1d radial fluid simulator in JAX, 📖 https://jf1uids.web.app/

Official implementation of Stochastic Taylor Derivative Estimator (STDE) NeurIPS2024

A 15TB Collection of Physics Simulation Datasets

AL4PDE: A Benchmark for Active Learning for Neural PDE Solvers

[Neurips 2024] A benchmark suite for autoregressive neural emulation of PDEs. (≥46 PDEs in 1D, 2D, 3D; Differentiable Physics; Unrolled Training; Rollout Metrics)

Training methodologies for autoregressive neural operators in JAX.

Efficient Differentiable n-d PDE solvers in JAX.

Neural Emulator Architectures in JAX.

Library for reading and processing ML training data.

Pandoc template for writing Markdown letters (DIN 5008)

Distrax, but in equinox. Lightweight JAX library of probability distributions and bijectors.

Add a tqdm progress bar to your JAX scans and loops.

Matrix-free linear algebra in JAX.

iFEM is a MATLAB software package containing robust, efficient, and easy-following codes for the main building blocks of adaptive finite element methods on unstructured simplicial grids in both two…

Minimal Viable Product for an open source, github hosted, python package

Opinionated cookiecutter template for creating a new Python library

Source-to-Source Debuggable Derivatives in Pure Python

Oryx is a library for probabilistic programming and deep learning built on top of Jax.

An interactive HTML pretty-printer for machine learning research in IPython notebooks.

Time- and space-continuous neural PDE forecaster based on INRs and ODEs

A JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations

an Open Collaborative project to explore the implications — theoretical or practical — of the PDE perspective of ConvNets

Neural Operator-Assisted Computational Fluid Dynamics in PyTorch

Convolutional Differential Operators for Physics-based Deep Learning Study

[ICLR 2024] Neural Spectral Methods: Self-supervised learning in the spectral domain.

Turn jitted jax functions back into python source code

An open large-scale dataset for training high-resolution physics emulators in hybrid multi-scale climate simulators.

Simple 1d UNet in JAX & Equinox to solve the Poisson equation.