d3LLM

We introduce a novel recipe for building an ultra-fast diffusion language model named d3LLM (pseuDo-Distilled Diffusion LLM) 🚀, a new metric AUP (Accuracy Under Parallelism) that captures both accuracy and parallelism📊, along with a Leaderboard 🏆 for various diffusion LLMs.

@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}
}