Speculative Decoding

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

10 new papers

A weekly snapshot of new work published in Speculative Decoding.

Period ending 2026-09-14

12 new papers

A weekly snapshot of new work published in Speculative Decoding.

Period ending 2026-09-07

21 new papers

A weekly snapshot of new work published in Speculative Decoding.

Inside this field

Focused directions

Focused topic

Speculative Decoding

Within Speculative Decoding

156 papersExplore

Focused topic

Self-Speculative

Within Speculative Decoding

56 papersExplore

Focused topic

Autoregressive Decoding

Within Speculative Decoding

44 papersExplore

Focused topic

Drafter

Within Speculative Decoding

18 papersExplore

230 papers

Latest in Speculative Decoding

Browse all topics →

A Generalized Formalism of Auto-Regressive Decoding for Speech Processing
Jun 16, 2026Julia Gachot, Philipp Allgeuer, Marie S. Bauer +1Autoregressive Decoding Autoregressive Model
Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition
Jun 16, 2026Hiroyuki Deguchi, Takatomo Kano, Katsuki Chousa +1Autoregressive Decoding Bayesian
Accelerating Speculative Diffusions via Block Verification
Jun 11, 2026Alexander Soen, Hisham Husain, Valentin De Bortoli +1Diffusion Language Models Speculative Decoding
ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
Jun 11, 2026Sihwa Lee, Janghwan Lee, Donghoon Yoo +4Fp8 Autoregressive Decoding
VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
Jun 10, 2026Yuchen Xian, Yang He, Yunqiu Xu +1Speculative Decoding LLM Inference Efficiency
MemNovo: Look Back at the Spectrum for Balanced De Novo Peptide Sequencing from Mass Spectrometry
Jun 10, 2026Dongxin Lyu, Jingbo Zhou, Hongxin Xiang +2Cyclic Peptides Tandem Mass Spectra
Teaching Diffusion to Speculate Left-to-Right
Jun 10, 2026Lexington Whalen, Yuki Ito, Ryo SakamotoSpeculative Decoding Diffusion Language Models
CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference
Jun 9, 2026Xuezhen Xie, Zhiqiang ZhouNext-Token Prediction LLM Inference Efficiency
Detecting Speculative Language in Biomedical Texts using Recurrent Neural Tensor Networks
Jun 9, 2026Dhruv DixitBiomedical Text Recurrent Neural Networks
AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding
Jun 7, 2026Yingxuan Ren, Yuxuan Lou, Yong Liu +4Diffusion Language Models Autoregressive Decoding
EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification
Jun 6, 2026Da Li, Xinxin Li, Xingyu Cui +3Symbolic Regression Neuro-Symbolic Framework
Cost-Aware Speculative Execution for LLM-Agent Workflows: An Integrated Five-Dimension Method
Jun 5, 2026Faisal FareedSelf-Speculative Agentic Workflows
WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing
Jun 5, 2026Young D. Kwon, Miles Williams, Rui Li +2Speculative Decoding LLM Inference Efficiency
DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models
Jun 4, 2026Zhuoming Liu, Jinhong Lin, Kwan Man Cheng +3Residual Adaptation Autoregressive Decoding
AdaPLD: Adaptive Retrieval and Reuse for Efficient Model-Free Speculative Decoding
Jun 4, 2026Runheng Liu, Jincheng Xie, Wen Hu +2Speculative Decoding Reuse
Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edge
Jun 3, 2026Haotian Zheng, Zhanwei Wang, Mingyao Cui +3Heterogeneous Edge Devices Wireless Resource Allocation
D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models
Jun 3, 2026Liyuan Zhang, Jiarui Zhang, Jinwei Yao +6Speculative Decoding Diffusion Language Models
TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding
Jun 2, 2026Peer Rheinboldt, Frédéric Berdoz, Roger WattenhoferSpeculative Decoding Flash
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Jun 2, 2026Lorenz K. Muller, Philippe Bich, Chiara Boretti +3Key-Value Cache Quantization Autoregressive Decoding
Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning
Jun 2, 2026Yanyu Zhu, Hoilam Pao, Niu Hu +6Speculative Decoding LLM Inference Efficiency
SimSD: Simple Speculative Decoding in Diffusion Language Models
Jun 1, 2026Junxia Cui, Haotian Ye, Runchu Tian +9Diffusion Language Models Speculative Decoding
Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools
Jun 1, 2026Bardia Mohammadi, Lars Klein, Akhil Arora +1Tool Invocation Call
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
Jun 1, 2026Jiebin Zhang, Zhenghan Yu, Song Liu +9Speculative Decoding LLM Inference Efficiency
Cost-Aware Diffusion Draft Trees for Speculative Decoding
Jun 1, 2026Shuai Zhang, Huachuan Qiu, Hongliang He +1Speculative Decoding Diffusion Language Models
Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
May 31, 2026Xin Su, Dawid Majchrowski, Fangyuan Yu +5Speculative Decoding LLM Inference Efficiency
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
May 30, 2026Zining Liu, Yunhai Hu, Tianhua Xia +4Speculative Decoding Autoregressive Generation
TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding
May 30, 2026Zhuoyu Wang, Junnan Huang, Xinyu ChenSpeculative Decoding Low-Latency Systems
Mellum2 Technical Report
May 29, 2026Marko Kojic, Ivan Bondyrev, Aral de Moor +6Mixture-Of-Expert Language Models Mixture-of-Experts Models
Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism
May 29, 2026Yijiong Yu, Huazheng Wang, Shuai Yuan +2Speculative Decoding Self-Speculative
BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding
May 29, 2026Liang He, Jingbo Wen, Qishi Zhan +4Speculative Decoding Graphics Processing Unit Memory
Speculative Decoding Across Languages
May 28, 2026Nirajan Paudel, Michael Ginn, Luc De Nardi +1Speculative Decoding Multilingual
Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
May 28, 2026Soowon Oh, Nam Cao, Yujin Kim +4Speculative Decoding Token Budgets
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
May 28, 2026Jianuo Huang, Yaojie Zhang, Qituan Zhang +3Speculative Decoding Causal Attention
Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based Thresholding
May 28, 2026Jeong Hun Yeo, Minsu Kim, Hyeongseop Rha +1Llm-Based Automatic Speech Recognition Autoregressive Decoding
Draft-OPD: On-Policy Distillation for Speculative Draft Models
May 28, 2026Haodi Lei, Yafu Li, Haoran Zhang +8Speculative Decoding Self-Speculative
DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution
May 27, 2026Yunhai Hu, Zining Liu, Xiangyang Yin +5Self-Speculative Multimodal Reasoning
Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs
May 26, 2026Wenhui Tan, Minghao Li, Xiaoqian Ma +5Next-Token Prediction LLM Inference Efficiency
Stateful Inference for Low-Latency Multi-Agent Tool Calling
May 25, 2026Victor NorgrenTool Low-Latency Systems
SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?
May 25, 2026Zihang Zhou, Ziqian Ren, Yukai Wu +7Repository Large Language Model Agents
Beyond the Target: From Imitation to Collaboration in Speculative Decoding
May 24, 2026Jinze Li, Yixing Xu, Guanchen Li +7Speculative Decoding LLM Inference Efficiency
SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
May 21, 2026Mehrdad Saberi, Keivan Rezaei, Soheil FeiziSelf-Speculative Multi-Hop Reasoning
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
May 19, 2026Yuhao Shen, Tianyu Liu, Xinyi Hu +9Speculative Decoding Heterogeneous Pruning Scores
FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
May 19, 2026Yaojie Zhang, Jianuo Huang, Junlong Ke +5Speculative Decoding LLM Inference Efficiency
KVBuffer: IO-aware Serving for Linear Attention
May 18, 2026Longwei Zou, Lin ZhongQuadratic Attention Speculative Decoding
VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
May 17, 2026Jiayi Yao, Samuel Shen, Kuntai Du +7Key-Value Cache LLM Inference Efficiency
Delay-Adaptive Speculation Control for Low-Latency Edge-Cloud LLM Inference
May 17, 2026Kangkang Sun, Jianhua Li, Xiuzhen Chen +2Self-Speculative Speculative Decoding
Lever: Speculative LLM Inference on Smartphones
May 16, 2026Tuowei Wang, Fengzu Li, Yanfan Sun +2LLM Inference Efficiency Inference Latency
Skim: Speculative Execution for Fast and Efficient Web Agents
May 15, 2026Mike Wong, Kevin Hsieh, Suman Nath +1Web Agents Web
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
May 15, 2026Shengyin Sun, Yiming Li, Renxi Liu +7Diffusion Language Models Speculative Decoding
KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy
May 14, 2026Yingbing Huang, Tharun Adithya Srikrishnan, Steven K. Reinhardt +1Key-Value Cache Compression Autoregressive Decoding
An Interpretable Latency Model for Speculative Decoding in LLM Serving
May 14, 2026Linghao Kong, Megan Flynn, Michael Peng +3Large Language Model Serving Speculative Decoding
Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing
May 14, 2026Jie Jiang, Xing Sun, Ruotian Chen +2Speculative Decoding LLM Inference Efficiency
Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding
May 14, 2026Xun Fang, Yunchen Li, Hang Yuan +1Diffusion Language Models Speculative Decoding
Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
May 13, 2026Shuoyang Sun, Chang Dai, Hao Fang +6Speculative Decoding LLM Inference Efficiency
Multi-Token Residual Prediction
May 12, 2026Yufeng Xu, Zishuo Bao, Qian Wang +6Diffusion Language Models Next-Token Prediction
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
May 12, 2026Tianyu Wu, Yu Yao, Zhenting Qi +7Speculative Decoding Parallel
BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion
May 12, 2026Shaobin Zhuang, Yuang Ai, Jiaming Han +7Autoregressive Language Models Speculative Decoding
CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration
May 11, 2026Yuning Han, Yangchenchen Jin, Dylan Zhao +1Speculative Decoding LLM Inference Efficiency
SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding
May 11, 2026Anton Plaksin, Sergei Krutikov, Sergei Skvortsov +1Speculative Decoding LLM Inference Efficiency
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
May 11, 2026Shuzhang Zhong, Haochen Huang, Shengxuan Qiu +3Large Language Model Reasoning Tree-Of-Thoughts

Jun 16, 2026 · cs.SDJ/K move · Enter open · S save

A Generalized Formalism of Auto-Regressive Decoding for Speech Processing

Julia Gachot, Philipp Allgeuer, Marie S. Bauer, Stefan Wermter

Knowledge Technology, Department of Informatics, University of Hamburg, Germany

In speech processing, most state-of-the-art sequence prediction models rely on auto-regressive (AR) strategies to generate output sequences based on the raw predictions of the model. Despite their crucial role in the inference process, a comprehensive overview of AR strategies as a unified field is lacking, due largely to implicit and multiple definitions of next-token decoding. This context complicates the choice, comparison, and evaluation of strategies, while creating inconsistencies in the characterization of approaches as auto-regressive or not. We begin by setting explicit inclusion criteria for the field of AR search in speech processing, and derive a generalized theoretical framework to categorize and report on search strategies for neural models. We show the capabilities of this formalism in simplifying the design of benchmarks centered around the decoding process, allowing for ablation studies that are focused on search strategies.

Autoregressive Decoding Autoregressive Model Sequence Modeling Theoretical Foundations Formalization

Open paper Ask about it PDF