Update README.md

README.md

@@ -34,21 +34,21 @@ We propose a MLLM based on Inner-Adaptor Architecture (IAA). IAA demonstrates th
 ### Main Results on General Multimodal Benchmarks. 
 
  <p align="center">
-  <img src="https://github.com/360CVGroup/Inner-Adaptor-Architecture/blob/main/iaa/mmresult.png" width=90%/>
+  <img src="mmresult.png" width=90%/>
 </p>
 
 ### Results on Visual Grounding Benchmarks.
 <!-- grounding_re -->
 
  <p align="center">
-  <img src="https://github.com/360CVGroup/Inner-Adaptor-Architecture/blob/main/iaa/grounding_re.png" width=90%/>
+  <img src="grounding_re.png" width=90%/>
 </p>
 
 ### Comparison on text-only question answering.
 <!-- grounding_re -->
 
  <p align="center">
-  <img src="https://github.com/360CVGroup/Inner-Adaptor-Architecture/blob/main/iaa/NLPresult.png" width=90%/>
+  <img src="NLPresult.png" width=90%/>
 </p>
 
 ## Quick Start 🤗