Pretrained model for molecular wavefunctions

MACE foundation models (MP, OMAT, Matpes)

Equivariant machine learning interatomic potentials in JAX.

Deep learning quantum Monte Carlo for electrons in real space

Machine learning algorithms for many-body quantum systems

DeepErwin is a python 3.8+ package that implements and optimizes JAX 2.x wave function models for numerical solutions to the multi-electron Schrödinger equation. DeepErwin supports weight-sharing w…

Reference implementation of "Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions" (ICLR, 2022) and "Sampling-free Inference ob Ab-Initio Potential Energy Surface Networks…

Official implementation of "Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations"

Efficient and Accurate Neural-Network Ansatz for Quantum Monte Carlo

An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations

Reference implementation of "Generalizing Neural Wave Functions" (ICML 2023)

Implementation of Forward Laplacian algorithm in JAX

Skala exchange-correlation functional

JAX accelerated Quantum Monte Carlo

Quantum Monte Carlo package, TurboRVB

MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.