English
Related papers

Related papers: The E$\Delta$-MHC-Geo Transformer: Adaptive Geodes…

200 papers

Magnetic fields play an important role in many astrophysical systems and a detailed understanding of their impact on the gas dynamics requires robust numerical simulations. Here we present a new method to evolve the ideal…

Instrumentation and Methods for Astrophysics · Physics 2015-06-18 Philip Mocz , Mark Vogelsberger , Lars Hernquist

We propose Geometric Pareto Control (GPC), a framework overcoming barriers of reinforcement learning in cyber-physical systems where governing physics is known. Reinforcement learning confronts barriers in safety-critical applications:…

Systems and Control · Electrical Eng. & Systems 2026-05-12 Tong Wu

Group equivariant neural networks are used as building blocks of group invariant neural networks, which have been shown to improve generalisation performance and data efficiency through principled parameter sharing. Such works have mostly…

Machine Learning · Computer Science 2021-06-17 Michael Hutchinson , Charline Le Lan , Sheheryar Zaidi , Emilien Dupont , Yee Whye Teh , Hyunjik Kim

Graph transformers achieve strong results on molecular and long-range reasoning tasks, yet remain hampered by over-smoothing (the progressive collapse of node representations with depth) and attention entropy degeneration. We observe that…

Machine Learning · Computer Science 2026-04-21 Dongxin Guo , Jikun Wu , Siu Ming Yiu

We derive new models of stochastic Hall magnetohydrodynamics (MHD) by using a symmetry-reduced stochastic Euler-Poincar\'e variational principle. The new stochastic Hall MHD theory has potential applications for uncertainty quantification…

Plasma Physics · Physics 2024-04-11 Darryl D. Holm , Ruiao Hu , Oliver D. Street

Estimating the depths of equirectangular (i.e., 360) images (EIs) is challenging given the distorted 180 x 360 field-of-view, which is hard to be addressed via convolutional neural network (CNN). Although a transformer with global attention…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Ilwi Yun , Chanyong Shin , Hyunku Lee , Hyuk-Jae Lee , Chae Eun Rhee

We propose a novel approach for performing convolution of signals on curved surfaces and show its utility in a variety of geometric deep learning applications. Key to our construction is the notion of directional functions defined on the…

Graphics · Computer Science 2018-10-05 Adrien Poulenard , Maks Ovsjanikov

We introduce Steerable Transformers, an extension of the Vision Transformer mechanism that maintains equivariance to the special Euclidean group $\mathrm{SE}(d)$. We propose an equivariant attention mechanism that operates on features…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Soumyabrata Kundu , Risi Kondor

Hybrid beamformer design plays very crucial role in the next generation millimeter-wave (mm-Wave) massive MIMO (multiple-input multiple-output) systems. Previous works assume the perfect channel state information (CSI) which results heavy…

Signal Processing · Electrical Eng. & Systems 2020-08-18 Ahmet M. Elbir

We present a novel data-driven approach for enhancing gradient reconstruction in unstructured finite volume methods for hyperbolic conservation laws, specifically for the 2D Euler equations. Our approach extends previous structured-grid…

Numerical Analysis · Mathematics 2025-07-23 G. de Romémont , F. Renac , F. Chinesta , J. Nunez , D. Gueyffier

To bridge the gap between empirical success and theoretical understanding in transfer reinforcement learning (RL), we study a principled approach with provable performance guarantees. We introduce a novel composite MDP framework where…

Machine Learning · Statistics 2025-02-04 Jinhang Chai , Elynn Chen , Lin Yang

Euclidean geometry has historically been the typical "workhorse" for machine learning applications due to its power and simplicity. However, it has recently been shown that geometric spaces with constant non-zero curvature improve…

Machine Learning · Computer Science 2020-02-14 Ondrej Skopek , Octavian-Eugen Ganea , Gary Bécigneul

The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or…

Machine Learning · Computer Science 2025-04-01 Jianqing Liang , Min Chen , Jiye Liang

Magnetohydrodynamics (MHD) couples the Navier--Stokes and Maxwell equations into a nonlinear system of partial differential equations governing stellar interiors, astrophysical jets, fusion plasmas, and space weather. Numerical advances,…

High Energy Astrophysical Phenomena · Physics 2026-05-20 E. A. Huerta

Kinodynamic planning for car-like vehicles on uneven terrain requires simultaneously optimizing competing objectives such as path efficiency and pose stability. This work presents an adaptive epsilon-constraint method integrated into a…

Robotics · Computer Science 2026-05-21 Otobong Jerome , Geesara Kalathunga , Tiago Nascimento

An exotic rotationally invariant harmonic oscillator (ERIHO) is constructed by applying a non-unitary isotropic conformal bridge transformation (CBT) to a free planar particle. It is described by the isotropic harmonic oscillator…

Quantum Physics · Physics 2021-05-12 Luis Inzunza , Mikhail S. Plyushchay

This paper provides a further step in our program of studying superconformal nets over S^1 from the point of view of noncommutative geometry. For any such net A and any family Delta of localized endomorphisms of the even part A^gamma of A,…

Operator Algebras · Mathematics 2015-06-17 Sebastiano Carpi , Robin Hillier , Roberto Longo

We develop a unified geometric framework for mechanical systems that combine conservative and dissipative dynamics by formulating them on contact manifolds. Within this setting, we identify the Reeb vector field as the intrinsic generator…

Mathematical Physics · Physics 2025-12-16 Vinesh Vijayan , Pasupuleti Thejasree , P Satish Kumar , K Suganya

High-performance multimode/multiwavelength (de)multiplexer is one of the most pivotal photonic devices for advanced on-chip interconnect systems. Traditional on-chip photonic (de)multiplexing requires large device footprint for maintaining…

Optics · Physics 2025-09-03 Faqian Chong , Yulun Wu , Bingtao Gao , Shilong Li , Hongsheng Chen , Song Han

This paper presents a framework for analyzing and designing cylindrical omega-bianisotropic metasurfaces, inspired by mode matching and digital signal processing techniques. Using the discrete Fourier transform, we decompose the the…

Classical Physics · Physics 2022-03-10 Gengyu Xu , George V. Eleftheriades , Sean V. Hum