English
Related papers

Related papers: Nystr\"omformer: A Nystr\"om-Based Algorithm for A…

200 papers

Since the proposal of transformers, these models have been limited to bounded input lengths, because of their need to attend to every token in the input. In this work, we propose Unlimiformer: a general approach that wraps any existing…

Computation and Language · Computer Science 2023-11-01 Amanda Bertsch , Uri Alon , Graham Neubig , Matthew R. Gormley

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

Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interaction pattern induces strong synchronization dynamics that…

Machine Learning · Computer Science 2026-05-26 Jingkun Liu , Yisong Yue , Max Welling , Yue Song

Natural language processing (NLP) made an impressive jump with the introduction of Transformers. ChatGPT is one of the most famous examples, changing the perception of the possibilities of AI even outside the research community. However,…

Machine Learning · Computer Science 2023-07-06 Silas Alberti , Niclas Dern , Laura Thesing , Gitta Kutyniok

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

Computation and Language · Computer Science 2018-06-19 Matthias Sperber , Jan Niehues , Graham Neubig , Sebastian Stüker , Alex Waibel

Sequence-to-sequence models have become central in Artificial Intelligence, particularly following the introduction of the transformer architecture. While initially developed for Natural Language Processing, these models have demonstrated…

Machine Learning · Computer Science 2025-10-03 Daniel Gallo Fernández

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

The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled dot product between query…

Machine Learning · Computer Science 2026-04-02 Hariprasath Govindarajan , Per Sidén , Jacob Roll , Fredrik Lindsten

Transformer-based models have achieved remarkable success in multivariate time series forecasting (MTSF) by capturing long-range dependencies. However, their widespread adoption is hindered by the quadratic computational complexity of…

Machine Learning · Computer Science 2026-05-12 Fanpu Cao , Shu Yang , Zhengjian Chen , Ye Liu , Laizhong Cui

The quadratic computational and memory complexities of the Transformer's attention mechanism have limited its scalability for modeling long sequences. In this paper, we propose Luna, a linear unified nested attention mechanism that…

Machine Learning · Computer Science 2021-11-04 Xuezhe Ma , Xiang Kong , Sinong Wang , Chunting Zhou , Jonathan May , Hao Ma , Luke Zettlemoyer

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

Computation and Language · Computer Science 2019-02-18 Baosong Yang , Jian Li , Derek Wong , Lidia S. Chao , Xing Wang , Zhaopeng Tu

Transformer has become ubiquitous in natural language processing (e.g., machine translation, question answering); however, it requires enormous amount of computations to achieve high performance, which makes it not suitable for mobile…

Computation and Language · Computer Science 2020-04-27 Zhanghao Wu , Zhijian Liu , Ji Lin , Yujun Lin , Song Han

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking…

Machine Learning · Computer Science 2024-12-12 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

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

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Machine Learning · Computer Science 2026-03-31 Yan Xie , Tiansheng Wen , Tangda Huang , Bo Chen , Chenyu You , Stefanie Jegelka , Yifei Wang

Transformer structures have been widely used in sequential recommender systems (SRS). However, as user interaction histories increase, computational time and memory requirements also grow. This is mainly caused by the standard attention…

Information Retrieval · Computer Science 2026-05-25 Mengyang Ma , Xiaopeng Li , Wanyu Wang , Zhaocheng Du , Jingtong Gao , Pengyue Jia , Yuyang Ye , Yiqi Wang , Yunpeng Weng , Weihong Luo , Xiao Han , Xiangyu Zhao

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Computation and Language · Computer Science 2023-08-03 Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin

Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a…

Computer Vision and Pattern Recognition · Computer Science 2018-06-19 Niki Parmar , Ashish Vaswani , Jakob Uszkoreit , Łukasz Kaiser , Noam Shazeer , Alexander Ku , Dustin Tran

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting…

Machine Learning · Computer Science 2026-02-03 Sayak Chakrabarti , Toniann Pitassi , Josh Alman