Update README.md

README.md

@@ -1,10 +1,28 @@
 ---
 title: README
-emoji: 📉
-colorFrom: green
+emoji: 🚀
+colorFrom: red
 colorTo: red
 sdk: static
 pinned: false
+license: apache-2.0
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+🔥🔥 **Introducing MMR1** — a Multimodal Reasoning Model trained with **Variance-Aware Sampling (VAS)**  
+
+💡 **Highlights**  
+* **Variance-Aware Sampling (VAS)** for multimodal RL training:  
+  - Establishes a theoretical link between reward variance and gradient signal strength;
+  - Proposes the **Variance Promotion Score (VPS)** integrating Outcome Variance and Trajectory Diversity;
+  - Enables more efficient and stable optimization under limited data conditions.
+* Open-sources **~1.6M Long-CoT cold-start samples**, annotated by Gemini 2.5 Pro/Flash and verified with GPT-4o.
+* Releases a suite of **SFT and RL checkpoints** at multiple scales: 3B, 7B, and 32B variants.
+
+📦 **Resources**  
+* 📄 Paper: [MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources](https://huggingface.co/papers/2509.21268)  
+* 🚀 Model Checkpoints (SFT & RL):  
+  - [MMR1-3B-SFT](https://huggingface.co/MMR1/MMR1-3B-SFT)  | [MMR1-3B-RL](https://huggingface.co/MMR1/MMR1-3B-RL)  
+  - [MMR1-7B-SFT](https://huggingface.co/MMR1/MMR1-7B-SFT)  | [MMR1-7B-RL](https://huggingface.co/MMR1/MMR1-7B-RL)  
+  - [MMR1-32B-SFT](https://huggingface.co/MMR1/MMR1-32B-SFT) | **MMR1-32B-RL coming soon!**  
+* 📊 Datasets: [MMR1-SFT](https://huggingface.co/datasets/MMR1/MMR1-SFT), [MMR1-RL](https://huggingface.co/datasets/MMR1/MMR1-RL)  
+* 💻 Code: [GitHub - MMR1](https://github.com/LengSicong/MMR1)