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.
Recursive speculative decoding: Accelerating llm inference via sampling without replacement.arXiv preprint arXiv:2402.14160
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
UniVer frames tree-based speculative decoding as conditional optimal transport, proving it is lossless with optimal acceptance rates and delivering 4.2-8.5% longer accepted sequences than standard rejection sampling.
Cactus uses constrained optimization to guarantee bounded divergence from the verifier LLM distribution during speculative sampling, raising acceptance rates without the distortion seen in typical acceptance sampling.
ConFu boosts speculative decoding acceptance rates 8-20% over EAGLE-3 by letting draft models use contemplate tokens and MoE to anticipate future generation direction.
citing papers explorer
-
Cost-Aware Diffusion Draft Trees for Speculative Decoding
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.
-
UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
UniVer frames tree-based speculative decoding as conditional optimal transport, proving it is lossless with optimal acceptance rates and delivering 4.2-8.5% longer accepted sequences than standard rejection sampling.
-
Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
Cactus uses constrained optimization to guarantee bounded divergence from the verifier LLM distribution during speculative sampling, raising acceptance rates without the distortion seen in typical acceptance sampling.
-
ConFu: Contemplate the Future for Better Speculative Sampling
ConFu boosts speculative decoding acceptance rates 8-20% over EAGLE-3 by letting draft models use contemplate tokens and MoE to anticipate future generation direction.