Add authors and paper highlights to model card (#1)

- Add authors and paper highlights to model card (0e40b3cb02329f33cae5c2567aa816a567d9bbb3)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,23 +1,33 @@
 ---
-license: mit
-tags:
-  - image-compression
-  - diffusion
-  - codec
-  - neural-compression
 language:
-  - en
+- en
+license: mit
 pipeline_tag: image-to-image
+tags:
+- image-compression
+- diffusion
+- codec
+- neural-compression
+- foundation-model
 ---
 
 <h2 align="center">CoD: A Diffusion Foundation Model for Image Compression</h2>
 
 <p align="center">
+  <a href="https://huggingface.co/papers/2511.18706"><img src="https://img.shields.io/badge/Paper-HF%20Paper%20Page-blue.svg" alt="Paper"></a>
   <a href="https://arxiv.org/abs/2511.18706"><img src="https://img.shields.io/badge/arXiv-2511.18706-b31b1b.svg" alt="arXiv"></a>
   <a href="https://github.com/microsoft/GenCodec/tree/main/CoD"><img src="https://img.shields.io/badge/Code-GitHub-blue.svg" alt="GitHub"></a>
 </p>
 
-**CoD** (**Co**mpression-oriented **D**iffusion) is the first diffusion foundation model designed and trained from scratch specifically for image compression. A lightweight condition encoder image-native features, a VQ information bottleneck compresses them into a compact bitstream, and a Diffusion Transformer reconstructs the image conditioned on the quantized representation.
+**CoD** (**Co**mpression-oriented **D**iffusion) is the first diffusion foundation model designed and trained from scratch specifically for image compression. It enables end-to-end optimization of both compression and generation.
+
+### Authors
+Zhaoyang Jia, Zihan Zheng, Naifu Xue, Jiahao Li, Bin Li, Zongyu Guo, Xiaoyi Zhang, Houqiang Li, Yan Lu
+
+### Key Advantages
+- **High compression efficiency**: Replaces Stable Diffusion in downstream codecs (like DiffC) to achieve SOTA results, especially at ultra-low bitrates (e.g., 0.0039 bpp).
+- **Low-cost and reproducible training**: 300$\times$ faster training than Stable Diffusion ($\sim$ 20 vs. $\sim$ 6,250 A100 GPU days) on entirely open image-only datasets.
+- **Architecture**: Features a lightweight condition encoder for image-native features, a VQ information bottleneck for compact bitstreams, and a Diffusion Transformer (DiT) for reconstruction.
 
 ## Available Models
 
@@ -141,4 +151,4 @@ python -m downstream.perceptual_loss_inference \
 
 ## License
 
-MIT
+MIT