2 papers
cs.LG2026
Knowing when to trust machine-learned interatomic potentials
Shams Mehdi, Ilkwon Cho, Olexandr Isayev
Prevailing machine-learned interatomic potential (MLIP) uncertainty-quantification methods rely on ensembles of independently trained backbones. These methods scale unfavorably wit…
physics.ed-ph2024
PLUMED Tutorials: a collaborative, community-driven learning ecosystem
Gareth A. Tribello, Massimiliano Bonomi, Giovanni Bussi +60
In computational physics, chemistry, and biology, the implementation of new techniques in a shared and open source software lowers barriers to entry and promotes rapid scientific p…