Update README.md

README.md

@@ -17,6 +17,17 @@ models and prior robot learning models using less training data and smaller mode
 
 The `theia-tiny-patch16-224-cddsv` model, uses [DeiT-Tiny](https://huggingface.co/facebook/deit-tiny-patch16-224) as a backbone, and simulatenously distills [CLIP](https://github.com/openai/CLIP), [Depth Anything](https://github.com/LiheYoung/Depth-Anything), [DINOv2](https://github.com/facebookresearch/dinov2), [Segment Anything](https://github.com/facebookresearch/segment-anything) and [ViT](https://github.com/google-research/vision_transformer). For more information on usage, please visit the [Theia repository](https://github.com/bdaiinstitute/theia/tree/main).
 
+## Citation
+If you use Theia in your research, please use the following BibTeX entry:
+```bibtex
+@article{shang2024theia,
+  author    = {Shang, Jinghuan and Schmeckpeper, Karl and May, Brandon B. and Minniti, Maria Vittoria and Kelestemur, Tarik and Watkins, David and Herlant, Laura},
+  title     = {Theia: Distilling Diverse Vision Foundation Models for Robot Learning},
+  journal   = {arXiv},
+  year      = {2024},
+}
+```
+
 ## Usage
 
 The pre-trained model weights and code released with Theia are available for use under [The AI Institute License](https://raw.githubusercontent.com/bdaiinstitute/theia/main/LICENSE), reproduced in full below: