Showing 2026Show all
3 papers · 1 filter
cs.CL2026
UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding
Chumeng Liang, Linxuan Wang, Xinyu Peng +6
Speculative decoding accelerates language model inference by verifying multiple draft tokens in a single target-model pass. Recent parallel drafters have achieved breakthrough perf…
cs.CL2026
DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
Ziyi Wang, Siva Rajesh Kasa, Ankith M S +6
Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottleneck…
cs.LG2026
Generalized Discrete Diffusion with Self-Correction
Linxuan Wang, Ziyi Wang, Yikun Bai +3
Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correcti…