English
Related papers

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

200 papers

Recent advancements in learning-based Multi-View Stereo (MVS) methods have prominently featured transformer-based models with attention mechanisms. However, existing approaches have not thoroughly investigated the profound influence of…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Chenjie Cao , Xinlin Ren , Yanwei Fu

Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the…

Machine Learning · Computer Science 2022-06-27 Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Cyril Zhang

Transformer models rely on self-attention to capture token dependencies but face challenges in effectively integrating positional information while allowing multi-head attention (MHA) flexibility. Prior methods often model semantic and…

Machine Learning · Computer Science 2025-05-28 Jintian Shao , Hongyi Huang , Jiayi Wu , Beiwen Zhang , ZhiYu Wu , You Shan , MingKai Zheng

Transformer-based architectures achieve state-of-the-art performance across a wide range of tasks in natural language processing, computer vision, and speech processing. However, their immense capacity often leads to overfitting, especially…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Mirza Samad Ahmed Baig , Syeda Anshrah Gillani , Abdul Akbar Khan , Shahid Munir Shah , Muhammad Omer Khan

Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Qinyu Zhao , Guangting Zheng , Tao Yang , Rui Zhu , Xingjian Leng , Stephen Gould , Liang Zheng

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

Autonomous navigation in marine environments can be extremely challenging, especially in the presence of spatially varying flow disturbances and dynamic and static obstacles. In this work, we demonstrate that incorporating local flow field…

Robotics · Computer Science 2025-07-11 Ehsan Kazemi , Dechen Gao , Iman Soltani

Sparsifying the Transformer has garnered considerable interest, as training the Transformer is very computationally demanding. Prior efforts to sparsify the Transformer have either used a fixed pattern or data-driven approach to reduce the…

Machine Learning · Computer Science 2023-09-25 Bokyeong Yoon , Yoonsang Han , Gordon Euhyun Moon

Normalizing flows transform a simple base distribution into a complex target distribution and have proved to be powerful models for data generation and density estimation. In this work, we propose a novel type of normalizing flow driven by…

Machine Learning · Computer Science 2021-07-14 Ruizhi Deng , Bo Chang , Marcus A. Brubaker , Greg Mori , Andreas Lehrmann

Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interaction pattern induces strong synchronization dynamics that…

Machine Learning · Computer Science 2026-05-26 Jingkun Liu , Yisong Yue , Max Welling , Yue Song

Inverse medium scattering solvers generally reconstruct a single solution without an associated measure of uncertainty. This is true both for the classical iterative solvers and for the emerging deep learning methods. But ill-posedness and…

Machine Learning · Computer Science 2022-12-12 AmirEhsan Khorashadizadeh , Ali Aghababaei , Tin Vlašić , Hieu Nguyen , Ivan Dokmanić

We offer a theoretical mathematical background through Lagrangian optimization on the unit hyperspherical manifold and its tangential collection with application to the Transformer and its token space. Our methods are catered to the…

Machine Learning · Computer Science 2026-01-27 Andrew Gracyk

Bayesian posterior inference is prevalent in various machine learning problems. Variational inference provides one way to approximate the posterior distribution, however its expressive power is limited and so is the accuracy of resulting…

Machine Learning · Computer Science 2018-07-11 Guoqing Zheng , Yiming Yang , Jaime Carbonell

We introduce a provably stable variant of neural ordinary differential equations (neural ODEs) whose trajectories evolve on an energy functional parametrised by a neural network. Stable neural flows provide an implicit guarantee on…

Machine Learning · Computer Science 2020-03-19 Stefano Massaroli , Michael Poli , Michelangelo Bin , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

This paper introduces Generalized Attention Flow (GAF), a novel feature attribution method for Transformer-based models to address the limitations of current approaches. By extending Attention Flow and replacing attention weights with the…

Machine Learning · Computer Science 2025-02-25 Behrooz Azarkhalili , Maxwell Libbrecht

Transformers have become the dominant architecture for sequence modeling tasks such as natural language processing or audio processing, and they are now even considered for tasks that are not naturally sequential such as image…

Machine Learning · Computer Science 2024-03-05 Jorg Bornschein , Yazhe Li , Amal Rannen-Triki

MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data. In practice, it is often used as a latent MF by leveraging the pre-trained Stable…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Zheyuan Hu , Chieh-Hsin Lai , Ge Wu , Yuki Mitsufuji , Stefano Ermon

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

Feature evolvable learning has been widely studied in recent years where old features will vanish and new features will emerge when learning with streams. Conventional methods usually assume that a label will be revealed after prediction at…

Machine Learning · Computer Science 2021-02-24 Bo-Jian Hou , Yu-Hu Yan , Peng Zhao , Zhi-Hua Zhou

A convolutional encoder-decoder-based transformer model is proposed for autoregressively training on spatio-temporal data of turbulent flows. The prediction of future fluid flow fields is based on the previously predicted fluid flow field…

Fluid Dynamics · Physics 2023-03-31 Aakash Patil , Jonathan Viquerat , Elie Hachem