Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
Lanxiang Hu, Zhaoxiang Feng, Yulun Wu +9
Speculative decoding (SD) accelerates autoregressive Large Language Models (LLMs) by drafting multiple tokens and verifying them in parallel, but it faces a scaling limitation: inc…
cs.CL2026
Dynamic Chunking for Diffusion Language Models
Yichen Zhu, Xiaoming Shi, Peng Zhao +3
Block discrete diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoising from across-block condi…