English
Related papers

Related papers: Attention is Not All You Need: Pure Attention Lose…

200 papers

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Shashanka Venkataramanan , Amir Ghodrati , Yuki M. Asano , Fatih Porikli , Amirhossein Habibian

This paper presents a mathematical interpretation of self-attention by connecting it to distributional semantics principles. We show that self-attention emerges from projecting corpus-level co-occurrence statistics into sequence context.…

Machine Learning · Computer Science 2025-11-19 Nihal Mehta

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Machine Learning · Computer Science 2026-01-21 Xiaojie Xia , Huigang Zhang , Chaoliang Zhong , Jun Sun , Yusuke Oishi

We propose an efficient interactive method for multi-head self-attention via decomposition. For existing methods using multi-head self-attention, the attention operation of each head is computed independently. However, we show that the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-28 Hankyul Kang , Ming-Hsuan Yang , Jongbin Ryu

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

Finding the right initialisation for neural networks is crucial to ensure smooth training and good performance. In transformers, the wrong initialisation can lead to one of two failure modes of self-attention layers: rank collapse, where…

Machine Learning · Statistics 2026-05-22 Alessio Giorlandino , Sebastian Goldt

Transformers are one of the most successful architectures of modern neural networks. At their core there is the so-called attention mechanism, which recently interested the physics community as it can be written as the derivative of an…

Machine Learning · Computer Science 2024-09-25 Francesco D'Amico , Matteo Negri

Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the…

Machine Learning · Computer Science 2022-06-27 Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Cyril Zhang

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block differs in form and…

Machine Learning · Computer Science 2025-03-18 Weronika Ormaniec , Felix Dangel , Sidak Pal Singh

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Kewei Zhang , Ye Huang , Yufan Deng , Jincheng Yu , Junsong Chen , Huan Ling , Enze Xie , Daquan Zhou

We establish the universal approximation capability of single-layer, single-head self- and cross-attention mechanisms with minimal attached structures. Our key insight is to interpret single-head attention as an input domain-partition…

Machine Learning · Computer Science 2025-04-29 Hude Liu , Jerry Yao-Chieh Hu , Zhao Song , Han Liu

Self-attention has greatly contributed to the success of the widely used Transformer architecture by enabling learning from data with long-range dependencies. In an effort to improve performance, a gated attention model that leverages a…

Machine Learning · Computer Science 2026-02-03 Viet Nguyen , Tuan Minh Pham , Thinh Cao , Tan Dinh , Huy Nguyen , Nhat Ho , Alessandro Rinaldo

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions…

Computation and Language · Computer Science 2021-02-26 Yaru Hao , Li Dong , Furu Wei , Ke Xu

Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism,…

Machine Learning · Computer Science 2022-11-23 Tolga Ergen , Behnam Neyshabur , Harsh Mehta

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

Attention and self-attention mechanisms, are now central to state-of-the-art deep learning on sequential tasks. However, most recent progress hinges on heuristic approaches with limited understanding of attention's role in model…

Machine Learning · Computer Science 2020-12-11 Giancarlo Kerg , Bhargav Kanuparthi , Anirudh Goyal , Kyle Goyette , Yoshua Bengio , Guillaume Lajoie

Transformers architecture apply self-attention to tokens represented as vectors, before a fully connected (neuronal network) layer. These two parts can be layered many times. Traditionally, self-attention is seen as a mechanism for…

Computation and Language · Computer Science 2025-01-22 Evgeniy Shin , Heinrich Matzinger

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt

Large vision-and-language models (LVLMs) have traditionally integrated visual and textual tokens by concatenating them into a single homogeneous input for large language models (LLMs), thereby maximally preserving the pre-trained language…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Chia-Wen Kuo , Sijie Zhu , Fan Chen , Xiaohui Shen , Longyin Wen

Attention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly…

Computation and Language · Computer Science 2020-04-08 Danish Pruthi , Mansi Gupta , Bhuwan Dhingra , Graham Neubig , Zachary C. Lipton
‹ Prev 1 4 5 6 7 8 10 Next ›