Initialize model card

README.md

@@ -1,3 +1,45 @@
 ---
-license: mit
+license: other
+library_name: pytorch
+pipeline_tag: text-generation
+tags:
+  - discrete-diffusion
+  - diffusion-language-model
+  - self-correction
+  - scdd
+  - icml-2026
+datasets:
+  - openwebtext
 ---
+
+# SCDD
+
+This repository contains the released checkpoints for **Generalized Discrete Diffusion with Self-Correction**.
+
+SCDD is a self-correcting discrete diffusion language model. It learns to revise incorrect visible tokens directly during generation, preserving parallel decoding without a remasking step.
+
+## Checkpoints
+
+| File | Model | Uniform noise ratio |
+| --- | --- | --- |
+| `checkpoints/scdd_pu_0.1.ckpt` | SCDD (0.1) | `p_u = 0.1` |
+| `checkpoints/scdd_pu_0.2.ckpt` | SCDD (0.2) | `p_u = 0.2` |
+
+The checkpoint filenames intentionally use `scdd` naming for the public release.
+
+## Code
+
+Code and evaluation scripts are available at:
+
+<https://github.com/laaaarrywang/Self-Correcting-Discrete-Diffusion>
+
+## Citation
+
+```bibtex
+@article{wang2026generalized,
+  title={Generalized Discrete Diffusion with Self-Correction},
+  author={Wang, Linxuan and Wang, Ziyi and Bai, Yikun and Deng, Wei and Lin, Guang and Song, Qifan},
+  journal={arXiv preprint arXiv:2603.02230},
+  year={2026}
+}
+```