SpecBlock achieves 8-13% higher mean speedup than EAGLE-3 at 44-52% drafting cost via block-iterative drafting with hidden-state inheritance, dynamic rank-head branching, valid-prefix masking, and optional cost-aware bandit adaptation.
Learning harmonized represen- tations for speculative sampling
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
KERV integrates kinematic Kalman Filter predictions with speculative decoding in VLA models to achieve 27-37% faster inference while maintaining nearly the same task success rates.
Three training interventions for diffusion drafters raise accepted draft length 21-76% over uniform baseline on reasoning, code, and dialogue tasks.
DREAM-S combines neural architecture search, target-aware supernet training, and attention-entropy-guided distillation to accelerate speculative decoding in VLMs, reporting up to 3.85x speedup over standard methods.
PPOW uses window-level RL with cost-aware speedup and proximity rewards plus adaptive divergence-aware windowing to reach 6.29-6.52 acceptance lengths and 3.39-4.36x speedups in speculative decoding.
SMART expands speculative decoding trees only when a node's marginal benefit-cost ratio exceeds current tree-level speedup, claiming ~15–20% extra wall-clock speedup without quality loss.
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
-
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
SpecBlock achieves 8-13% higher mean speedup than EAGLE-3 at 44-52% drafting cost via block-iterative drafting with hidden-state inheritance, dynamic rank-head branching, valid-prefix masking, and optional cost-aware bandit adaptation.
-
KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
KERV integrates kinematic Kalman Filter predictions with speculative decoding in VLA models to achieve 27-37% faster inference while maintaining nearly the same task success rates.
-
Teaching Diffusion to Speculate Left-to-Right
Three training interventions for diffusion drafters raise accepted draft length 21-76% over uniform baseline on reasoning, code, and dialogue tasks.
-
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
DREAM-S combines neural architecture search, target-aware supernet training, and attention-entropy-guided distillation to accelerate speculative decoding in VLMs, reporting up to 3.85x speedup over standard methods.
-
Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing
PPOW uses window-level RL with cost-aware speedup and proximity rewards plus adaptive divergence-aware windowing to reach 6.29-6.52 acceptance lengths and 3.39-4.36x speedups in speculative decoding.
-
SMART: When is it Actually Worth Expanding a Speculative Tree?
SMART expands speculative decoding trees only when a node's marginal benefit-cost ratio exceeds current tree-level speedup, claiming ~15–20% extra wall-clock speedup without quality loss.
-
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.