Update README.md

README.md

@@ -1,3 +1,14 @@
----
-license: gpl
----
+---
+license: gpl
+---
+This is the official pre-trained model of the paper ''VIRT: Vision Instructed Robotic Transformer for Manipulation Learning''. The model is pre-trained using the robotic 
+imagery pre-training technique on the Droid dataset. If you find this model useful, please cite:
+
+```BibTeX
+@article{li2024virt,
+  title={VIRT: Vision Instructed Robotic Transformer for Manipulation Learning},
+  author={xxx},
+  journal={xxx},
+  year={2024}
+}
+```