English
Related papers

Related papers: A Mechanistic Analysis of Transformers for Dynamic…

200 papers

Large language models rely on attention mechanisms with a softmax activation. Yet the dominance of softmax over alternatives (e.g., component-wise or linear) remains poorly understood, and many theoretical works have focused on the…

Machine Learning · Computer Science 2026-02-27 O. Duranthon , P. Marion , C. Boyer , B. Loureiro , L. Zdeborová

With the advent of large models based on the Transformer architecture, researchers have observed an anomalous phenomenon in the Attention mechanism--there is a very high attention on the first element, which is prevalent across…

Machine Learning · Computer Science 2024-07-04 Ruiqing Yan , Xingbo Du , Haoyu Deng , Linghan Zheng , Qiuzhuang Sun , Jifang Hu , Yuhang Shao , Penghao Jiang , Jinrong Jiang , Lian Zhao

Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Ruize He , Dongchen Han , Gao Huang

Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge. In time series forecasting, the autoregressive…

Machine Learning · Computer Science 2021-06-01 Kai Chen , Guang Chen , Dan Xu , Lijun Zhang , Yuyao Huang , Alois Knoll

Accurate and physically consistent modeling of Earth system dynamics requires machine-learning architectures that operate directly on continuous geophysical fields and preserve their underlying geometric structure. Here we introduce…

Machine Learning · Computer Science 2025-12-24 Maximilian Witte , Johannes Meuer , Étienne Plésiat , Christopher Kadow

The dot product self-attention is known to be central and indispensable to state-of-the-art Transformer models. But is it really required? This paper investigates the true importance and contribution of the dot product-based self-attention…

Computation and Language · Computer Science 2021-05-25 Yi Tay , Dara Bahri , Donald Metzler , Da-Cheng Juan , Zhe Zhao , Che Zheng

While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the time series forecasting task. Our hypothesis is that models should learn a direct link from…

Machine Learning · Computer Science 2026-05-15 Alexis-Raja Brachet , Pierre-Yves Richard , Céline Hudelot

Modern machine learning requires system designers to specify aspects of the learning pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn, instead aims to learn those aspects, and promises to unlock…

Machine Learning · Computer Science 2024-01-10 Louis Kirsch , James Harrison , Jascha Sohl-Dickstein , Luke Metz

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

Data-driven learning of partial differential equations' solution operators has recently emerged as a promising paradigm for approximating the underlying solutions. The solution operators are usually parameterized by deep learning models…

Machine Learning · Computer Science 2023-05-01 Zijie Li , Kazem Meidani , Amir Barati Farimani

Transformers are ubiquitous in wide tasks. Interpreting their internals is a pivotal goal. Nevertheless, their particular components, feed-forward (FF) blocks, have typically been less analyzed despite their substantial parameter amounts.…

Computation and Language · Computer Science 2024-04-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

We introduce a new discrete-time attention model, termed the localmax dynamics, which interpolates between the classic softmax dynamics and the hardmax dynamics, where only the tokens that maximize the influence toward a given token have a…

Computation and Language · Computer Science 2025-09-22 Henri Cimetière , Maria Teresa Chiri , Bahman Gharesifard

Transformers are deep architectures that define "in-context mappings" which enable predicting new tokens based on a given set of tokens (such as a prompt in NLP applications or a set of patches for a vision transformer). In this work, we…

Computation and Language · Computer Science 2024-10-04 Takashi Furuya , Maarten V. de Hoop , Gabriel Peyré

Transformers have recently been utilized to perform object detection and tracking in the context of autonomous driving. One unique characteristic of these models is that attention weights are computed in each forward pass, giving insights…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Felicia Ruppel , Florian Faion , Claudius Gläser , Klaus Dietmayer

Self-attention is a useful mechanism to build generative models for language and images. It determines the importance of context elements by comparing each element to the current time step. In this paper, we show that a very lightweight…

Computation and Language · Computer Science 2019-02-26 Felix Wu , Angela Fan , Alexei Baevski , Yann N. Dauphin , Michael Auli

End-to-end paradigms have demonstrated great potential for autonomous driving. Additionally, most existing methods are built upon Transformer architectures. However, transformers incur a quadratic attention cost, limiting their ability to…

Artificial Intelligence · Computer Science 2025-12-19 Jihao Huang , Xi Xia , Zhiyuan Li , Tianle Liu , Jingke Wang , Junbo Chen , Tengju Ye

This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain $[0,1]^d$ and $d$-dimensional compact Riemannian manifolds. We propose a novel constructive approximation framework for…

Machine Learning · Statistics 2026-05-12 Zhongjie Shi , Wenjing Liao

Despite several successes in document understanding, the practical task for long document understanding is largely under-explored due to several challenges in computation and how to efficiently absorb long multimodal input. Most current…

Computation and Language · Computer Science 2022-08-18 Hai Pham , Guoxin Wang , Yijuan Lu , Dinei Florencio , Cha Zhang

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

Computation and Language · Computer Science 2022-11-29 Nikolaos Mylonas , Ioannis Mollas , Grigorios Tsoumakas

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…

Machine Learning · Computer Science 2025-02-14 Bhavya Vasudeva , Deqing Fu , Tianyi Zhou , Elliott Kau , Youqi Huang , Vatsal Sharan