English
Related papers

Related papers: Gradient Flow Structure and Quantitative Dynamics …

200 papers

We propose an effective field-theoretic framework for analyzing Transformer attention through a thermodynamic lens. By constructing a Lagrangian on the information manifold equipped with the Fisher metric, we show that, within the…

Machine Learning · Computer Science 2026-02-16 Gunn Kim

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran

Self-attention is key to the remarkable success of transformers in sequence modeling tasks including many applications in natural language processing and computer vision. Like neural network layers, these attention mechanisms are often…

Machine Learning · Computer Science 2024-06-21 Tan M. Nguyen , Tam Nguyen , Nhat Ho , Andrea L. Bertozzi , Richard G. Baraniuk , Stanley J. Osher

Recently, a considerable number of studies in computer vision involves deep neural architectures called vision transformers. Visual processing in these models incorporates computational models that are claimed to implement attention…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Paria Mehrani , John K. Tsotsos

Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…

Machine Learning · Computer Science 2023-08-02 Yihe Dong , Jean-Baptiste Cordonnier , Andreas Loukas

Multi-head, key-value attention is the backbone of the widely successful Transformer model and its variants. This attention mechanism uses multiple parallel key-value attention blocks (called heads), each performing two fundamental…

Machine Learning · Computer Science 2022-02-15 Sarthak Mittal , Sharath Chandra Raparthy , Irina Rish , Yoshua Bengio , Guillaume Lajoie

Transformers have demonstrated great potential in computer vision tasks. To avoid dense computations of self-attentions in high-resolution visual data, some recent Transformer models adopt a hierarchical design, where self-attentions are…

Computer Vision and Pattern Recognition · Computer Science 2021-07-13 Jinpeng Li , Yichao Yan , Shengcai Liao , Xiaokang Yang , Ling Shao

The self-attention mechanism prevails in modern machine learning. It has an interesting functionality of adaptively selecting tokens from an input sequence by modulating the degree of attention localization, which many researchers speculate…

Machine Learning · Statistics 2024-02-06 Han Bao , Ryuichiro Hataya , Ryo Karakida

Impressive performance of Transformer has been attributed to self-attention, where dependencies between entire input in a sequence are considered at every position. In this work, we reform the neural $n$-gram model, which focuses on only…

Computation and Language · Computer Science 2022-07-28 Mengsay Loem , Sho Takase , Masahiro Kaneko , Naoaki Okazaki

The neural attention mechanism plays an important role in many natural language processing applications. In particular, the use of multi-head attention extends single-head attention by allowing a model to jointly attend information from…

Machine Learning · Computer Science 2020-11-03 Bang An , Jie Lyu , Zhenyi Wang , Chunyuan Li , Changwei Hu , Fei Tan , Ruiyi Zhang , Yifan Hu , Changyou Chen

Transformer architectures have led to remarkable progress in many state-of-art applications. However, despite their successes, modern transformers rely on the self-attention mechanism, whose time- and space-complexity is quadratic in the…

Machine Learning · Computer Science 2022-09-13 Feyza Duman Keles , Pruthuvi Mahesakya Wijewardena , Chinmay Hegde

Transformer models rely on self-attention to capture token dependencies but face challenges in effectively integrating positional information while allowing multi-head attention (MHA) flexibility. Prior methods often model semantic and…

Machine Learning · Computer Science 2025-05-28 Jintian Shao , Hongyi Huang , Jiayi Wu , Beiwen Zhang , ZhiYu Wu , You Shan , MingKai Zheng

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

We characterize the pre-softmax attention matrix $\mathbf{QK^\top}$ in transformers as an associative memory matrix encoding pairwise associations between input features. By decomposing this matrix into its symmetric and skew-symmetric…

Machine Learning · Computer Science 2026-05-28 Hyunmin Cho , Woo Kyoung Han , Kyong Hwan Jin

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

Effective representation learning from text has been an active area of research in the fields of NLP and text mining. Attention mechanisms have been at the forefront in order to learn contextual sentence representations. Current…

Computation and Language · Computer Science 2020-08-11 Sneha Mehta , Huzefa Rangwala , Naren Ramakrishnan

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

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

Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads in the encoder to the overall…

Computation and Language · Computer Science 2019-06-10 Elena Voita , David Talbot , Fedor Moiseev , Rico Sennrich , Ivan Titov

We analyze the dynamics of concentrated polymer solutions modeled by a 2D Smoluchowski equation. We describe the long time behavior of the polymer suspensions in a fluid. When the flow influence is neglected the equation has a gradient…

Analysis of PDEs · Mathematics 2025-09-17 Xingyu Li , Arghir Zarnescu