A generative world for general-purpose robotics & embodied AI learning.

Learning in infinite dimension with neural operators.

High-Performance Symbolic Regression in Python and Julia

Massively parallel rigidbody physics simulation on accelerator hardware.

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

Fast and Easy Infinite Neural Networks in Python

A 15TB Collection of Physics Simulation Datasets

A differentiable PDE solving framework for machine learning

A package for the sparse identification of nonlinear dynamical systems from data

Computations and statistics on manifolds with geometric structures.

Differentiable, Hardware Accelerated, Molecular Dynamics

Aircraft design optimization made fast through computational graph transformations (e.g., automatic differentiation). Composable analysis tools for aerodynamics, propulsion, structures, trajectory …

PDEBench: An Extensive Benchmark for Scientific Machine Learning

The Fastest Deep Reinforcement Learning Library

Computational Fluid Dynamics in JAX

Python toolbox for optimization on Riemannian manifolds with support for automatic differentiation

TORAX: Tokamak transport simulation in JAX

Differentiable Fluid Dynamics Package

Large-Scale Multimodal Dataset of Astronomical Data

A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

XLB: Accelerated Lattice Boltzmann (XLB) for Physics-based ML

Code repository for our paper DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact

NeuralFoil is a practical airfoil aerodynamics analysis tool using physics-informed machine learning, exposed to end-users in pure Python/NumPy.

Turn SymPy expressions into trainable JAX expressions.

[ICLR 2024] DiffTactile: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation

A library for programmatically generating equivariant layers through constraint solving

[ICLR 2023] FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation

High performance computational platform in Python for the spectral Galerkin method