English
Related papers

Related papers: Accelerating Diffusion LLMs via Adaptive Parallel …

200 papers

Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a single model call. PTP…

Computation and Language · Computer Science 2026-03-06 Felix Draxler , Justus Will , Farrin Marouf Sofian , Theofanis Karaletsos , Sameer Singh , Stephan Mandt

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…

Computation and Language · Computer Science 2025-06-12 Jui-Ming Yao , Hao-Yuan Chen , Zi-Xian Tang , Bing-Jia Tan , Sheng-Wei Peng , Bing-Cheng Xie , Shun-Feng Su

Despite the crucial importance of accelerating text generation in large language models (LLMs) for efficiently producing content, the sequential nature of this process often leads to high inference latency, posing challenges for real-time…

Computation and Language · Computer Science 2024-05-27 Mahsa Khoshnoodi , Vinija Jain , Mingye Gao , Malavika Srikanth , Aman Chadha

Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify them in parallel. However, conventional sequential…

Computation and Language · Computer Science 2026-05-20 Yaojie Zhang , Jianuo Huang , Junlong Ke , Yuhang Han , Yongji Long , Tianchen Zhao , Biqing Qi , Linfeng Zhang

The interest in combining model-based control approaches with diffusion models has been growing. Although we have seen many impressive robotic control results in difficult tasks, the performance of diffusion models is highly sensitive to…

Robotics · Computer Science 2026-02-04 Yutaka Shimizu , Masayoshi Tomizuka

When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge the gap between external knowledge and the LLMs' parametric knowledge. Recent research has been…

Computation and Language · Computer Science 2024-10-08 Youna Kim , Hyuhng Joon Kim , Cheonbok Park , Choonghyun Park , Hyunsoo Cho , Junyeob Kim , Kang Min Yoo , Sang-goo Lee , Taeuk Kim

Scaling the size of language models to tens of billions of parameters has led to impressive performance on a wide range of tasks. At generation, these models are used auto-regressively, requiring a forward pass for each generated token, and…

Computation and Language · Computer Science 2023-11-23 Giovanni Monea , Armand Joulin , Edouard Grave

Diffusion Language models (DLMs) are a promising avenue for text generation due to their practical properties on tractable controllable generation. They also have the advantage of not having to predict text autoregressively. However,…

Machine Learning · Computer Science 2024-02-13 Sofia Maria Lo Cicero Vaina , Nikita Balagansky , Daniil Gavrilov

We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies on the observation that the latency of parallel scoring of…

Computation and Language · Computer Science 2023-02-03 Charlie Chen , Sebastian Borgeaud , Geoffrey Irving , Jean-Baptiste Lespiau , Laurent Sifre , John Jumper

The alternating direction method of multipliers (ADMM) has been recognized as a versatile approach for solving modern large-scale machine learning and signal processing problems efficiently. When the data size and/or the problem dimension…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-05-04 Tsung-Hui Chang , Wei-Cheng Liao , Mingyi Hong , Xiangfeng Wang

LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety or usability. Among many approaches to mitigate the inefficiencies of…

Latent Diffusion Models (LDMs) are generally trained at fixed resolutions, limiting their capability when scaling up to high-resolution images. While training-based approaches address this limitation by training on high-resolution datasets,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Sangmin Han , Jinho Jeong , Jinwoo Kim , Seon Joo Kim

Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited…

Computation and Language · Computer Science 2024-07-26 Haoran You , Yichao Fu , Zheng Wang , Amir Yazdanbakhsh , Yingyan Celine Lin

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…

Computation and Language · Computer Science 2024-06-05 Heming Xia , Zhe Yang , Qingxiu Dong , Peiyi Wang , Yongqi Li , Tao Ge , Tianyu Liu , Wenjie Li , Zhifang Sui

Aiming at solving large-scale learning problems, this paper studies distributed optimization methods based on the alternating direction method of multipliers (ADMM). By formulating the learning problem as a consensus problem, the ADMM can…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-05-04 Tsung-Hui Chang , Mingyi Hong , Wei-Cheng Liao , Xiangfeng Wang

Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…

Computation and Language · Computer Science 2026-01-01 Tiancheng Su , Meicong Zhang , Guoxiu He

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Quan Kong , Yuhao Shen , Yicheng Ji , Huan Li , Cong Wang

Effectively addressing the challenge of industrial Anomaly Detection (AD) necessitates an ample supply of defective samples, a constraint often hindered by their scarcity in industrial contexts. This paper introduces a novel algorithm…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Hanxi Li , Zhengxun Zhang , Hao Chen , Lin Wu , Bo Li , Deyin Liu , Mingwen Wang

While LLM-based Automatic Speech Recognition (ASR) achieves high accuracy, its speed is limited by sequential autoregressive decoding. Diffusion Language Models (DLMs) offer a parallel alternative, yet their decoding strategies remain…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-29 Jeong Hun Yeo , Minsu Kim , Hyeongseop Rha , Yong Man Ro