English
Related papers

Related papers: Selective Attention: Enhancing Transformer through…

200 papers

Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Nhat Thanh Tran , Fanghui Xue , Shuai Zhang , Jiancheng Lyu , Yunling Zheng , Yingyong Qi , Jack Xin

We study how multi-head softmax attention models are trained to perform in-context learning on linear data. Through extensive empirical experiments and rigorous theoretical analysis, we demystify the emergence of elegant attention patterns:…

Machine Learning · Computer Science 2025-05-29 Jianliang He , Xintian Pan , Siyu Chen , Zhuoran Yang

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…

The Transformer-based model have made significant strides in semantic matching tasks by capturing connections between phrase pairs. However, to assess the relevance of sentence pairs, it is insufficient to just examine the general…

Computation and Language · Computer Science 2024-12-11 Bo Li , Di Liang , Zixin Zhang

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Machine Learning · Computer Science 2025-11-26 Wei Chen , Jingxi Yu , Zichen Miao , Qiang Qiu

Since its introduction in 2017, Transformer has emerged as the leading neural network architecture, catalyzing revolutionary advancements in many AI disciplines. The key innovation in Transformer is a Self-Attention (SA) mechanism designed…

Machine Learning · Computer Science 2024-02-05 Yueyao Yu , Yin Zhang

Transformer-based speech recognition models have achieved great success due to the self-attention (SA) mechanism that utilizes every frame in the feature extraction process. Especially, SA heads in lower layers capture various phonetic…

Computation and Language · Computer Science 2022-07-13 Kyuhong Shim , Wonyong Sung

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not…

Machine Learning · Computer Science 2025-04-22 Sushant Singh , Ausif Mahmood

In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Simpenzwe Honore Leandre , Natenaile Asmamaw Shiferaw , Dillip Rout

The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanism. However, despite its power, the standard attention…

Machine Learning · Computer Science 2026-01-08 Zichuan Fu , Wentao Song , Guojing Li , Yejing Wang , Xian Wu , Yimin Deng , Hanyu Yan , Yefeng Zheng , Xiangyu Zhao

Transformers have demonstrated exceptional performance across various domains due to their self-attention mechanism, which captures complex relationships in data. However, training on smaller datasets poses challenges, as standard attention…

Computation and Language · Computer Science 2024-12-10 Minhajur Rahman , Yasir Arafat

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

Computation and Language · Computer Science 2019-06-05 Matthias Sperber , Graham Neubig , Ngoc-Quan Pham , Alex Waibel

Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…

Computation and Language · Computer Science 2022-06-03 Hao Peng , Jungo Kasai , Nikolaos Pappas , Dani Yogatama , Zhaofeng Wu , Lingpeng Kong , Roy Schwartz , Noah A. Smith

Visual attention mechanisms are widely used in multimodal tasks, as visual question answering (VQA). One drawback of softmax-based attention mechanisms is that they assign some probability mass to all image regions, regardless of their…

Computation and Language · Computer Science 2021-07-09 Pedro Henrique Martins , Vlad Niculae , Zita Marinho , André Martins

Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…

The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with…

Machine Learning · Computer Science 2025-10-03 Adam Filipek

Multivariate time series (MTS) analysis prevails in real-world applications such as finance, climate science and healthcare. The various self-attention mechanisms, the backbone of the state-of-the-art Transformer-based models, efficiently…

Machine Learning · Computer Science 2023-11-21 Quang Minh Nguyen , Lam M. Nguyen , Subhro Das

To overcome the quadratic cost of self-attention, recent works have proposed various sparse attention modules, most of which fall under one of two groups: 1) sparse attention under a hand-crafted patterns and 2) full attention followed by a…

Machine Learning · Computer Science 2022-10-28 Sungjun Cho , Seonwoo Min , Jinwoo Kim , Moontae Lee , Honglak Lee , Seunghoon Hong

Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Zhenyu Hu , Wanjie Sun

Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Yong He , Hongshan Yu , Chaoxu Mu , Mingtao Feng , Tongjia Chen , Zechuan Li , Anwaar Ulhaq , Ajmal Mian