English
Related papers

Related papers: Superposed Decoding: Multiple Generations from a S…

200 papers

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any…

Machine Learning · Computer Science 2023-05-22 Yaniv Leviathan , Matan Kalman , Yossi Matias

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Computation and Language · Computer Science 2026-03-06 Jia-Nan Li , Jian Guan , Wei Wu , Chongxuan Li

Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive…

Computation and Language · Computer Science 2025-11-05 Jameson Sandler , Jacob K. Christopher , Thomas Hartvigsen , Ferdinando Fioretto

Large language models (LLMs) are often equipped with multi-sample decoding strategies. An LLM implicitly defines an arithmetic code book, facilitating efficient and embarrassingly parallelizable \textbf{arithmetic sampling} to produce…

Artificial Intelligence · Computer Science 2025-04-29 Aditya Parashar , Aditya Vikram Singh , Avinash Amballa , Jinlin Lai , Benjamin Rozonoyer

Recent works have revealed the great potential of speculative decoding in accelerating the autoregressive generation process of large language models. The success of these methods relies on the alignment between draft candidates and the…

Computation and Language · Computer Science 2025-09-15 Jikai Wang , Zhenxu Tian , Juntao Li , Qingrong Xia , Xinyu Duan , Zhefeng Wang , Baoxing Huai , Min Zhang

Massive parameters of LLMs have made inference latency a fundamental bottleneck. Speculative decoding represents a lossless approach to accelerate inference through a guess-and-verify paradigm. Some methods rely on additional architectures…

Computation and Language · Computer Science 2025-05-27 Xianzhen Luo , Yixuan Wang , Qingfu Zhu , Zhiming Zhang , Xuanyu Zhang , Qing Yang , Dongliang Xu

It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation to re-sample after a rejection, or distort the distribution of outputs by constraining…

Computation and Language · Computer Science 2025-10-09 Daniel Melcer , Sujan Gonugondla , Pramuditha Perera , Haifeng Qian , Wen-Hao Chiang , Yanjun Wang , Nihal Jain , Pranav Garg , Xiaofei Ma , Anoop Deoras

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models.…

Computation and Language · Computer Science 2025-01-24 Yi Cheng , Xiao Liang , Yeyun Gong , Wen Xiao , Song Wang , Yuji Zhang , Wenjun Hou , Kaishuai Xu , Wenge Liu , Wenjie Li , Jian Jiao , Qi Chen , Peng Cheng , Wayne Xiong

Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration. Retrieval-based SD methods, one kind of model-free method, have yielded promising speedup, but they often rely on incomplete…

Computation and Language · Computer Science 2024-12-17 Yuxuan Hu , Ke Wang , Xiaokang Zhang , Fanjin Zhang , Cuiping Li , Hong Chen , Jing Zhang

Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While…

Computation and Language · Computer Science 2024-08-01 Yuchen Li , Alexandre Kirchmeyer , Aashay Mehta , Yilong Qin , Boris Dadachev , Kishore Papineni , Sanjiv Kumar , Andrej Risteski

Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context. While standard autoregressive decoding is slow due to its sequential nature, the…

Computation and Language · Computer Science 2026-04-30 Theodore Glavas , Nikhita Vedula , Dushyanta Dhyani , Yilun Zhu , Shervin Malmasi

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the…

Computation and Language · Computer Science 2025-02-06 Andrea Santilli , Silvio Severino , Emilian Postolache , Valentino Maiorca , Michele Mancusi , Riccardo Marin , Emanuele Rodolà

Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces additional latency…

Computation and Language · Computer Science 2025-12-15 Nikhil Bhendawade , Kumari Nishu , Arnav Kundu , Chris Bartels , Minsik Cho , Irina Belousova

Deliberation is a common and natural behavior in human daily life. For example, when writing papers or articles, we usually first write drafts, and then iteratively polish them until satisfied. In light of such a human cognitive process, we…

Software Engineering · Computer Science 2022-09-15 Fangwen Mu , Xiao Chen , Lin Shi , Song Wang , Qing Wang

Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Speculative decoding mitigates this cost through a draft-verify…

Machine Learning · Computer Science 2025-12-18 Zicong Cheng , Guo-Wei Yang , Jia Li , Zhijie Deng , Meng-Hao Guo , Shi-Min Hu

In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. Taking inspiration from autoregressive generative models that predict the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Yassine Ouali , Céline Hudelot , Myriam Tami

As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…

Computation and Language · Computer Science 2025-10-06 Guanghao Li , Zhihui Fu , Min Fang , Qibin Zhao , Ming Tang , Chun Yuan , Jun Wang

A recent study showed that large language models (LLMs) can reconstruct surprisingly long texts - up to thousands of tokens - via autoregressive generation from just one trained input embedding. In this work, we explore whether…

Computation and Language · Computer Science 2025-11-04 Gleb Mezentsev , Ivan Oseledets

Standard decoders for neural machine translation autoregressively generate a single target token per time step, which slows inference especially for long outputs. While architectural advances such as the Transformer fully parallelize the…

Computation and Language · Computer Science 2020-10-06 Nader Akoury , Kalpesh Krishna , Mohit Iyyer

Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to early pruning of relevant prefixes under finite-beam…

Information Retrieval · Computer Science 2026-05-26 Kidist Amde Mekonnen , Yongkang Li , Yubao Tang , Simon Lupart , Maarten de Rijke