AI RESEARCH

Scaling Machine Learning Interatomic Potentials with Mixtures of Experts

arXiv CS.LG

ArXi:2603.07977v1 Announce Type: cross Machine Learning Interatomic Potentials (MLIPs) enable accurate large-scale atomistic simulations, yet improving their expressive capacity efficiently remains challenging. Here we systematically develop Mixture-of-Experts (MoE) and Mixture-of-Linear-Experts (MoLE) architectures for MLIPs and analyze the effects of routing strategies and expert designs.