DPara is a PSD framework that reuses effective parallel drafters yet guarantees backbone--verification overlap in every round, thereby eliminating this probabilistic fallback altogether and surpassing the strongest serial and parallel speculative decoding baselines alike.
Abstract
DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every round. Parallel speculative decoding (PSD) overlaps drafting with verification, yet existing methods must guess the accepted prefix and bonus token in advance: a wrong guess reverts the whole batch to serial drafting. We present DPara, a PSD framework that reuses effective parallel drafters yet guarantees backbone--verification overlap in every round, thereby eliminating this probabilistic fallback altogether. While the target verifies, DPara's diffusion backbone precomputes draft representations for every acceptance boundary with the bonus left unspecified; a lightweight autoregressive head then combines the revealed verification outcome with the matching precomputed representation to emit the next round's draft tokens almost instantly---fully parallelizing the dominant backbone forward with verification and leaving only the negligible head cost serial. Experiments on Qwen3-8B and Qwen3-14B across seven math, coding, and chat benchmarks show that DPara achieves average speedups of $3.21\times$ and $3.52\times$ over autoregressive decoding, surpassing the strongest serial and parallel speculative decoding baselines alike.
This work introduces LongSpark, a block-diffusion drafter that achieves state-of-the-art end-to-end efficiency across multiple model scales and realistic serving conditions by extracting fixed-size, multiscale views from the target's verification pass, thereby eliminating the need for a growing persistent state.
Hao-Yuan He, Peng-Fei Liu, Si-Shi Shen et al.· 0 citations
DEdit is introduced, a diffusion-based drafter that can not only draft by conventional parallel unmasking but also iteratively edit its draft through token-to-token predictions, and ProposalMix, a training scheme that mixes draft predictions with ground-truth tokens based on first-pass confidence during training.
Long-Xuan Yu, Bingsen Chen, Peng Shi et al.· arXiv.org· 1 citation
DSpine is proposed, a drafter with causal conditioning injection throughout the backbone: at every layer, gated adjacent injection writes each predecessor's predicted feature into its successor, so the causal conditioning chain unfolds over network depth while all positions update in parallel.
Hao-Hui Zhang, Ke-Yu Chen, Hao-Cheng Sun et al.· 1 citation
Carryover Drafting is introduced, a parallel draft--verify--draft training that exposes the drafter to inference-aligned rejected states while preserving parallelism across training positions.
Jahyun Koo, Sunghyeon Woo, J. Kil et al.· 1 citation
Speculative decoding accelerates large language model inference by drafting future tokens cheaply and verifying them with the target model in parallel. Block drafters score a whole block of future tokens in one forward pass, yet standard decoding verifies only the top-scoring chain and discards the other candidates. Be...
Looped language models repeatedly apply a weight-shared block to increase effective depth without increasing parameter count, but the resulting T sequential recurrent-block calls per generated token substantially increase decoding latency. To address the issue, we introduce Wavefront Decoding (WFD), a training-free sel...
Hyeongju Ha, Jae-Joon Kim· 1 citation
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.