Update README.md

README.md

@@ -9,6 +9,10 @@ pinned: true
 
 **We are looking for collaboration and compute donation! Contact drluodian@gmail.com if you want to vibe researching with us.**
 
+-**[2025-4]** 🔥🔥 Introducing **`LLaVA-Critic-R1`**: A family of generative critic VLM trained through GRPO using pairwise critic data. LLaVA-Critic-R1 not only demonstrates strong critic capability, but also achieves SoTA policy performance at the 7B scale.
+
+    [💻 GitHub](https://github.com/LLaVA-VL/LLaVA-NeXT/tree/main/llava-critic-r1) | [🤗 Model and Dataset](https://huggingface.co/collections/lmms-lab/llava-critic-r1-68922484e5822b89fab4aca1) | [📖 Paper](https://arxiv.org/abs/2509.00676)
+
 - **[2025-4]** 🔈🔈 Introducing **`Aero-1-Audio`**: It is a compact audio model adept at various audio tasks, including speech recognition, audio understanding, and following audio instructions. 
 
     [📚 Blog](https://www.lmms-lab.com/posts/aero_audio/) | [🤗 Model Checkpoints](https://huggingface.co/lmms-lab/Aero-1-Audio-1.5B) | [📖 Evaluation Results](https://github.com/EvolvingLMMs-Lab/lmms-eval/pull/658) | [📚 Cookbook](https://www.lmms-lab.com/posts/lmms-lab-docs/aero_audio/)