AIMNet-2

AIMNet2 is a machine-learned interatomic potential included in a benchmark that evaluates the performance of various potentials in hybrid transition-state search workflows across a range of chemical reactions.

Papers using AIMNet-2 (3)

Basic stability tests of machine learning potentials for molecular simulations in computational drug discovery2025 · 5 citesHow Accurate Are DFT Forces? Unexpectedly Large Uncertainties in Molecular Datasets2025 · 1 citesReliable and Efficient Automated Transition-State Searches with Machine-Learned Interatomic Potentials2026