English
Related papers

Related papers: Monotonic Chunkwise Attention

200 papers

Generative models have long been the dominant approach for speech recognition. The success of these models however relies on the use of sophisticated recipes and complicated machinery that is not easily accessible to non-practitioners.…

Computation and Language · Computer Science 2017-06-21 Chung-Cheng Chiu , Dieterich Lawson , Yuping Luo , George Tucker , Kevin Swersky , Ilya Sutskever , Navdeep Jaitly

Recently, recurrent large language models (Recurrent LLMs) with linear computational complexity have re-emerged as efficient alternatives to self-attention-based LLMs (Self-Attention LLMs), which have quadratic complexity. However,…

Computation and Language · Computer Science 2025-07-28 Kai Liu , Zhan Su , Peijie Dong , Fengran Mo , Jianfei Gao , ShaoTing Zhang , Kai Chen

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…

Computation and Language · Computer Science 2020-11-17 Ching-Feng Yeh , Yongqiang Wang , Yangyang Shi , Chunyang Wu , Frank Zhang , Julian Chan , Michael L. Seltzer

Multi-Head Attention (MHA) is a key component of Transformer. In MHA, attention heads work independently, causing problems such as low-rank bottleneck of attention score matrices and head redundancy. We propose Dynamically Composable…

Machine Learning · Computer Science 2024-06-05 Da Xiao , Qingye Meng , Shengping Li , Xingyuan Yuan

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…

Computation and Language · Computer Science 2025-11-04 Yuxuan Hu , Jianchao Tan , Jiaqi Zhang , Wen Zan , Pingwei Sun , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai , Jing Zhang

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Machine Learning · Computer Science 2021-07-27 Zhenhai Zhu , Radu Soricut

Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. Towards this task, two main architectures have been applied, namely single-encoder (based on concatenation) and…

Computation and Language · Computer Science 2024-02-05 Paweł Mąka , Yusuf Can Semerci , Jan Scholtes , Gerasimos Spanakis

In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs. The efficient design makes the incorporation between attention…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Rui Li , Jianlin Su , Chenxi Duan , Shunyi Zheng

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…

Machine Learning · Computer Science 2022-08-02 Tan Nguyen , Richard G. Baraniuk , Robert M. Kirby , Stanley J. Osher , Bao Wang

Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers are gradually diluted by repeated residual updates, making…

Computation and Language · Computer Science 2026-03-17 Lianghui Zhu , Yuxin Fang , Bencheng Liao , Shijie Wang , Tianheng Cheng , Zilong Huang , Chen Chen , Lai Wei , Yutao Zeng , Ya Wang , Yi Lin , Yu Li , Xinggang Wang

Soft attention in Transformer-based Large Language Models (LLMs) is susceptible to incorporating irrelevant information from the context into its latent representations, which adversely affects next token generations. To help rectify these…

Computation and Language · Computer Science 2023-11-21 Jason Weston , Sainbayar Sukhbaatar

Semantic segmentation is a vital problem in computer vision. Recently, a common solution to semantic segmentation is the end-to-end convolution neural network, which is much more accurate than traditional methods.Recently, the decoders…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Hao Guo , Hongbiao Si , Guilin Jiang , Wei Zhang , Zhiyan Liu , Xuanyi Zhu , Xulong Zhang , Yang Liu

The transformer architecture has driven breakthroughs in recent years on tasks which require modeling pairwise relationships between sequential elements, as is the case in natural language understanding. However, long seqeuences pose a…

Computation and Language · Computer Science 2024-03-26 Heejun Lee , Jina Kim , Jeffrey Willette , Sung Ju Hwang

Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices. In this work, we show that multi-task learning is naturally suited to handle the statistical…

Machine Learning · Computer Science 2018-02-28 Virginia Smith , Chao-Kai Chiang , Maziar Sanjabi , Ameet Talwalkar

Linear attentions have shown potential for improving Transformer efficiency, reducing attention's quadratic complexity to linear in sequence length. This holds exciting promise for (1) training linear Transformers from scratch, (2)…

Machine Learning · Computer Science 2024-02-08 Michael Zhang , Kush Bhatia , Hermann Kumbong , Christopher Ré

A modern deep neural network (DNN) for image classification tasks typically consists of two parts: a backbone for feature extraction, and a head for feature encoding and class predication. We observe that the head structures of mainstream…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Chao Li , Aojun Zhou , Anbang Yao

The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity…

Computation and Language · Computer Science 2026-03-27 Yijiong Yu , Jiale Liu , Qingyun Wu , Huazheng Wang , Ji Pei

Motivated by the attention mechanism of the human visual system and recent developments in the field of machine translation, we introduce our attention-based and recurrent sequence to sequence autoencoders for fully unsupervised…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-20 Shahin Amiriparian , Pawel Winokurow , Vincent Karas , Sandra Ottl , Maurice Gerczuk , Björn W. Schuller

Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general black-box relationships between functional data. We propose a…