Update README.md
Browse files
README.md
CHANGED
|
@@ -9,9 +9,6 @@ pinned: false
|
|
| 9 |
|
| 10 |
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.
|
| 11 |
|
| 12 |
-
|
| 13 |
-
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:
|
| 14 |
-
|
| 15 |
```bibtex
|
| 16 |
@article{arxiv'26:d3llm,
|
| 17 |
title = {d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation},
|
|
|
|
| 9 |
|
| 10 |
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.
|
| 11 |
|
|
|
|
|
|
|
|
|
|
| 12 |
```bibtex
|
| 13 |
@article{arxiv'26:d3llm,
|
| 14 |
title = {d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation},
|