arXiv Computation and Language September 21, 2026 By Haodi Lei, Yafu Li, Haoran Zhang, Shunkai Zhang, Qianjia Cheng, Xiaoye Qu, Ganqu Cui, Bowen Zhou, Ning Ding, Yun Luo, Yu Cheng

Draft-OPD: On-Policy Distillation for Speculative Draft Models

Read the original on arXiv Computation and Language →

Draft-OPD introduces an on‑policy distillation method for speculative draft models, addressing the mismatch between supervised fine‑tuning and inference by letting the target model supervise the drafter on draft‑induced states. The approach uses target‑assisted rollouts for stable continuations and replays drafting from error positions exposed during verification, enabling the drafter to learn from both accepted and rejected proposals. Experiments demonstrate that Draft‑OPD achieves more than five‑fold lossless acceleration across diverse tasks, outperforming prior draft models such as EAGLE‑3 and DFlash by 23 % and 13 % respectively.

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.

arXiv Computation and Language

Sep 1

ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding

arXiv:2608.29748v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which a...

By Luxi Lin, Zhanpeng Zeng, Shuang Peng, Songwei Liu, Rongrong Ji

llms rag diffusion

arXiv Machine Learning

Oct 21

DStill: Trajectory Consistency Distillation for Accelerated One-Step Drafting in Block Diffusion Speculative Decoding

arXiv:2610.27379v1 Announce Type: cross Abstract: Block-diffusion speculative decoding accelerates large language model inference by drafting multiple tokens in parallel. However, one-step drafting i...

By Shreyas Kulkarni, Uttam Gurram, Madhav Kanda, Krishna Teja Chitty Venkata, Shichu Chen, Kartik Balasubramaniam, Supriyo Chakraborty, Sambit Sahu

llms diffusion efficiency benchmarks

arXiv AI

Sep 15

Carryover Drafting: Recycling Rejected States for Speculative Decoding

arXiv:2609.14717v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept seve...

By Jahyun Koo, Sunghyeon Woo, Jaeeun Kil, Jeongtae Lee, Sungjae Lee, Kyomin Jung, Minsub Kim

llms rag

arXiv Machine Learning

Oct 8

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

Hugging Face Trending Papers

Jun 10

Teaching Diffusion to Speculate Left-to-Right

Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation. Speculative decoding addresses this bottleneck by employing a lightweight draft model to propose multiple future tokens that are subsequently verified in parallel by a larger target model.

llms diffusion benchmarks safety

arXiv Computation and Language

Sep 4

Margins, Not Windows: Training-Free Per-Step Lossy Speculative Decoding

The paper introduces AdaptiveSpec, a training‑free speculative decoding method that simultaneously adapts the per‑step verification rule and the draft‑tree shape using signals generated during decoding. It replaces the fixed token‑match rule with a margin‑based threshold and adjusts tree depth, width, and node count based on draft confidence and recent acceptance history, allowing the total draft count to vary. Experiments on SGLang show up to 56% throughput gains over EAGLE‑3 while maintaining 93% of lossless task accuracy on GSM8K, MATH‑500, and HumanEval across three models.

By Oszk\'ar Urb\'an, Young D. Kwon, Stylianos I. Venieris, Cecilia Mascolo

llms efficiency benchmarks