-
EPFL
- Lausanne
- marcel.science
- @marceldotsci
Stars
SO3krates and Universal Pairwise Force Field for Molecular Simulation
ORB forcefield models from Orbital Materials
Universal Tensor Operations in Einstein-Inspired Notation for Python.
A massively parallel, high-level programming language
An interface to various automatic differentiation backends in Julia.
Reference implementation of "Ewald-based Long-Range Message Passing for Molecular Graphs" (ICML 2023)
A flexible and performant framework for training machine learning potentials.
suadou / glp
Forked from sirmarcel/glptools for graph-based machine-learning potentials in jax
A dataset for benchmarking non-local capabilities of geometric machine learning models.
A collection of modern/faster/saner alternatives to common unix commands.
Physics simulation software for space + aerospace
Atomistic machine learning library for training interatomic potentials within PyTorch and PyTorch Geometric frameworks
Build neural networks for machine learning force fields with JAX
Multiple dispatch over abstract array types in JAX.
E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.
Hardware accelerated, batchable and differentiable optimizers in JAX.
Julia Programming for Machine Learning course at TU Berlin
Multi-language library for the calculation of spherical harmonics in Cartesian coordinates
Materials graph network with 3-body interactions featuring a DFT surrogate crystal relaxer and a state-of-the-art property predictor.