Upload README.md

README.md

@@ -1,7 +1,7 @@
 # ChartX & ChartVLM
 
 <div align=center>
-<img src="https://img-blog.csdnimg.cn/direct/c3f44dade40b48d98e1df100cad2bf7b.png" height="40%">
+<img src="https://github.com/UniModal4Reasoning/ChartVLM/blob/main/assets/ChartX-logo.png?raw=true" height="40%">
 </div>
 
 
@@ -15,7 +15,7 @@ ChartX presents two primary contributions.
 - (2) We develop ChartVLM, offering a new perspective on handling the multi-modal tasks that strongly depend on interpretable patterns such as reasoning tasks in the field of chart or geometric images. To augment the model’s interpretability in cognition tasks in chart domain, ChartVLM incorporates the intermediate chart representations such as CSV data, chart title, chart type, etc.
 
 <div align=center>
-<img src="https://github.com/UniModal4Reasoning/ChartVLM/blob/main/assets/motivation.png" height="85%">
+<img src="https://github.com/UniModal4Reasoning/ChartVLM/blob/main/assets/motivation.png?raw=true" height="85%">
 </div>
 
 ------------------------
@@ -59,7 +59,7 @@ ChartX
 <summary> Visualization of Data Distribution</summary>
 
 <div align=center>
-<img src="https://github.com/UniModal4Reasoning/ChartVLM/blob/main/assets/tsne.png" height="85%">
+<img src="https://raw.githubusercontent.com/UniModal4Reasoning/ChartVLM/main/assets/tsne.png" height="85%">
 </div>
 
 </details>
@@ -80,7 +80,7 @@ ChartX
 - **(2)** To choose the task that users expect to perform according to the prompts they used, the instruction adapter is designed, which can cover a variety of user instructions as illustrated in this figure
 
 <div align=center>
-<img src="https://github.com/UniModal4Reasoning/ChartVLM/blob/main/assets/chartvlm.png" height="85%">
+<img src="https://github.com/UniModal4Reasoning/ChartVLM/blob/main/assets/chartvlm.png?raw=true" height="85%">
 </div>
 
 ## 快速开始（Qiuckstart）