Update README.md

README.md

@@ -8,7 +8,7 @@ license: other
 [The AI Institute](https://theaiinstitute.com/)
 
 Theia is a vision foundation model for robot learning that distills multiple off-the-shelf vision foundation models trained on varied vision tasks. Theia’s rich visual representations encode diverse visual knowledge, enhancing downstream robot learning. It was introduced in the paper [Theia: Distilling Diverse Vision Foundation Models for Robot Learning](https://arxiv.org/abs/2407.20179), which also includes experiments demonstrating that Theia outperforms its teacher
-models and prior robot learning models using less training data and smaller model sizes.
+models and prior robot learning models using less training data and smaller model sizes. Demo videos can be found on the [project page](http://theia.theaiinstitute.com/).
 
 <img src="https://raw.githubusercontent.com/bdaiinstitute/theia/main/doc/theia_overview.gif" height="300px">