SciML

Predicting electronic structures at any length scale with machine learning
Training-free hyperparameter optimization of neural networks for electronic structures in matter
Concentric Spherical Neural Network for 3D Representation Learning
Machine Learning for Materials Modeling
Using Machine Learning to Accelerate Science Calculations
Accelerating finite-temperature Kohn-Sham density functional theory with deep neural networks
Co-design center for exascale machine learning technologies (ExaLearn)
Concentric Spherical GNN for 3D Representation Learning
Union: A unified HW-SW Co-Design ecosystem in MLIR for evaluating tensor operations on spatial accelerators
Towards simulations on the Exascale hardware and beyond