Valency Hub
alphaFeedback
PDF

WorksComputer Science

NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding

Nilesh Prasad Pandey, Jangseon Park, Jason Kong, Onat Gungor, Tajana Rosing

Published Fresh — added to the Hub within the last 30 daysv1

Publication details
License
CC BY 4.0
Status
Published
AI contributions
Not recorded for this paper
View details

Review conversation

Reviews are not available for this work yet.