English
Related papers

Related papers: DynaMo: Accelerating Language Model Inference with…

200 papers

The autoregressive nature of conventional large language models (LLMs) inherently limits inference speed, as tokens are generated sequentially. While speculative and parallel decoding techniques attempt to mitigate this, they face…

Artificial Intelligence · Computer Science 2024-10-22 Aishwarya P S , Pranav Ajit Nair , Yashas Samaga , Toby Boyd , Sanjiv Kumar , Prateek Jain , Praneeth Netrapalli

Inference with modern Large Language Models (LLMs) is expensive and time-consuming, and speculative sampling has proven to be an effective solution. Most speculative sampling methods such as EAGLE use a static draft tree, implicitly…

Computation and Language · Computer Science 2024-07-02 Yuhui Li , Fangyun Wei , Chao Zhang , Hongyang Zhang

Autoregressive language models accumulate errors due to their fixed, irrevocable left-to-right token generation. To address this, we propose a new sampling method called Resample-Previous-Tokens (RPT). RPT mitigates error accumulation by…

Machine Learning · Computer Science 2025-06-09 Itai Gat , Neta Shaul , Uriel Singer , Yaron Lipman

Diffusion models have demonstrated significant potential in achieving state-of-the-art performance across various text generation tasks. In this systematic study, we investigate their application to the table-to-text problem by adapting the…

Computation and Language · Computer Science 2024-09-24 Aleksei S. Krylov , Oleg D. Somov

Multimodal models have been proven to outperform text-based models on learning semantic word representations. Almost all previous multimodal models typically treat the representations from different modalities equally. However, it is…

Computation and Language · Computer Science 2018-01-03 Shaonan Wang , Jiajun Zhang , Chengqing Zong

Large language models (LLMs) have revolutionized natural language processing and broadened their applicability across diverse commercial applications. However, the deployment of these models is constrained by high inference time in…

Computation and Language · Computer Science 2024-11-12 Euiin Yi , Taehyeon Kim , Hongseok Jeung , Du-Seong Chang , Se-Young Yun

Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency -…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Zhangyin Feng , Runyi Hu , Liangxin Liu , Fan Zhang , Duyu Tang , Yong Dai , Xiaocheng Feng , Jiwei Li , Bing Qin , Shuming Shi

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Computation and Language · Computer Science 2024-08-20 Xukun Liu , Bowen Lei , Ruqi Zhang , Dongkuan Xu

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

To enhance reasoning capabilities, previous works have explored incorporating special-purpose tokens into the training process. These strategies strengthen the learning mechanism of transformer-based large language models (LLMs). Building…

Computation and Language · Computer Science 2025-08-12 Eunki Kim , Sangryul Kim , James Thorne

This paper investigates the enhancement of reasoning capabilities in language models through token-level multi-model collaboration. Our approach selects the optimal tokens from the next token distributions provided by multiple models to…

Artificial Intelligence · Computer Science 2025-08-27 Chao Hao , Zezheng Wang , Yanhua Huang , Ruiwen Xu , Wenzhe Niu , Xin Liu , Zitong Yu

Diffusion models have emerged as the leading approach for text-to-image generation. However, their iterative sampling process, which gradually morphs random noise into coherent images, introduces significant latency that limits their…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Peijie Qiu , Hariharan Ramshankar , Arnau Ramisa , René Vidal , Amit Kumar K C , Vamsi Salaka , Rahul Bhagat

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Machine Learning · Computer Science 2025-05-27 Yixuan Wang , Yijun Liu , Shiyu ji , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Sound · Computer Science 2024-04-02 Xiang Li , Fan Bu , Ambuj Mehrish , Yingting Li , Jiale Han , Bo Cheng , Soujanya Poria

Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…

Computation and Language · Computer Science 2021-09-22 Giulio Zhou , Gerasimos Lampouras

Masked diffusion models have demonstrated competitive results on various tasks including language generation. However, due to its iterative refinement process, the inference is often bottlenecked by slow and static sampling speed. To…

Machine Learning · Computer Science 2026-03-09 Seo Hyun Kim , Sunwoo Hong , Hojung Jung , Youngrok Park , Se-Young Yun

Speculative decoding aims to speed up autoregressive generation of a language model by verifying in parallel the tokens generated by a smaller draft model.In this work, we explore the effectiveness of learning-free, negligible-cost draft…

Machine Learning · Computer Science 2024-11-07 Lawrence Stewart , Matthew Trager , Sujan Kumar Gonugondla , Stefano Soatto

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

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinder their applications to text-to-speech deployment. Through…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-14 Rongjie Huang , Zhou Zhao , Huadai Liu , Jinglin Liu , Chenye Cui , Yi Ren

We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…

Machine Learning · Computer Science 2025-10-08 Nima Fathi , Torsten Scholak , Pierre-André Noël
‹ Prev 1 3 4 5 6 7 10 Next ›