@ -25,11 +25,10 @@ The implementation currently supports **LLaVA-v1.5** and **LLaVA-Next** models.
 ## Citation
 
 ```bibtex
-@inproceedings{
-  wsvd2026iclr,
+@article{wang2026wsvd,
   title={WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models},
-  author={...},
-  booktitle={International Conference on Learning Representations (ICLR)},
+  author={Wang, Haiyu and Wang, Yutong and Jiang, Jack and Zhang, Sai Qian},
+  journal={arXiv preprint arXiv:2604.02570},
   year={2026}
 }
 ```