Update README.md

README.md

@@ -3,16 +3,21 @@ license: mit
 ---
 
 <p align="center">
-  <img src="https://github.com/Gen-Verse/dLLM-RL/raw/main/assets/figure1.png" width="100%"/>
+  <img src="https://github.com/yinjjiew/Data/blob/main/dllm-rl/figure1.png" width="100%"/>
 </p>
 
 
-# Introduction to our ReasonFlux-Coders
+<p align="center">
+  <img src="https://github.com/yinjjiew/Data/blob/main/dllm-rl/maintable.png" width="100%"/>
+</p>
+
+
+# Introduction to TraDo
 
-We introduce **ReasonFlux-Coders**, trained with **CURE**, our algorithm for co-evolving an LLM's coding and unit test generation abilities.
+We introduce **TraDo**, SOTA diffusion language model, trained with **TraceRL**.
 
-* **ReasonFlux-Coder-7B** and **ReasonFlux-Coder-14B** outperform similarly sized Qwen Coders, DeepSeek Coders, and Seed-Coders, and naturally integrate into common test-time scaling and agentic coding pipelines.
-* **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/2506.03136)).
+* **TraDo-4B-Instruct** and **TraDo-8B-Instruct** outperform similarly sized strong AR models across math reasoning tasks.
+* **TraDo-8B-Thinking** is the first Long-CoT diffusion model.
 
 [Paper](https://arxiv.org/abs/2506.03136) | [Code](https://github.com/Gen-Verse/CURE)