ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models

Paper recorded by Signals 4 on 2026-10-14 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-14 on arXiv · recorded by Signals 4 on 2026-10-15

Category: cs.CL · 自然语言处理 · first seen 2026-10-15

Abstract

Speculative decoding accelerates autoregressive generation by drafting multiple tokens per step, yet feature-based drafters rely on target hidden features whose contextual emphasis may not align with the needs of subsequent draft positions. Hybrid linear attention (HLA) models maintain compact recurrent states that accumulate historical associations, offering an efficient source of complementary c

Read on arXiv →