DEdit is a diffusion-based drafter for that not only generates drafts in parallel but also iteratively edits them using bidirectional context. This allows later tokens to fix earlier errors before the target model verifies, extending the accepted prefix. The training scheme, ProposalMix, mixes draft predictions with ground truth to teach the editor when to preserve or revise tokens. Across seven benchmarks on Qwen3-4B and Qwen3-8B, DEdit achieves the highest macro-average speedup among evaluated drafters, with 5.72x and 5.97x over autoregressive generation.
Iterative draft editing speeds up speculative language model decoding
DEdit repairs parallel token proposals using later draft tokens as context, increasing acceptance before target-model verification.
Big Tech
Longxuan Yu · Bingsen Chen · Peng Shi · Dongkyu Lee · Yi Xiang · Hideo Kobayashi · +6 more
University of California, Riverside · Amazon Web Services · New York University
Research Digest··2 min read
In one line
DEdit improves speculative decoding speed by iteratively editing drafts with bidirectional context, achieving over 5.7x speedup on Qwen3 models.
Before you read this
Two ideas this paper builds onRead it as
Yu, Chen and colleagues introduce DEdit, a diffusion-based drafter that revises an entire speculative draft before an autoregressive language model verifies it.
uses a small model to propose several tokens, then asks the larger target model to verify them in parallel.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.