English
Related papers

Related papers: Understanding Transformer Architecture through Con…

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

We introduce PDE-Transformer, an improved transformer-based architecture for surrogate modeling of physics simulations on regular grids. We combine recent architectural improvements of diffusion transformers with adjustments specific for…

Machine Learning · Computer Science 2025-06-02 Benjamin Holzschuh , Qiang Liu , Georg Kohl , Nils Thuerey

Learning underlying dynamics from data is important and challenging in many real-world scenarios. Incorporating differential equations (DEs) to design continuous networks has drawn much attention recently, however, most prior works make…

Machine Learning · Computer Science 2023-02-03 Yesom Park , Jaemoo Choi , Changyeon Yoon , Chang hoon Song , Myungjoo Kang

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely…

Machine Learning · Computer Science 2025-12-30 Yukun Zhang , Xueqing Zhou

Partial differential equations (PDEs) are fundamental for modeling complex physical systems, yet classical numerical solvers face prohibitive computational costs in high-dimensional and multi-scale regimes. While Transformer-based neural…

Machine Learning · Computer Science 2026-03-04 Pengyu Lai , Yixiao Chen , Dewu Yang , Rui Wang , Feng Wang , Hui Xu

Modeling the traffic dynamics is essential for understanding and predicting the traffic spatiotemporal evolution. However, deriving the partial differential equation (PDE) models that capture these dynamics is challenging due to their…

Systems and Control · Electrical Eng. & Systems 2025-05-05 Zihang Wei , Yunlong Zhang , Chenxi Liu , Yang Zhou

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

Modeling sequential patterns from data is at the core of various time series forecasting tasks. Deep learning models have greatly outperformed many traditional models, but these black-box models generally lack explainability in prediction…

Machine Learning · Computer Science 2023-05-23 Yingtao Luo , Chang Xu , Yang Liu , Weiqing Liu , Shun Zheng , Jiang Bian

In many scientific fields, the generation and evolution of data are governed by partial differential equations (PDEs) which are typically informed by established physical laws at the macroscopic level to describe general and predictable…

Methodology · Statistics 2025-07-01 Ziyuan Chen , Shunxing Yan , Fang Yao

The Transformer architecture is widely used in natural language processing. Despite its success, the design principle of the Transformer remains elusive. In this paper, we provide a novel perspective towards understanding the architecture:…

Machine Learning · Computer Science 2019-06-10 Yiping Lu , Zhuohan Li , Di He , Zhiqing Sun , Bin Dong , Tao Qin , Liwei Wang , Tie-Yan Liu

As artificial intelligence models have exploded in scale and capability, understanding of their internal mechanisms remains a critical challenge. Inspired by the success of dynamical systems approaches in neuroscience, here we propose a…

Artificial Intelligence · Computer Science 2025-02-18 Jesseba Fernando , Grigori Guitchounts

Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introduce a reformulation of layer-level transformations that…

Machine Learning · Computer Science 2025-08-04 Saleh Nikooroo , Thomas Engel

Transformer architectures are typically described in algorithmic and statistical terms, leaving their internal mechanics without a familiar structural language for researchers trained in physical theories. To bridge this gap, we develop a…

Disordered Systems and Neural Networks · Physics 2026-03-18 Po-Hao Chang

An important development in deep learning from the earliest MLPs has been a move towards architectures with structural inductive biases which enable the model to keep distinct sources of information and routes of processing well-separated.…

Machine Learning · Computer Science 2021-03-02 Alex Lamb , Di He , Anirudh Goyal , Guolin Ke , Chien-Feng Liao , Mirco Ravanelli , Yoshua Bengio

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

Partial differential equations (PDEs) govern nearly every physical process in science and engineering, yet solving them at scale remains prohibitively expensive. Generative AI has transformed language, vision, and protein science, but…

Machine Learning · Computer Science 2026-04-10 Yilong Dai , Shengyu Chen , Xiaowei Jia , Runlong Yu

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block differs in form and…

Machine Learning · Computer Science 2025-03-18 Weronika Ormaniec , Felix Dangel , Sidak Pal Singh

We present Mechanistic PDE Networks -- a model for discovery of governing partial differential equations from data. Mechanistic PDE Networks represent spatiotemporal data as space-time dependent linear partial differential equations in…

Machine Learning · Computer Science 2025-06-12 Adeel Pervez , Efstratios Gavves , Francesco Locatello

Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dynamic state tracking. State tracking -- the iterative updating of latent variables…

Machine Learning · Computer Science 2026-04-29 Michael C. Mozer , Shoaib Ahmed Siddiqui , Rosanne Liu

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
‹ Prev 1 2 3 10 Next ›