Open access
Jul 2026
Uncertainty-Aware Speculative Decoding for Diffusion Language Models in Long Document Generation
Uncertainty-Aware Speculative Decoding for Diffusion Language Models (UASD-DLM), a complementary inference scheduler for long document generation that improves the speed-memory trade-off over fixed-depth speculative decoding and recovers technical-term accuracy lost by summary-free windowing.
Yu-Gyeom Kim
· Computer Life · 0 citations