Update README.md

README.md

@@ -8,18 +8,20 @@ language:
 
 We developed a domain-speciffc large language-vision assistant (PA-LLaVA) for pathology image understanding. Specifically, (1) we first construct a human pathology image-text dataset by cleaning the public medical image-text data for domainspecific alignment; (2) Using the proposed image-text data, we first train a pathology language-image pretraining (PLIP) model as the specialized visual encoder for pathology image, and then we developed scale-invariant connector to avoid the information loss caused by image scaling; (3) We adopt two-stage learning to train PA-LLaVA, first stage for domain alignment, and second stage for end to end visual question & answering (VQA) task.
 
-Our code is publicly available on Github.[ddw2AIGROUP2CQUPT/PA-LLaVA (github.com)](https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA)
+###### Our code is publicly available on Github.[ddw2AIGROUP2CQUPT/PA-LLaVA (github.com)](https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA)
 
-## Architecture
 
-![image](https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA/blob/main/xtuner_add/d285474a96a76781d5088a0a0dd85a3.png) 
+## Architecture
 
-## Data Cleaning Process
+![image](https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA/blob/main/Architecture.png) 
 
 
+## Data Cleaning Process
+![image](https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA/blob/main/DataCleanProcess.png)
 
 Only the image names of the cleaned dataset are provided here, for the specific training code please visit our Github.
 
+
 ## contact
 
 mailto: [[email protected]](mailto:[email protected]) or [[email protected]](mailto:[email protected])