Update README.md

README.md

@@ -7,6 +7,6 @@ sdk: static
 pinned: false
 ---
 
-CanViT (Canvas Vision Transformer) is a scalable recurrent architecture for the Active Vision Foundation Model (AVFM) era.
+CanViT (Canvas Vision Transformer) is a scalable recurrent architecture for the Active-Vision Foundation Model (AVFM) era.
 
-See https://github.com/m2b3/CanViT-PyTorch for more.
+See https://github.com/m2b3/CanViT-PyTorch and [CanViT: Toward Active-Vision Foundation Models](https://arxiv.org/pdf/2603.22570) for more.