English
Related papers

Related papers: DynaMo: Accelerating Language Model Inference with…

200 papers

Current auto-regressive models can generate high-quality, topologically precise meshes; however, they necessitate thousands-or even tens of thousands-of next-token predictions during inference, resulting in substantial latency. We introduce…

Graphics · Computer Science 2025-08-07 Dian Chen , Yansong Qu , Xinyang Li , Ming Li , Shengchuan Zhang

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their widespread application is hindered by the resource-intensive decoding process. To address this challenge, current approaches have…

Computation and Language · Computer Science 2024-04-19 Ziqian Zeng , Jiahong Yu , Qianshi Pang , Zihao Wang , Huiping Zhuang , Hongen Shao , Xiaofeng Zou

To reduce the computational and memory overhead of Large Language Models, various approaches have been proposed. These include a) Mixture of Experts (MoEs), where token routing affects compute balance; b) gradual pruning of model…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-16 Mohamed Wahib , Muhammed Abdullah Soyturk , Didem Unat

Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…

Computation and Language · Computer Science 2025-12-08 Tianyi Li , Mingda Chen , Bowei Guo , Zhiqiang Shen

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…

Machine Learning · Computer Science 2025-02-10 Justin Deschenaux , Caglar Gulcehre

Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach,…

Computation and Language · Computer Science 2019-10-04 Rui Wang , Masao Utiyama , Eiichiro Sumita

Diffusion LLMs have emerged as a promising alternative to conventional autoregressive LLMs, offering significant potential for improved runtime efficiency. However, existing diffusion models lack the ability to provably enforce…

Machine Learning · Computer Science 2025-05-30 Tarun Suresh , Debangshu Banerjee , Shubham Ugare , Sasa Misailovic , Gagandeep Singh

Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregressive (AR) models that generate tokens sequentially,…

Machine Learning · Computer Science 2026-01-09 Gen Li , Changxiao Cai

Accelerating the inference of large language models (LLMs) has been a critical challenge in generative AI. Speculative decoding (SD) substantially improves LLM inference efficiency. However, its utility is limited by a fundamental…

Computation and Language · Computer Science 2026-05-05 Sibo Xiao , Jinyuan Fu , Zhongle Xie , Lidan Shou

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Computation and Language · Computer Science 2024-05-24 Yufan Jiang , Qiaozhi He , Xiaomin Zhuang , Zhihua Wu , Kunpeng Wang , Wenlai Zhao , Guangwen Yang

Autoregressive language models dominate modern text generation, yet their sequential nature introduces fundamental limitations: decoding is slow, and maintaining global coherence remains challenging. Diffusion models offer a promising…

Computation and Language · Computer Science 2026-01-06 Viacheslav Meshchaninov , Egor Chimbulatov , Alexander Shabalin , Aleksandr Abramov , Dmitry Vetrov

In this paper, we presents a novel method for improving text-to-image generation by combining Large Language Models (LLMs) with diffusion models, a hybrid approach aimed at achieving both higher quality and efficiency in image synthesis…

Computation and Language · Computer Science 2025-02-04 Julian Perry , Frank Sanders , Carter Scott

This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings…

Computation and Language · Computer Science 2026-04-07 Nicolas Calbucura , Jose Guillen , Valentin Barriere

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Computation and Language · Computer Science 2025-03-03 Rachel Wicks , Kartik Ravisankar , Xinchen Yang , Philipp Koehn , Matt Post

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Subhasis Dasgupta , Hetvi Waghela

We introduce UGen, a unified autoregressive multimodal model that demonstrates strong performance across text processing, image understanding, and image generation tasks simultaneously. UGen converts both texts and images into discrete…

Computation and Language · Computer Science 2025-03-28 Hongxuan Tang , Hao Liu , Xinyan Xiao

Recent research has shown that large language models pretrained using unsupervised approaches can achieve significant performance improvement on many downstream tasks. Typically when adapting these language models to downstream tasks, like…

Computation and Language · Computer Science 2022-06-08 Xiaodi Sun , Sunny Rajagopalan , Priyanka Nigam , Weiyi Lu , Yi Xu , Belinda Zeng , Trishul Chilimbi

Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling…

Computation and Language · Computer Science 2025-02-12 Jacob K Christopher , Brian R Bartoldson , Tal Ben-Nun , Michael Cardei , Bhavya Kailkhura , Ferdinando Fioretto

We introduce Dream 7B, the most powerful open diffusion large language model to date. Unlike autoregressive (AR) models that generate tokens sequentially, Dream 7B employs discrete diffusion modeling to refine sequences in parallel through…

Computation and Language · Computer Science 2025-08-22 Jiacheng Ye , Zhihui Xie , Lin Zheng , Jiahui Gao , Zirui Wu , Xin Jiang , Zhenguo Li , Lingpeng Kong

Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…

Sound · Computer Science 2023-12-06 Pavel Andreev , Nicholas Babaev , Azat Saginbaev , Ivan Shchekotov , Aibek Alanov