1
S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation
块扩散语言模型新突破：无需训练的自推测解码，兼顾质量与速度，少步数下比标准方法更稳健。
arXiv:2603.25702v2 Announce Type: replace Abstract: Block-diffusion language models offer a promising path toward faster-than-autoregressive generatio…