Update README.md

README.md

@@ -95,6 +95,24 @@ model-index:
 
 # LLaVAction-7B
 
+<div align="center">
+<h2>LLaVAction: evaluating and training multi-modal large language models for action recognition
+</h2>
+
+[Shaokai Ye](https://jwyang.github.io/)<sup>*</sup><sup>1</sup>&nbsp;
+[Haozhe Qi](https://cs-people.bu.edu/rxtan/)<sup>*</sup><sup>1</sup>&nbsp;
+
+[Alexander Mathis](https://qianhuiwu.github.io/)<sup>1</sup><sup>†</sup>&nbsp;
+[Mackenzie Weygandt Mathis](https://ruijiezheng.com/)<sup>1</sup><sup>†</sup><sup>‡</sup>&nbsp;
+
+<sup>1</sup> EPFL
+
+<sup>*</sup> First authors  <sup>†</sup> Senior Authors  <sup>‡</sup> Corresponding Author
+
+\[[arXiv Paper](https://www.arxiv.org/tbd)\] &nbsp; \[[Project Page](https://mmathislab.github.io/llavaction/)\] &nbsp; \[[Github Repo](https://github.com/AdaptiveMotorControlLab/LLaVAction)\] &nbsp; 
+
+</div>
+
 ## Model Summary
 The LLaVAction-7B model is trained on EPIC-KITCHENS-100-MQA, based on Qwen2 language model with a context window of 32K tokens.
 This model supports at most 64 frames.