update the news about training code

README.md

@@ -23,6 +23,10 @@
   year={2025}
 }
 ```
+
+## Updates
+- [Apr 13, 2025] Training code is being gradually cleaned and uploaded to the [training](https://github.com/facebookresearch/vggt/tree/training) branch. It will be merged into the main branch once finalized.
+
 ## Overview
 
 Visual Geometry Grounded Transformer (VGGT, CVPR 2025) is a feed-forward neural network that directly infers all key 3D attributes of a scene, including extrinsic and intrinsic camera parameters, point maps, depth maps, and 3D point tracks, **from one, a few, or hundreds of its views, within seconds**.
@@ -230,4 +234,4 @@ Thanks to these great repositories: [PoseDiffusion](https://github.com/facebookr
 
 
 ## License
-See the [LICENSE](./LICENSE.txt) file for details about the license under which this code is made available.
+See the [LICENSE](./LICENSE.txt) file for details about the license under which this code is made available.