Update README.md (#16)

Author: MMathisLab

README.md

@@ -2,7 +2,11 @@
 
 
 - This repository contains the implementation for our ICCV 2025 submission on evaluating and training multi-modal large language models for action recognition. 
-- Our code is built on [LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT), and files in the directory `llava/action` are related to this work. We thank the authors of LLaVA-NeXT for making their code publicly available.
+- Our code is built on [LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT), and files in the directory `llavaction/action` are related to this work. We thank the authors of LLaVA-NeXT for making their code publicly available.
+- The files in the`\model` ... etc ...  are directly from [LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT).
+- Modified files are:
+  - - file path
+  - - 
 A diff can be generated against the FIX of LLaVA-NeXT to see our modifications.
 - The code will be made publicaly available when published. For review, the provdied code and model license is [no license](https://choosealicense.com/no-permission/).
 - Please see the `\example` directory for a demo notebook and installation instructions.