English
Related papers

Related papers: Beyond Linearity in Attention Projections: The Cas…

200 papers

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

Transformers have achieved state-of-the-art results across a range of domains, but their quadratic attention mechanism poses significant challenges for long-sequence modelling. Recent efforts to design linear-time attention mechanisms have…

Computation and Language · Computer Science 2025-12-03 Rares Dolga , Lucas Maystre , Marius Cobzarenco , David Barber

Linear attention offers a linear-time alternative to self-attention but often struggles to capture long-range patterns. We revisit linear attention through a prediction-correction lens and show that prevalent variants can be written as a…

Machine Learning · Computer Science 2025-10-01 Xunhao Lai , Jialiang Kang , Jianqiao Lu , Tong Lin , Pengyu Zhao

Visual grounding focuses on establishing fine-grained alignment between vision and natural language, which has essential applications in multimodal reasoning systems. Existing methods use pre-trained query-agnostic visual backbones to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Jiabo Ye , Junfeng Tian , Ming Yan , Xiaoshan Yang , Xuwu Wang , Ji Zhang , Liang He , Xin Lin

Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the…

Machine Learning · Statistics 2025-02-27 Pierre Marion , Raphaël Berthier , Gérard Biau , Claire Boyer

Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each…

Computation and Language · Computer Science 2018-10-02 Lesly Miculicich Werlen , Nikolaos Pappas , Dhananjay Ram , Andrei Popescu-Belis

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Axel Berg , Mark O'Connor , Miguel Tairum Cruz

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated…

Machine Learning · Computer Science 2021-06-10 Shujian Zhang , Xinjie Fan , Bo Chen , Mingyuan Zhou

In mechanistic interpretability, recent work scrutinizes transformer "circuits" - sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid-tested for their…

Machine Learning · Computer Science 2026-02-20 Karan Bali , Jack Stanley , Praneet Suresh , Danilo Bzdok

In recent research, Learned Image Compression has gained prominence for its capacity to outperform traditional handcrafted pipelines, especially at low bit-rates. While existing methods incorporate convolutional priors with occasional…

Image and Video Processing · Electrical Eng. & Systems 2023-10-18 Natacha Luka , Romain Negrel , David Picard

Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization. Such desirable properties are…

Machine Learning · Computer Science 2020-12-22 Alessandro Achille , Aditya Golatkar , Avinash Ravichandran , Marzia Polito , Stefano Soatto

Transformers have shown great power in time series forecasting due to their global-range modeling ability. However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over…

Machine Learning · Computer Science 2023-11-27 Yong Liu , Haixu Wu , Jianmin Wang , Mingsheng Long

Since their inception, encoder-decoder models have successfully been applied to a wide array of problems in computational linguistics. The most recent successes are predominantly due to the use of different variations of attention…

Computation and Language · Computer Science 2019-06-11 Dennis Ulmer , Dieuwke Hupkes , Elia Bruni

The sequence-to-sequence (seq2seq) task aims at generating the target sequence based on the given input source sequence. Traditionally, most of the seq2seq task is resolved by the Encoder-Decoder framework which requires an encoder to…

Computation and Language · Computer Science 2023-04-11 Zihao Fu , Wai Lam , Qian Yu , Anthony Man-Cho So , Shengding Hu , Zhiyuan Liu , Nigel Collier

Transformers are increasingly adopted for modeling and forecasting time-series, yet their internal mechanisms remain poorly understood from a dynamical systems perspective. In contrast to classical autoregressive and state-space models,…

Machine Learning · Computer Science 2025-12-25 Gregory Duthé , Nikolaos Evangelou , Wei Liu , Ioannis G. Kevrekidis , Eleni Chatzi

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

Computation and Language · Computer Science 2026-05-20 Jiaoda Li , Ryan Cotterell

In recent years, multi-modal transformers have shown significant progress in Vision-Language tasks, such as Visual Question Answering (VQA), outperforming previous architectures by a considerable margin. This improvement in VQA is often…

Computer Vision and Pattern Recognition · Computer Science 2022-01-12 Ankur Sikarwar , Gabriel Kreiman

Gated Linear Units (GLU) have shown great potential in enhancing neural network performance. In this paper, I introduce a novel attention mechanism called GLU Attention, which introduces nonlinearity into the values of Attention. My…

Machine Learning · Computer Science 2025-07-08 Zehao Wang

In this paper we delve deep in the Transformer architecture by investigating two of its core components: self-attention and contextual embeddings. In particular, we study the identifiability of attention weights and token embeddings, and…

Computation and Language · Computer Science 2020-02-10 Gino Brunner , Yang Liu , Damián Pascual , Oliver Richter , Massimiliano Ciaramita , Roger Wattenhofer

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç