English
Related papers

Related papers: Positional Knowledge is All You Need: Position-ind…

200 papers

Recent advances in Transformer-based Neural Operators have enabled significant progress in data-driven solvers for Partial Differential Equations (PDEs). Most current research has focused on reducing the quadratic complexity of attention to…

Machine Learning · Computer Science 2026-01-08 Wenjie Hu , Sidun Liu , Peng Qiao , Zhenglun Sun , Yong Dou

Positional encodings enable Transformers to incorporate sequential information, yet their theoretical understanding remains limited to two properties: distance attenuation and translation invariance. Because natural language lacks purely…

Machine Learning · Computer Science 2026-02-11 Zihan Gu , Ruoyu Chen , Han Zhang , Hua Zhang , Yue Hu

Self-attention mechanism has been a key factor in the recent progress of Vision Transformer (ViT), which enables adaptive feature extraction from global contexts. However, existing self-attention methods either adopt sparse global attention…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Xuran Pan , Tianzhu Ye , Zhuofan Xia , Shiji Song , Gao Huang

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran

Partial differential equations (PDEs) play a foundational role in modeling physical phenomena. This study addresses the challenging task of determining variable coefficients within PDEs from measurement data. We introduce a novel neural…

Numerical Analysis · Mathematics 2023-10-17 Ke Chen , Jasen Lai , Chunmei Wang

We present FIT: a transformer-based architecture with efficient self-attention and adaptive computation. Unlike original transformers, which operate on a single sequence of data tokens, we divide the data tokens into groups, with each group…

Machine Learning · Computer Science 2023-05-26 Ting Chen , Lala Li

Physics-Informed Neural Networks (PINNs) have become a kind of attractive machine learning method for obtaining solutions of partial differential equations (PDEs). Training PINNs can be seen as a semi-supervised learning task, in which only…

Machine Learning · Computer Science 2022-10-25 Jia Guo , Haifeng Wang , Chenping Hou

Physics-Informed Neural Networks (PINNs) have gained popularity in solving nonlinear partial differential equations (PDEs) via integrating physical laws into the training of neural networks, making them superior in many scientific and…

Machine Learning · Computer Science 2023-08-15 Milad Ramezankhani , Abbas S. Milani

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Many-query computations, in which a computational model for an engineering system must be evaluated many times, are crucial in design and control. For systems governed by partial differential equations (PDEs), typical high-fidelity…

Numerical Analysis · Mathematics 2024-02-09 Tomoki Koike , Elizabeth Qian

Inverse problems involving partial differential equations (PDEs) can be seen as discovering a mapping from measurement data to unknown quantities, often framed within an operator learning approach. However, existing methods typically rely…

Numerical Analysis · Mathematics 2025-02-10 Sung Woong Cho , Hwijae Son

An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded…

Machine Learning · Computer Science 2025-11-18 Felipe Urrutia , Jorge Salas , Alexander Kozachinskiy , Cristian Buc Calderon , Hector Pasten , Cristobal Rojas

While Transformers have demonstrated remarkable potential in modeling Partial Differential Equations (PDEs), modeling large-scale unstructured meshes with complex geometries remains a significant challenge. Existing efficient architectures…

Machine Learning · Computer Science 2026-05-01 Zhuo Zhang , Xi Yang , Ying Miao , Xiaobin Hu , Yifu Gao , Yuan Zhao , Yong Yang , Canqun Yang , Boocheong Khoo

Learning partial differential equations' (PDEs) solution operators is an essential problem in machine learning. However, there are several challenges for learning operators in practical applications like the irregular mesh, multiple input…

Machine Learning · Computer Science 2023-06-16 Zhongkai Hao , Zhengyi Wang , Hang Su , Chengyang Ying , Yinpeng Dong , Songming Liu , Ze Cheng , Jian Song , Jun Zhu

Vision Transformer (ViT) has shown great potential for various visual tasks due to its ability to model long-range dependency. However, ViT requires a large amount of computing resource to compute the global self-attention. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Gaojie Wu , Wei-Shi Zheng , Yutong Lu , Qi Tian

Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures. Inspired by the evidence that pure self-attention possesses a strong…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Wenchi Ma , Tianxiao Zhang , Guanghui Wang

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Laziz U. Abdullaev , Maksim Tkachenko , Tan M. Nguyen

Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initialization remains challenging and computationally expensive. In this paper, we propose two…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Hongyi Pan , Emadeldeen Hamdan , Xin Zhu , Ahmet Enis Cetin , Ulas Bagci

The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent…

Computation and Language · Computer Science 2025-05-05 Md Kowsher , Nusrat Jahan Prottasha , Chun-Nam Yu , Ozlem Ozmen Garibay , Niloofar Yousefi

Neural operators have emerged as powerful data-driven solvers for PDEs, offering substantial acceleration over classical numerical methods. However, existing transformer-based operators still face critical challenges when modeling PDEs on…

Artificial Intelligence · Computer Science 2026-05-12 Chun-Wun Cheng , Sifan Wang , Carola-Bibiane Schönlieb , Angelica I. Aviles-Rivero