Update README.md

README.md

@@ -2,4 +2,38 @@
 license: apache-2.0
 datasets:
 - Junwei-Xi/DDA-Training-Set
----
+---
+# Dual Data Alignment (NeurIPS'25 Spotlight)
+
+This repository contains the official checkpoint (`DDA_ckpt.pth`) for the paper **"Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable"**, accepted by **NeurIPS 2025 as a Spotlight**.
+
+[![GitHub](https://img.shields.io/badge/GitHub-Project%20Page-black?logo=github)](https://github.com/roy-ch/Dual-Data-Alignment)
+[![arXiv](https://img.shields.io/badge/arXiv-2505.14359-b31b1b.svg)](https://arxiv.org/abs/2505.14359)
+
+## 📄 Model Details
+
+- **Model File**: `DDA_ckpt.pth`
+- **Paper**: [Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable](https://arxiv.org/abs/2505.14359)
+
+## 🚀 Performance
+
+DDA achieves state-of-the-art performance across 11 benchmarks, including 4 in-the-wild datasets.
+
+| Metric | GenImage | DDA-COCO | ... | **Avg ACC** |
+| :--- | :---: | :---: | :---: | :---: |
+| **DDA (Ours)** | **91.7%** | **92.2%** | ... | **90.7%** |
+
+*Notably, DDA is the first detector to achieve over 80% cross-data accuracy on the Chameleon benchmark.*
+
+## 📚 Citation
+
+If you find this model useful, please cite our paper:
+```code
+@inproceedings{chen2025dual,
+  title={Dual Data Alignment Makes {AI}-Generated Image Detector Easier Generalizable},
+  author={Ruoxin Chen and Junwei Xi and Zhiyuan Yan and Ke-Yue Zhang and Shuang Wu and Jingyi Xie and Xu Chen and Lei Xu and Isabel Guan and Taiping Yao and Shouhong Ding},
+  booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
+  year={2025},
+  url={[https://openreview.net/forum?id=C39ShJwtD5](https://openreview.net/forum?id=C39ShJwtD5)}
+}
+```