Update README.md

README.md

@@ -38,9 +38,8 @@ For the COCO dataset, we utilized Llava-style prompts to generate data. For the
 
 ### Techniques Used
 
-- **Caption-based Prompting:** Utilizes accurate captions and bounding boxes from the original dataset.
-- **Image-based Prompting:** Leverages images to generate captions and conversations.
-
+- **MoE-LLaVA**: [MoE-LLaVA](https://github.com/PKU-YuanGroup/MoE-LLaVA/tree/main)
+- 
 ## Evaluation
 - Comming soon 🫡