English
Related papers

Related papers: cosFormer: Rethinking Softmax in Attention

200 papers

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…

Machine Learning · Computer Science 2019-11-13 Yao-Hung Hubert Tsai , Shaojie Bai , Makoto Yamada , Louis-Philippe Morency , Ruslan Salakhutdinov

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Yuang Ai , Huaibo Huang , Tao Wu , Qihang Fan , Ran He

Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization. While effective in many settings, this constraint can limit flexibility in controlling attention…

Computation and Language · Computer Science 2026-02-27 Jeongin Bae , Baeseong Park , Gunho Park , Minsub Kim , Joonhyung Lee , Junhee Yoo , Sunghyeon Woo , Jiwon Ryu , Se Jung Kwon , Dongsoo Lee

Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient training and inference, we carefully redesigned Conformer with a…

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between…

We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) that outperforms conventional softmax attention-based models in terms of both accuracy and efficiency. TransNormerLLM evolves from the previous linear…

Computation and Language · Computer Science 2024-01-22 Zhen Qin , Dong Li , Weigao Sun , Weixuan Sun , Xuyang Shen , Xiaodong Han , Yunshen Wei , Baohong Lv , Xiao Luo , Yu Qiao , Yiran Zhong

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

Self-attention has become a defacto choice for capturing global context in various vision applications. However, its quadratic computational complexity with respect to image resolution limits its use in real-time applications, especially…

Computer Vision and Pattern Recognition · Computer Science 2023-07-27 Abdelrahman Shaker , Muhammad Maaz , Hanoona Rasheed , Salman Khan , Ming-Hsuan Yang , Fahad Shahbaz Khan

An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we show that a forget gate can be naturally incorporated into Transformers by down-weighting the…

Machine Learning · Computer Science 2025-04-02 Zhixuan Lin , Evgenii Nikishin , Xu Owen He , Aaron Courville

Transformers based on the attention mechanism have achieved impressive success in various areas. However, the attention mechanism has a quadratic complexity, significantly impeding Transformers from dealing with numerous tokens and scaling…

Machine Learning · Computer Science 2022-06-17 Haixu Wu , Jialong Wu , Jiehui Xu , Jianmin Wang , Mingsheng Long

Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. The self-attention mechanism underpinning the strength of ViTs has a quadratic complexity in both computation and memory usage. This motivates the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Jiachen Lu , Junge Zhang , Xiatian Zhu , Jianfeng Feng , Tao Xiang , Li Zhang

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the Transformer…

Computation and Language · Computer Science 2023-04-27 Shuai Li , Zhao Song , Yu Xia , Tong Yu , Tianyi Zhou

Transformer models have achieved state-of-the-art results across a diverse range of domains. However, concern over the cost of training the attention mechanism to learn complex dependencies between distant inputs continues to grow. In…

In-context reinforcement learning (ICRL) studies agents that, after pretraining, adapt to new tasks by conditioning on additional context without parameter updates. Existing theoretical analyses of ICRL largely rely on linear attention,…

Machine Learning · Computer Science 2026-05-19 Zixuan Xie , Xinyu Liu , Claire Chen , Shuze Daniel Liu , Rohan Chandra , Shangtong Zhang

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

Transformers have been extensively studied in medical image segmentation to build pairwise long-range dependence. Yet, relatively limited well-annotated medical image data makes transformers struggle to extract diverse global features,…

Image and Video Processing · Electrical Eng. & Systems 2023-09-13 Xian Lin , Zengqiang Yan , Xianbo Deng , Chuansheng Zheng , Li Yu

Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference. Prior work on linear or hybrid attention typically replaces…

Transformer is a powerful tool for many natural language tasks which is based on self-attention, a mechanism that encodes the dependence of other tokens on each specific token, but the computation of self-attention is a bottleneck due to…

Machine Learning · Computer Science 2021-03-11 Madhusudan Verma

As the core operator of Transformers, Softmax Attention exhibits excellent global modeling capabilities. However, its quadratic complexity limits its applicability to vision tasks. In contrast, Linear Attention shares a similar formulation…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Qihang Fan , Huaibo Huang , Yuang Ai , Ran He

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Chunmeng Liu , Enze Xie , Wenjia Wang , Wenhai Wang , Guangyao Li , Ping Luo