Update README.md

README.md

@@ -7,4 +7,17 @@ sdk: static
 pinned: false
 ---
 
-We introduce a novel recipe for building an ultra-fast diffusion language model named [d3LLM](https://github.com/hao-ai-lab/d3llm) (pseuDo-Distilled Diffusion LLM) 🚀, a new metric [AUP (Accuracy Under Parallelism)](https://hao-ai-lab.github.io/blogs/text-diffusion/) that captures both accuracy and parallelism📊, along with a [Leaderboard](https://huggingface.co/spaces/d3LLM/dLLM_Leaderboard) 🏆 for various diffusion LLMs.
+We introduce a novel recipe for building an ultra-fast diffusion language model named [d3LLM](https://github.com/hao-ai-lab/d3llm) (pseuDo-Distilled Diffusion LLM) 🚀, a new metric [AUP (Accuracy Under Parallelism)](https://hao-ai-lab.github.io/blogs/text-diffusion/) that captures both accuracy and parallelism📊, along with a [Leaderboard](https://huggingface.co/spaces/d3LLM/dLLM_Leaderboard) 🏆 for various diffusion LLMs.
+
+
+If you find our d3LLM or the AUP metric useful for your research, please ⭐️ star [our project](https://github.com/hao-ai-lab/d3LLM) and cite our work:
+
+```bibtex
+@article{arxiv'26:d3llm,
+  title   = {d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation},
+  author  = {Yu-Yang Qian and Junda Su and Lanxiang Hu and Peiyuan Zhang and Zhijie Deng and Peng Zhao and Hao Zhang},
+  journal = {ArXiv preprint},
+  volume  = {arXiv:2601.07568},
+  year    = {2026}
+}
+```