Signals 4 · free daily AI digest

RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding

Paper recorded by Signals 4 on 2026-09-18 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-18 on arXiv · recorded by Signals 4 on 2026-09-21

Category: cs.CL · 自然语言处理 · first seen 2026-09-21

Abstract

Speculative decoding accelerates LLM inference by drafting multiple tokens in parallel, with tree-based methods further improving efficiency through hierarchical structures. Dynamic-tree methods such as EAGLE-3 perform well under greedy decoding via deterministic top-K expansion and global pruning. However, in stochastic decoding (T>0), this mechanism collapses the draft distribution into one-hot

Read on arXiv →

#8 most recent of 200 cs.CL papers we have recorded · ↑ newer: Reusing Latent Speech Representations for Query-Conditioned Topic Loca · ↓ older: CASCADE Against Jailbreaks: Combination Across Stages with Controlled
Cite this page: RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding: the #8 most recent of 200 cs.CL papers we have recorded (as of 2026-09-18). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/rheosampling-resolving-the-one-hot-dilemma-in-stochastic-dynamic-tree-speculativ.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions