Update README.md

README.md

@@ -195,17 +195,16 @@ The model is built on top of two pre-trained models: [google/siglip-so400m-patch
 **BibTeX:**
 
 ```bibtex
-@misc{laurençon2024matters,
-      title={What matters when building vision-language models?}, 
-      author={Hugo Laurençon and Léo Tronchon and Matthieu Cord and Victor Sanh},
+@misc{laurençon2024building,
+      title={Building and better understanding vision-language models: insights and future directions.}, 
+      author={Hugo Laurençon and Andrés Marafioti and Victor Sanh and Léo Tronchon},
       year={2024},
-      eprint={2405.02246},
+      eprint={2408.12637},
       archivePrefix={arXiv},
       primaryClass={cs.CV}
 }
 ```
 
-TODO: new paper
 
 # Acknowledgements