Add model card for UniX

README.md

@@ -1,3 +1,49 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: any-to-any
+---
+
+# UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation
+
+UniX is a next-generation unified medical foundation model specifically designed for chest X-ray understanding and generation. It addresses the inherent conflict between semantic abstraction (understanding) and pixel-level reconstruction (generation) by decoupling the tasks into an autoregressive branch and a diffusion branch, coordinated via a cross-modal self-attention mechanism.
+
+- **Paper:** [UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation](https://huggingface.co/papers/2601.11522)
+- **Repository:** [https://github.com/ZrH42/UniX](https://github.com/ZrH42/UniX)
+
+## Highlights
+
+- **Decoupled Dual-Branch Architecture:** Unifies autoregressive understanding and diffusion-based generation to fundamentally resolve intrinsic task conflicts and feature interference.
+- **Superior Efficiency & Quality:** Achieves state-of-the-art performance with **only 25% of the parameters** compared to previous unified models like LLM-CXR, while boosting understanding (Micro-F1) by 46.1% and generation quality (FD-RadDino) by 24.2%.
+- **Cross-Modal Synergy:** Introduces a novel self-attention mechanism that enables dynamic semantic guidance for high-fidelity, continuous medical image synthesis.
+
+## Quick Start
+
+To set up the environment and run the model, follow the instructions from the official repository:
+
+1. **Install Environment** 
+   
+   ```bash
+   git clone https://github.com/ZrH42/UniX.git
+   cd UniX
+   conda create -n unix python=3.10 -y
+   conda activate unix
+   bash install.sh
+   ```
+   
+2. **Launch Gradio Demo**
+   ```bash
+   python demo_gradio.py
+   ```
+
+## Citation
+
+If you find UniX useful in your research, please cite:
+
+```bibtex
+@article{zhang2026unix,
+  title={UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation},
+  author={Zhang, Ruiheng and Yao, Jingfeng and Zhao, Huangxuan and Yan, Hao and He, Xiao and Chen, Lei and Wei, Zhou and Luo, Yong and Wang, Zengmao and Zhang, Lefei and Tao, Dacheng and Du, Bo},
+  journal={arXiv preprint arXiv:2601.11522},
+  year={2026}
+}
+```