DeLS-Spec: Decoupled Long-Short Contexts for Parallel Speculative Drafting
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(南京航空航天大学人工智能学院);MIIT Key Laboratory of Pattern Analysis and Machine Intelligence(工业和信息化部模式分析与机器智能重点实验室);The Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education(教育部脑机智能技术重点实验室)
Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel. Block-parallel drafters such as DFlash further improve drafting efficiency by predicting an entire block in one pass, but their position-wise predictions lack explicit intra-block causal conditioning. Recent methods such as Domino and DSpark attempt to introduce such causality into block-parallel drafting, but they require training the draft model from scratch, which limits their flexibility and increases training cost. We propose DeLS-Spec, a decoupled long-short context speculative decoding method. DeLS-Spec treats the fixed DFlash model as a long-context expert and introduces a lightweight local head as a short-context expert. The local head can be trained independently with a standard next-token prediction objective, without joint training with the target model or the DFlash backbone, leading to extremely low training cost. At inference time, DeLS-Spec combines long-context and short-context logits, and the local head is not tied to a specific DFlash checkpoint, making the method more modular and flexible. Experiments on Qwen3 models show that DeLS-Spec consistently improves speedup and average acceptance length over DFlash across math, code, and dialogue benchmarks.
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
Institute for Artificial Intelligence(人工智能研究院);Department of Computer Science and Technology(计算机科学与技术系);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);ModelBest Inc.(模佰科技);Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心);Tsinghua University(清华大学)
DFlow: Enabling Verifier Information Flow in Block Diffusion Speculative Decoding
Peking University(北京大学);University of Electronic Science and Technology of China(电子科技大学);Shanghai Jiao Tong University(上海交通大学);Institute of Computational Social Science, Peking University (Qingdao)(北京大学(青岛)计算社会科学研究所)
DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
Courant Institute of Mathematical Sciences, New York University(纽约大学数学科学学院);Tandon School of Engineering, New York University(纽约大学工程学院);Cerebras Systems Inc.(Cerebras Systems公司);University of Pennsylvania(宾夕法尼亚大学)
Thinking with Drafting: Optical Decompression via Logical Reconstruction
Shenyang Institute of Computing Technology, Chinese Academy of Sciences(中国科学院沈阳计算技术研究所);University of Chinese Academy of Sciences 3 ByteDance 4 Westlake University(中国科学院大学 3 字节跳动 4 西湖大学);Key Laboratory of Computing Power Network(计算功率网络重点实验室);Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences)(信息安全,教育部,山东计算机科学中心(济南国家超级计算中心),齐鲁工业大学(山东省科学院))
FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
EPIC Lab, SJTU(上海交通大学EPIC实验室);UESTC;School of Software Engineering, HUST(华中科技大学软件工程学院);Tsinghua University(清华大学);HKUST(GZ)(香港科技大学(广州));Shanghai AI Laboratory(上海人工智能实验室)
Learning to Draft: Adaptive Speculative Decoding with Reinforcement Learning
National Key Laboratory for Multimedia Information Processing, Peking University(多媒体信息处理国家级重点实验室,北京大学);School of Computer Science, Peking University(计算机科学学院,北京大学);Microsoft Research Asia(微软亚洲研究院)
AdaSpec: Adaptive Speculative Decoding for Fast, SLO-Aware Large Language Model Serving
Tongji University(同济大学);Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen(深圳大数据研究院,香港中文大学(深圳));Huazhong University of Science and Technology(华中科技大学);School of Data Science, The Chinese University of Hong Kong, Shenzhen(数据科学学院,香港中文大学(深圳))
CLaSp: In-Context Layer Skip for Self-Speculative Decoding
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Singapore University of Technology and Design(新加坡科技设计大学);School of Biomedical Engineering, UNSW Sydney(新南威尔士大学生物医学工程学院)