SpecRoll accelerates GRPO rollouts with future-token heads plus a gradient-free Reflex memory, achieving 1.21x to 2.04x end-to-end speedup over vanilla GRPO while preserving the target sampling distribution.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SpecRoll: Fast-Slow Verifier-Feedback Adaptation for Speculative Reinforcement Learning Rollouts
SpecRoll accelerates GRPO rollouts with future-token heads plus a gradient-free Reflex memory, achieving 1.21x to 2.04x end-to-end speedup over vanilla GRPO while preserving the target sampling distribution.