GEqTrain: A Configuration-Driven Framework for Retargeting Equivariant Graph Neural Networks Across 3D Scientific Tasks
GEqTrain is presented, a configuration-driven framework that separates dataset semantics, model composition, and training objectives, and GEqDiff, a generative extension based on equivariant flow matching that aims to make equivariant modeling more reproducible, extensible, and reusable.
Daniele Angioletti, Marco Nobile, V. Limongelli
· 0 citations