English
Related papers

Related papers: Transformer as an Euler Discretization of Score-ba…

200 papers

The Transformer architecture has revolutionized the field of sequence modeling and underpins the recent breakthroughs in large language models (LLMs). However, a comprehensive mathematical theory that explains its structure and operations…

Machine Learning · Computer Science 2026-04-14 Xue-Cheng Tai , Hao Liu , Lingfeng Li , Raymond H. Chan

To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a…

Information Retrieval · Computer Science 2024-04-05 Zhen Tian , Wayne Xin Zhao , Changwang Zhang , Xin Zhao , Zhongrui Ma , Ji-Rong Wen

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 show that the standard discrete update rule of transformer layers can be naturally interpreted as a forward Euler discretization of a continuous dynamical system. Our Transformer Flow Approximation Theorem demonstrates that, under…

Machine Learning · Computer Science 2025-05-26 Jacob Fein-Ashley

Transformer-based models have achieved remarkable success across a wide range of domains, yet our understanding of their training dynamics remains limited. In this work, we identify a recurrent focus-dilution cycle in attention learning and…

Machine Learning · Computer Science 2026-05-05 Zheng-An Chen , Pengxiao Lin , Zhi-Qin John Xu , Tao Luo

Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity. We observe that when the training set is sufficiently complex, the…

Computation and Language · Computer Science 2024-02-12 Yichen Jiang , Xiang Zhou , Mohit Bansal

Multivariate time series classification is a crucial task in data mining, attracting growing research interest due to its broad applications. While many existing methods focus on discovering discriminative patterns in time series,…

Machine Learning · Computer Science 2024-12-24 Wenjie Xi , Rundong Zuo , Alejandro Alvarez , Jie Zhang , Byron Choi , Jessica Lin

Transformer self-attention can be interpreted as a gradient flow on the unit sphere, in which tokens evolve under softmax interaction potentials and tend to form clusters. While prior work has established clustering behavior for single-head…

Machine Learning · Computer Science 2026-05-11 Ayan Pendharkar

While behavior cloning with flow/diffusion policies excels at learning complex skills from demonstrations, it remains vulnerable to distributional shift, and standard RL methods struggle to fine-tune these models due to their iterative…

Machine Learning · Computer Science 2025-10-20 Mingyang Sun , Pengxiang Ding , Weinan Zhang , Donglin Wang

Transformers have shown strong ability to model long-term dependencies and are increasingly adopted as world models in model-based reinforcement learning (RL) under partial observability. However, unlike natural language corpora, RL…

Machine Learning · Computer Science 2025-11-11 Daniel De Dios Allegue , Jinke He , Frans A. Oliehoek

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Computation and Language · Computer Science 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

Flow matching models generate samples by numerically integrating a learned velocity field, with each integration step requiring a neural network evaluation. Fast generation therefore requires using a small fixed evaluation budget…

Machine Learning · Computer Science 2026-05-13 Aditi Gupta , Soon Hoe Lim , Annan Yu , N. Benjamin Erichson

Transformers have achieved remarkable success across natural language processing (NLP) and computer vision (CV). However, deep transformer models often suffer from an over-smoothing issue, in which token representations converge to similar…

Machine Learning · Computer Science 2025-10-21 Satoshi Noguchi , Yoshinobu Kawahara

Transformers, which are state-of-the-art in most machine learning tasks, represent the data as sequences of vectors called tokens. This representation is then exploited by the attention function, which learns dependencies between tokens and…

Machine Learning · Computer Science 2025-01-31 Valérie Castin , Pierre Ablin , José Antonio Carrillo , Gabriel Peyré

The aim of this paper is to provide a mathematical analysis of transformer architectures using a self-attention mechanism with layer normalization. In particular, observed patterns in such architectures resembling either clusters or uniform…

Analysis of PDEs · Mathematics 2025-04-29 Martin Burger , Samira Kabri , Yury Korolev , Tim Roith , Lukas Weigand

Transformer-based neural network architectures achieve state-of-the-art results in different domains, from natural language processing (NLP) to computer vision (CV). The key idea of Transformers, the attention mechanism, has already led to…

Machine Learning · Computer Science 2023-11-07 Alina Ermilova , Nikita Baramiia , Valerii Kornilov , Sergey Petrakov , Alexey Zaytsev

Learning unsupervised representations that are both semantically meaningful and stable across runs remains a central challenge in modern representation learning. We introduce entropy-ordered flows (EOFlows), a normalizing-flow framework…

Machine Learning · Computer Science 2026-02-09 Daniel Galperin , Ullrich Köthe

We study the problem of learning generative models for discrete sequences in a continuous embedding space. Whereas prior approaches typically operate in Euclidean space or on the probability simplex, we instead work on the sphere $\mathbb…

Machine Learning · Statistics 2026-05-12 Jannis Chemseddine , Gregor Kornhardt , Gabriele Steidl

We develop a mathematical framework that interprets Transformer attention as an interacting particle system and studies its continuum (mean-field) limits. By idealizing attention on the sphere, we connect Transformer dynamics to Wasserstein…

Machine Learning · Computer Science 2026-02-02 Philippe Rigollet

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
‹ Prev 1 2 3 10 Next ›