pith. sign in

arXiv preprint arXiv:2604.02047 , year=

Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding , author= · arXiv 2604.02047

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

clear filters

representative citing papers

Cost-Aware Diffusion Draft Trees for Speculative Decoding

cs.CL · 2026-06-01 · unverdicted · novelty 7.0

CaDDTree jointly selects tree structure and budget to maximize expected tokens per unit time in speculative decoding, proving unimodality under convex verification cost and matching oracle DDTree performance on Qwen models.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Cost-Aware Diffusion Draft Trees for Speculative Decoding cs.CL · 2026-06-01 · unverdicted · none · ref 16

    CaDDTree jointly selects tree structure and budget to maximize expected tokens per unit time in speculative decoding, proving unimodality under convex verification cost and matching oracle DDTree performance on Qwen models.