Improve model card: add arXiv ID, H1 title, and update paper links (#4)

- Improve model card: add arXiv ID, H1 title, and update paper links (e2b375f5ff3bb6b6244e07ba4d14cbdfd9dbc3e3)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,29 +1,32 @@
 ---
-license: cc-by-nc-4.0
 language:
 - en
+library_name: transformers
+license: cc-by-nc-4.0
 pipeline_tag: text-generation
 tags:
 - text diffusion model
 - language model
 - code generation
-library_name: transformers
+arxiv: 2510.03270
 ---
 
+# CoDA: Coding LM via Diffusion Adaptation
+
 <p align="center">
   <img alt="coda-logo" src="https://raw.githubusercontent.com/weirayao/CoDA/main/CoDA-logo.png">
 </p>
 
 <p align="center">
   <a href="https://github.com/SalesforceAIResearch/CoDA"><strong>Try CoDA</strong></a> ·
-  <a href="https://github.com/SalesforceAIResearch/CoDA/blob/main/technical_report.pdf"><strong>Technical Report</strong></a> ·
+  <a href="https://huggingface.co/papers/2510.03270"><strong>Paper</strong></a> ·
   <a href="https://huggingface.co/collections/Salesforce/coda-68d627d87921c0e28a69e340"><strong>Model Collection</strong></a> ·
   <a href="https://github.com/SalesforceAIResearch/CoDA/blob/main/README.md"><strong>GitHub Repository</strong></a>
 </p>
 
 <br>
 
-Welcome to CoDA, Salesforce AI Research's diffusion-based language model designed for powerful code generation and bidirectional context understanding.
+Welcome to CoDA, Salesforce AI Research's diffusion-based language model designed for powerful code generation and bidirectional context understanding, presented in the paper [CoDA: Coding LM via Diffusion Adaptation](https://huggingface.co/papers/2510.03270).
 
 We're releasing CoDA as a lightweight yet capable model:
 - `CoDA-1.7B-Instruct` — optimized for code generation tasks with bidirectional diffusion modeling (1.7B parameters)
@@ -34,29 +37,29 @@ CoDA leverages discrete diffusion processes to enable understanding of both past
 > [!NOTE]
 > This model card is dedicated to the `CoDA-1.7B-Instruct` model. Check out our [model collection](https://huggingface.co/collections/Salesforce/coda-68d627d87921c0e28a69e340) for other variants.
 
-# ⭐️ Highlights
+# ⭐ Highlights
 
-* **Bidirectional Context Understanding:** Leverage discrete diffusion processes to understand both past and future tokens, enabling superior code completion.
-* **Confidence-Guided Sampling:** Maintain competitive inference latency through intelligent sampling strategies that balance quality and speed.
-* **Lightweight Architecture:** Achieve strong performance with only 1.7B parameters, making it accessible for researchers with limited computational resources.
-* **Full Training Pipeline:** Complete reproducible training pipeline from pre-training to fine-tuning, enabling customization for specific domains.
-* **Optimized for Code:** Specifically designed and trained for code generation tasks, with strong performance on HumanEval, MBPP, and other coding benchmarks.
+*   **Bidirectional Context Understanding:** Leverage discrete diffusion processes to understand both past and future tokens, enabling superior code completion.
+*   **Confidence-Guided Sampling:** Maintain competitive inference latency through intelligent sampling strategies that balance quality and speed.
+*   **Lightweight Architecture:** Achieve strong performance with only 1.7B parameters, making it accessible for researchers with limited computational resources.
+*   **Full Training Pipeline:** Complete reproducible training pipeline from pre-training to fine-tuning, enabling customization for specific domains.
+*   **Optimized for Code:** Specifically designed and trained for code generation tasks, with strong performance on HumanEval, MBPP, and other coding benchmarks.
 
 ---
 
 ## 📊 Model Details
 
-- **Model Size**: 1.7B parameters
-- **Architecture**: Diffusion-based language model
-- **Training**: TPU-based pre-training with GPU fine-tuning
-- **Primary Use**: Code generation and completion tasks
+-   **Model Size**: 1.7B parameters
+-   **Architecture**: Diffusion-based language model
+-   **Training**: TPU-based pre-training with GPU fine-tuning
+-   **Primary Use**: Code generation and completion tasks
 
 ## ✨ Key Features
 
-- **Bidirectional Context**: Diffusion modeling enables understanding of both past and future tokens
-- **Confidence-Guided Sampling**: Maintains competitive inference latency through intelligent sampling
-- **Lightweight Design**: Achieves strong performance with fewer parameters than comparable models
-- **Open Training Pipeline**: Fully reproducible training from pre-training to fine-tuning
+-   **Bidirectional Context**: Diffusion modeling enables understanding of both past and future tokens
+-   **Confidence-Guided Sampling**: Maintains competitive inference latency through intelligent sampling
+-   **Lightweight Design**: Achieves strong performance with fewer parameters than comparable models
+-   **Open Training Pipeline**: Fully reproducible training from pre-training to fine-tuning
 
 ## 📈 Performance
 
@@ -191,8 +194,6 @@ bash eval_mbpp_humaneval.sh
 ```
 ## 📚 Citation
 
-Technical report coming soon. For now, please cite:
-
 ```bibtex
 @misc{coda2025,
   title={CoDA: Coding LM via Diffusion Adaptation},
@@ -204,7 +205,7 @@ Technical report coming soon. For now, please cite:
 
 ## 🔗 Resources
 
-- 📄 **Technical Report**: [technical_report.pdf](https://github.com/SalesforceAIResearch/CoDA/blob/main/technical_report.pdf)
+- 📄 **Paper**: [huggingface.co/papers/2510.03270](https://huggingface.co/papers/2510.03270)
 - 💻 **Code Repository**: [github.com/SalesforceAIResearch/CoDA](https://github.com/SalesforceAIResearch/CoDA)
 - 🤗 **Model Hub**: [Salesforce CoDA collection](https://huggingface.co/collections/Salesforce/coda-68d627d87921c0e28a69e340)