Overview

Autoregressive decoding studies how models choose and produce each next token or code from the context generated so far, shaping output quality, diversity, and latency. Common approaches include greedy and beam search, stochastic sampling, constrained generation, and speculative decoding, which drafts several tokens or paths for parallel verification; related methods exploit spatial structure or change decoding order for images and speech. Systems work reduces costs through KV-cache compression, sparse attention, and hardware-aware kernels, with evaluation spanning language reasoning and code tasks, image fidelity, speech quality, and end-to-end throughput. A central tension is whether relaxed verification and added parallelism can deliver real speedups without changing useful output behavior, since exact token matching, task accuracy, and free-running quality do not always agree.

Latest papers

CardsList

60 papers6 papers in the last four weeks, down 45% on the four weeks before. 0.0% of all new papers.

  1. Typing Matters: Muscle, Language and Typing Behaviour in Live Keystroke Decoding from sEMG

    Nov 13, 2026Abhilash Durgam, Nyle Siddiqui, Mubarak Shah +1Surface ElectromyographyAutoregressive Decoding

  2. On the Difficulty of Sequence-Level Supervised Learning for Autoregressive Language Models

    Nov 12, 2026Mathieu Blondel, Michaël E. Sander, Germain Vivier-Ardisson +2moment matchingAutoregressive Language Modeling

  3. On the Fundamental Limits of Prefill-Based Decoding Length Prediction

    Oct 29, 2026Haowen Shi, Xuzhe Yan, Fahao Chen +1LLM Inference SchedulingAutoregressive Decoding

  4. Dynamic Multi-Step Decoding for Time-Series Foundation Models

    Oct 25, 2026Birmjune Kim, Hyungju Lee, Hyun Oh SongTime Series ForecastingTime-Series Foundation Models

  5. ProVe: Proposer-Verifier Decoding

    Oct 20, 2026Ziqi Jin, Weiwen Xu, Jiaxi Li +3LLM Inference AccelerationSpeculative Decoding

  6. WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding

    Oct 14, 2026Chenxu Wang, Hangyi Kuang, Bo-Wen Yin +6Vision-Language GroundingAutoregressive Decoding

  7. Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation

    Oct 12, 2026Xiahui Zhu, Zhenyi Qi, Wanwei Liu +4Autoregressive DecodingAutoregressive Language Modeling

  8. Lossless Inference Acceleration for ASR via EAGLE-Style Speculative Decoding

    Oct 9, 2026Sen Zhang, Xianghu Yue, Yiming Chen +3Automatic Speech RecognitionAutoregressive Decoding

  9. Nucleus Speculative Decoding: Plausibility-Aware Verification Beyond Exact Distribution

    Oct 6, 2026Shuhao Li, Fanghua Ye, Wanyu Lin +2Speculative DecodingLLM Inference Acceleration

  10. DLoop: Looped Speculative Decoding

    Oct 6, 2026Geonmo Gu, Byeongho Heo, HeeJae Jun +4Speculative DecodingLLM Inference Acceleration

  11. RVQ Position Aware Speculative Decoding for On Device Text to Speech

    Sep 29, 2026Berkin Durmus, Eduardo Pacheco, Zach Nagengast +1TTS SynthesisStreaming TTS Synthesis

  12. One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting?

    Sep 20, 2026Ziang Li, Yue Huang, Guoxu Zhou +4Long-Term Time Series ForecastingTime Series Forecasting

  13. Self-Orchestrating Language Models: Leveraging Semantic Dependence for Efficient Inference

    Sep 13, 2026Tian JinAutoregressive DecodingEfficient Language Model Reasoning

  14. OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation

    Sep 11, 2026Xiangrui Yang, Cheng Peng, Yunfeng Zhao +9Linear AttentionAutoregressive Decoding

  15. Line-Coupled Language Model

    Sep 7, 2026Shiyuan Li, Shaorong Zhang, Zhaorui Yang +3Multi-Token PredictionLanguage Model Decoding

  16. Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations

    Sep 3, 2026Yoto Fujita, Simon Leglaive, Laurent GirinSpeech EnhancementAutoregressive Decoding

  17. GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning

    Sep 1, 2026Wenjian Wu, Zesheng Jia, Jiaying Tang +2Combinatorial OptimizationVehicle Routing

  18. SHSP: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear Programming

    Aug 26, 2026Zherong Zhang, Guanlin Li, Chengrui Gao +5Mixed-Integer Linear ProgrammingNeural Combinatorial Optimization

  19. Grounded Decoding for Autoregressive Speech Enhancement via Adaptive Code-Space Grounding and Local LLM Refinement

    Aug 21, 2026Hao Shi, Yuan Gao, Zhaoheng Ni +4Speech EnhancementSpeech Language Models

  20. ReLMCodec: Designing Predictable Speech Tokens from Pre-Quantization Phoneme Structure

    Aug 8, 2026Zixiang Wan, Xusheng Yang, Zheng Wang +1Neural Audio CodecsAudio Tokenization

  21. Approximate Speculative Decoding

    Aug 4, 2026Yuannuo Feng, Zegang Peng, Yuxin Xie +5Speculative DecodingLLM Inference Acceleration