English
Related papers

Related papers: When to Use Efficient Self Attention? Profiling Te…

200 papers

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Computation and Language · Computer Science 2020-10-07 Ameet Deshpande , Karthik Narasimhan

Transformer with self-attention has achieved great success in the area of nature language processing. Recently, there have been a few studies on transformer for end-to-end speech recognition, while its application for hybrid acoustic model…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-24 Liang Lu

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Computation and Language · Computer Science 2020-12-03 Iz Beltagy , Matthew E. Peters , Arman Cohan

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements…

Computation and Language · Computer Science 2026-03-25 Riccardo Bravin , Massimo Pavan , Hazem Hesham Yousef Shalby , Fabrizio Pittorino , Manuel Roveri

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Axel Berg , Mark O'Connor , Miguel Tairum Cruz

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Dongchen Han , Xuran Pan , Yizeng Han , Shiji Song , Gao Huang

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity…

Computation and Language · Computer Science 2025-09-04 Qianchao Zhu , Jiangfei Duan , Chang Chen , Siran Liu , Guanyu Feng , Xin Lv , Xiao Chuanfu , Dahua Lin , Chao Yang

We propose a novel self-attention mechanism that can learn its optimal attention span. This allows us to extend significantly the maximum context size used in Transformer, while maintaining control over their memory footprint and…

Machine Learning · Computer Science 2019-08-09 Sainbayar Sukhbaatar , Edouard Grave , Piotr Bojanowski , Armand Joulin

Modeling of longitudinal cohort data typically involves complex temporal dependencies between multiple variables. There, the transformer architecture, which has been highly successful in language and vision applications, allows us to…

The state of the art in learning meaningful semantic representations of words is the Transformer model and its attention mechanisms. Simply put, the attention mechanisms learn to attend to specific parts of the input dispensing recurrence…

Computation and Language · Computer Science 2020-12-24 Dongsheng Wang , Casper Hansen , Lucas Chaves Lima , Christian Hansen , Maria Maistro , Jakob Grue Simonsen , Christina Lioma

Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the…

Computation and Language · Computer Science 2021-06-01 Potsawee Manakul , Mark J. F. Gales

Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Ting Yao , Yehao Li , Yingwei Pan , Yu Wang , Xiao-Ping Zhang , Tao Mei

The transformer has revolutionized modern AI across language, vision, and beyond. It consists of $L$ layers, each running $H$ attention heads in parallel and feeding the combined output to the subsequent layer. In attention, the input…

Computational Complexity · Computer Science 2026-03-13 Barna Saha , Yinzhan Xu , Christopher Ye , Hantao Yu

Vision Transformers (ViT) have shown their competitive advantages performance-wise compared to convolutional neural networks (CNNs) though they often come with high computational costs. To this end, previous methods explore different…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Cong Wei , Brendan Duke , Ruowei Jiang , Parham Aarabi , Graham W. Taylor , Florian Shkurti

Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meaning. In this paper, we explored trade-offs and ordering of…

Machine Learning · Computer Science 2021-05-18 Swetha Mandava , Szymon Migacz , Alex Fit Florea

Modern neural speech models benefit from having longer context, and many approaches have been proposed to increase the maximum context a model can use. However, few have attempted to measure how much context these models actually use, i.e.,…

Sound · Computer Science 2025-05-29 Yen Meng , Sharon Goldwater , Hao Tang

In this paper, we introduce the prior knowledge, multi-scale structure, into self-attention modules. We propose a Multi-Scale Transformer which uses multi-scale multi-head self-attention to capture features from different scales. Based on…

Computation and Language · Computer Science 2019-12-03 Qipeng Guo , Xipeng Qiu , Pengfei Liu , Xiangyang Xue , Zheng Zhang

Transformer models have revolutionized natural language processing, achieving state-of-the-art performance and demonstrating remarkable scalability. However, their memory demands, particularly due to maintaining full context in memory, pose…

Computation and Language · Computer Science 2025-11-04 Juan Gabriel Kostelec , Qinghai Guo

Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in…

Computation and Language · Computer Science 2022-04-20 Belen Alastruey , Javier Ferrando , Gerard I. Gállego , Marta R. Costa-jussà

Self-attention is a key enabler of state-of-art accuracy for various transformer-based Natural Language Processing models. This attention mechanism calculates a correlation score for each word with respect to the other words in a sentence.…

Computation and Language · Computer Science 2022-04-18 Zheng Li , Soroush Ghodrati , Amir Yazdanbakhsh , Hadi Esmaeilzadeh , Mingu Kang