Update README.md

README.md

@@ -17,12 +17,6 @@
 
 
 
-<h4 align="center">
-    <p>
-        <a href="./README_ZH.md">简体中文</a> |
-        <b>English</b>
-    <p>
-</h4>
 
 
 -----
@@ -41,7 +35,7 @@ Yuan3.0 Ultra enhances the Reflection Inhibition Reward Mechanism (RIRM) propose
 
 Additionally, the <a href="./Docs/Yuan3.0_Ultra Paper.pdf">**technical report**</a> for Yuan3.0 Ultra has been released, which provides more detailed technical specifications and evaluation results.
 
-<div align=center> <img src=https://github.com/Yuan-lab-LLM/Yuan3.0-Ultra/blob/main/Docs/Yuan3.0-Ultra-architecture.png width=80% />
+<div align=center>   <img src="https://huggingface.co/YuanLabAI/Yuan3.0-Ultra/resolve/main/docs/Yuan3.0-Ultra-architecture.png" width="80%" />
 
 Fig.1: Yuan3.0 Ultra Multimodal Architecture
 
@@ -67,7 +61,7 @@ Fig.1: Yuan3.0 Ultra Multimodal Architecture
 
 Yuan3.0 Ultra delivers outstanding performance on retrieval-augmented generation, multimodal document understanding, tabular data analysis, content summarization, and tool invocation tasks, providing core capability support for enterprises building document-driven and data-driven Agent applications. Detailed evaluation results are presented in Section 5.
 
-<div align=center> <img src=https://github.com/Yuan-lab-LLM/Yuan3.0-Ultra/blob/main/Docs/Yuan3.0-Ultra-benchmarks.png width=80% />
+<div align=center>  <img src="https://huggingface.co/YuanLabAI/Yuan3.0-Ultra/resolve/main/docs/Yuan3.0-Ultra-benchmarks.png" width="80%" />
 
 Fig.2: Benchmark Evaluation Results of Yuan3.0 Ultra