PDE-Transformer is a neural network architecture designed to efficiently process and predict the evolution of physical systems described by partial differential equations.

NeurIPS 2025: Improving Monte Carlo Tree Search for Symbolic Regression

Code for Point-Calibrated Spectral Neural Operators

Run PyTorch in JAX. 🤝

A place to store reusable transformer components of my own creation or found on the interwebs

DAFoam: Discrete Adjoint with OpenFOAM for High-fidelity Multidisciplinary Design Optimization

2D/3D simplicial mesh generator interface for Python (Triangle, TetGen, gmsh)

[NeurIPS 2025] Geometry Aware Operator Transformer As An Efficient And Accurate Neural Surrogate For PDEs On Arbitrary Domains

A code generator for array-based code on CPUs and GPUs

Extension for dolfinx to handle multi-point constraints.

PyTorch implementation of the diffusion-based method for CFD data super-resolution proposed in the paper "A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction".

Advanced long-term earth system forecasting by learning the small-scale nature

Code to automatically prove or verify estimates in analysis

Parallel algorithms and data structures for tree-based adaptive mesh refinement (AMR) with arbitrary element shapes.

GINOT is a deep learning model that combines transformers with neural operators for accurate forward predictions on arbitrary 2D and 3D geometries. It processes surface point clouds using attention…

mathLab mirror of Python Dynamic Mode Decomposition

Interactive data visualizations and plotting in Julia

A Library for Advanced Neural PDE Solvers.

About code release of "Transolver: A Fast Transformer Solver for PDEs on General Geometries", ICML 2024 Spotlight. https://arxiv.org/abs/2402.02366

Extension of DOLFINx implementing the concept of external operator

[NeurIPS 2024 Spotlight] Towards Universal Mesh Movement Networks

RGB Driver for Linux

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

A Julia Basket of Hand-Picked Krylov Methods

The matrix cookbook, proved in the Lean theorem prover

3D plotting and mesh analysis through a streamlined interface for the Visualization Toolkit (VTK)