Improve model card metadata and content

This PR improves the model card by:
- Adding the `pipeline_tag: text-generation` for better discoverability.
- Adding `library_name: transformers` metadata as the model is compatible with the library via `trust_remote_code=True`.
- Linking the model to its associated paper [DMax: Aggressive Parallel Decoding for dLLMs](https://huggingface.co/papers/2604.08302).
- Updating the README with highlights, a "Quick Start" usage example, and the BibTeX citation from the official repository.

README.md

@@ -1,9 +1,11 @@
 ---
-license: apache-2.0
-datasets:
-- Zigeng/DMax-LLaDA-2.0-Mini-Code-Trajectories
 base_model:
 - inclusionAI/LLaDA2.0-mini
+datasets:
+- Zigeng/DMax-LLaDA-2.0-Mini-Code-Trajectories
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
 <div align="center">
@@ -12,7 +14,7 @@ base_model:
   <a href="https://github.com/czg1225/DMax/blob/main/LICENSE">
     <img alt="Apache" src="https://img.shields.io/badge/License-Apache-4E94CE.svg">
   </a>
-  <a href="https://arxiv.org/pdf/2604.08302">
+  <a href="https://huggingface.co/papers/2604.08302">
     <img src="https://img.shields.io/badge/Paper-Arxiv-darkred.svg" alt="Paper">
   </a>
   <a href="https://github.com/czg1225/DMax">
@@ -21,10 +23,7 @@ base_model:
 </div>
 </div>
 
-> **DMax: Aggressive Parallel Decoding for dLLMs**  
-> [Zigeng Chen](https://czg1225.github.io/chenzigeng99/), [Gongfan Fang](https://fangggf.github.io/), [Xinyin Ma](https://horseee.github.io/), [Ruonan Yu](https://scholar.google.com/citations?user=UHP95egAAAAJ&hl=en), [Xinchao Wang](https://sites.google.com/site/sitexinchaowang/)  
-> [xML Lab](https://sites.google.com/view/xml-nus), National University of Singapore
-
+DMax is a new paradigm for efficient diffusion language models (dLLMs) that enables aggressive decoding parallelism while preserving generation quality. This repository contains the **DMax-Coder-16B** model, specialized for highly parallel code generation.
 
 ## 💪 Highlights
 
@@ -33,7 +32,7 @@ base_model:
 - **Soft Parallel Decoding**: Uses interpolation between mask and token embeddings to propagate confidence priors from previous steps.
 
 <div align="center">
-  <img src="assets/tradeoff.png" width="100%" />
+  <img src="https://github.com/czg1225/DMax/raw/main/assets/tradeoff.png" width="100%" />
   <br>
   <em>Superior Parallelism-Accuracy Trade-off, Increased TPF with Maintained Accuracy.</em>
 </div>
@@ -66,7 +65,14 @@ model = model.to(torch.bfloat16)
 model.eval()
 tokenizer = AutoTokenizer.from_pretrained("Zigeng/DMax-Coder-16B", trust_remote_code=True)
 
-prompt = "Write a python function to find the first repeated character in a given string." + "\n\nPlease enclose your code within delimiters as follows:\n```python\n# YOUR CODE HERE\n```\n\n"
+prompt = "Write a python function to find the first repeated character in a given string." + "
+
+Please enclose your code within delimiters as follows:
+```python
+# YOUR CODE HERE
+```
+
+"
 
 input_ids = tokenizer.apply_chat_template(
     [{"role": "user", "content": prompt}],
@@ -91,7 +97,16 @@ print(generated_answer)
 print("nfe:",nfe,"token length",len(generated_tokens[0]))
 ```
 
-## 📖 Experimental Results
-
-![trade-off](assets/exp.png)
-
+## 📖 Citation
+
+```bibtex
+@misc{chen2026dmaxaggressiveparalleldecoding,
+      title={DMax: Aggressive Parallel Decoding for dLLMs}, 
+      author={Zigeng Chen and Gongfan Fang and Xinyin Ma and Ruonan Yu and Xinchao Wang},
+      year={2026},
+      eprint={2604.08302},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2604.08302}, 
+}
+```