Update README.md

README.md

@@ -21,6 +21,8 @@ datasets:
 
 ![- visual selection.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/ZTVZYShywtf52cgBMV583.png)
 
+*SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features* https://arxiv.org/pdf/2502.14786
+
 ```py
 Classification Report:
                precision    recall  f1-score   support