Stars
DeepStruc is a Conditional Variational Autoencoder which can predict the mono-metallic nanoparticle from a Pair Distribution Function.
Implementation of Physics-Informed Diffusion Models
Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates
An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]
Artificial Intelligence Research for Science (AIRS)
a Flax-based implementation of PsiFormer and its variant
An E(3) equivariant Graph Neural Network for predicting electronic Hamiltonian matrix
An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations
MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
Universal Ensemble-Embedding Graph Neural Network for Direct Prediction of Optical Spectra from Crystal Structures
HPRO: Hamiltonian Projection and Reconstruction to atomic Orbitals
🤖 Machine Learning Summer School Guide