Update README.md

README.md

@@ -106,8 +106,17 @@ Our training code was implemented in Pytorch. Our inference code is available fo
 
 ## Citation
 
+```
+@article{kyutai2025moshivis,
+  author = {Amélie Royer and Moritz Böhle and Gabriel de Marmiesse and
+  Laurent Mazaré and Alexandre Défossez and Neil Zeghidour and Patrick Pérez},
+  year = {2025},
+  title = {Vision-Speech Models: Teaching Speech Models to Converse about Images},
+  journal = {ArXiv},
+  url = {https://arxiv.org/abs/2503.15633}
+}
+```
 
-Blog post: https://kyutai.org/