accept-until-fail

Tag

Cards List
#accept-until-fail

Spec-AUF: Accept-Until-Fail Training under Train-Inference Misalignment for Masked Block Drafters

arXiv cs.AI · 2026-07-03 Cached

The paper introduces AUF (Accept-Until-Fail), a simple modification to the cross-entropy loss for masked block drafters in speculative decoding that restricts supervision to the prefix up to the first predicted failure, improving average emitted length across benchmarks without changing inference.

0 favorites 0 likes
← Back to home

Submit Feedback