Update README.md

README.md

@@ -36,7 +36,7 @@ By exporting the **vision encoder** into ONNX and TensorRT engines, we significa
 The MiniVLA deployment is designed with modular microservices:  
 
 <p align="center">
-  <img src="System_Architecture.svg" width="100%">
+  <img src="System_Architecture.svg">
 </p>
 
 
@@ -49,7 +49,7 @@ The MiniVLA deployment is designed with modular microservices:
 ### Hybrid Acceleration
 
 <p align="center">
-  <img src="MiniVLA_Architecture.svg" width="100%">
+  <img src="MiniVLA_Architecture.svg">
 </p>
 
 
@@ -79,6 +79,13 @@ The MiniVLA deployment is designed with modular microservices:
 
 ---
 
+
+## 🔗 Related Project
+
+For full implementation and code, please visit the companion GitHub repository:  
+👉 [https://github.com/Zhenxintao/MiniVLA](https://github.com/Zhenxintao/MiniVLA)
+
+
 ## 🚀 Usage
 
 ### Load Hugging Face Qwen-0.5B
@@ -148,9 +155,4 @@ If you use **MiniVLA** in your research or deployment, please cite:
 
 We also acknowledge and thank the authors of [Stanford-ILIAD/minivla-vq-libero90-prismatic](https://huggingface.co/Stanford-ILIAD/minivla-vq-libero90-prismatic), which serves as the base for the checkpoints included in this repository.  
 
----
-
-## 🔗 Related Project
-
-For full implementation and code, please visit the companion GitHub repository:  
-👉 [https://github.com/Zhenxintao/MiniVLA](https://github.com/Zhenxintao/MiniVLA)
+---