arXiv Computation and Language October 12, 2026 By Roy Eisenstadt, Harel Lidar, Tal Gonen, Omer Luxembourg, Itamar Zimerman, Lior Wolf, Eli David, Ilan Naiman

Contextual Correction of Parallel Draftsfor Speculative Decoding

Read the original on arXiv Computation and Language →

The paper introduces DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores intra-block dependencies in speculative decoding by evaluating multiple candidate tokens for contextual compatibility across adjacent draft positions. DCOCO maintains parallel drafting while enabling contextually informed token selection at low additional cost. Across multiple verifier backbones and benchmarks, DCOCO achieves the highest average throughput, delivering speedups of up to 6.6× over vanilla decoding and outperforming competing methods by 6–23% under concurrent serving loads.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers

Jul 21

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference. Recent work such as DFlash further boosts drafting efficiency by leveraging diffusion drafters, whose parallel denoising mechanism enables draft generation in a single forward pass.

llms diffusion efficiency benchmarks

arXiv Machine Learning

Jul 22

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

arXiv:2607. 19223v1 Announce Type: new Abstract: Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference.

By Yu-Yang Qian, Hao-Cong Wu, Chen Chen, Jiacheng Sun, Zhenhua Dong, Peng Zhao, Zhi-Hua Zhou

llms diffusion efficiency benchmarks

arXiv Machine Learning

Sep 22

H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache

arXiv:2609.24197v1 Announce Type: new Abstract: Speculative decoding losslessly accelerates large language model inference by having a lightweight draft model predict future tokens for verification b...

By Weifan Jiang, Krishna Teja Chitty-Venkata, Megan Flynn, Reed Meyerson, Zhenting Qi, Tianyu Wu, Eldar Kurtic, Minlan Yu, Alexandre Marques

llms diffusion efficiency

arXiv Machine Learning

Sep 30

SEED: Self-Speculative Decoding via Implicit Encoder-Decoder

arXiv:2609.36590v1 Announce Type: cross Abstract: Self-speculative decoding accelerates large language model (LLM) inference by drafting tokens from the target model itself, but faces a sharp tradeof...

By Hankun Lin, Patrick Pynadath, Ruqi Zhang

llms fine-tuning benchmarks

arXiv AI

Sep 30

LongSpark: Efficient speculative decoding with a fixed-cost parallel drafter

arXiv:2609.37029v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive inference by verifying multiple draft tokens in a single target forward pass. However, as the context...

By Hao-Yuan He, Peng-Fei Liu, Si Shen, Ming Li

llms diffusion benchmarks

arXiv Machine Learning

6d ago

Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds

The paper introduces the Expected Decoding Rounds (EDR) objective, a theoretical framework that models speculative decoding as a Markov reward process and directly optimizes the number of decoding rounds. EDR weights local rejection costs by state occupancies, eliminating auxiliary hyperparameters and enabling unbiased stochastic optimization via temporal‑difference gradients. Applying EDR to fine‑tune state‑of‑the‑art draft models (DSpark and DFly) improves mean accepted length and outperforms prior training objectives across nine benchmarks in math reasoning, code generation, and chat.

By Yunxiao Zhao, Changxiao Cai

llms fine-tuning benchmarks

One email a morning, machine-written

Related stories

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache

SEED: Self-Speculative Decoding via Implicit Encoder-Decoder

LongSpark: Efficient speculative decoding with a fixed-cost parallel drafter

Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds