Nequip
1 mentions across 1 person
Visit ↗All mentions
Alex Hormozi
Recommendedpaper · 2026-06-01
“We show that NequIP, an equivariant message-passing graph neural network (GNN), learns the high-dimensional, rugged potential energy landscape of the system and reproduces classical DFT energies across a range of PGN design parameters at four orders of magnitude lower cost.”
Equivariant GNNs Learn Many-Body Interactions in Amorphous Materials at 10,000x ↗