Efficient Differentiable n-d PDE Solvers in JAX.
[Neurips 2024] A benchmark suite for autoregressive neural emulation of PDEs. (≥46 PDEs in 1D, 2D, 3D; Differentiable Physics; Unrolled Training; Rollout Metrics)
Differentiable Hydrologic Model Library
A simple JAX-powered simulation library for numerical experiments of fuzzy dark matter, stars, gas + more!
A library for soft differentiable relaxations of common JAX functions.
Generic framework for building differentiable models.
Electromagnetics simulation library for moving point charges built on JAX
A differentiable astrophysics simulator in JAX
Universal Partial Differential Equations Simulator
A library for soft differentiable relaxations of common PyTorch functions.
