Update README.md

README.md

@@ -3,10 +3,17 @@ license: mit
 library_name: transformers
 ---
 
+<p align="center">
+  <img src="https://github.com/yinjjiew/Data/raw/main/cure/overviewplot.png" width="100%"/>
+</p>
+
+
 <p align="center">
   <img src="https://github.com/yinjjiew/Data/raw/main/cure/results.png" width="100%"/>
 </p>
 
+[Paper](https://arxiv.org/abs/2505.15809) | [Code](https://github.com/Gen-Verse/CURE)
+
 
 
 # Introduction to our ReasonFlux-Coders
@@ -17,7 +24,6 @@ We introduce **ReasonFlux-Coders**, trained with **CURE**, our algorithm for co-
 * **ReasonFlux-Coder-4B** is our Long-CoT model, outperforming Qwen3-4B while achieving 64.8% efficiency in unit test generation. We have demonstrated its ability to serve as a reward model for training base models via reinforcement learning (see our [paper](https://arxiv.org/abs/2505.15809)).
 
 
-[Paper](https://arxiv.org/abs/2505.15809) | [Code](https://github.com/Gen-Verse/CURE)
 
 # Citation