Recent advances of data-driven machine learning have revolutionized fields like computer
vision, reinforcement learning, and many scientific and engineering domains. In many real …

Partial differential equations (PDEs) see widespread use in sciences and engineering to
describe simulation of physical processes as scalar and vector fields interacting and …

Transformer has shown state-of-the-art performance on various applications and has
recently emerged as a promising tool for surrogate modeling of partial differential equations …

Partial differential equations (PDEs) are central to describing complex physical system
simulations. Their expensive solution techniques have led to an increased interest in deep …

Neural networks have shown promising potential in accelerating the numerical simulation of
systems governed by partial differential equations (PDEs). Different from many existing …

We present a novel graph transformer framework, HAMLET, designed to address the
challenges in solving partial differential equations (PDEs) using neural networks. The …

Applying machine learning methods and Neural Operators to solve differential equations
has proven effective in generating reliable surrogates. However, incorporating boundary …

We develop a novel computational framework to approximate solution operators of evolution
partial differential equations (PDEs). By employing a general nonlinear reduced-order …

Neural networks have shown promising potential in accelerating the numerical simulation of
systems governed by partial differential equations (PDEs). While many of the existing neural …

Time-independent Partial Differential Equations (PDEs) on large meshes pose significant
challenges for data-driven neural PDE solvers. We introduce a novel graph rewiring …