collaborators

19 papers

physics.chem-ph2026

Using large language models to probe the limits of atom-centered structural descriptors

Michelangelo Domina, Michele Ceriotti

The paper uses large language models to find atomic structures that cannot be distinguished by atom‑centered symmetry‑invariant descriptors even when clusters of up to seven neighb…

physics.chem-ph2026

Pushing the limits of unconstrained machine-learned interatomic potentials

Filippo Bigi, Paolo Pegolo, Arslan Mazitov +2

Machine-learned interatomic potentials (MLIPs) are increasingly used to replace computationally demanding electronic-structure calculations to model matter at the atomic scale. The…

physics.chem-ph2026

Comparing the latent features of universal machine-learning interatomic potentials

Sofiia Chorna, Davide Tisi, Cesare Malosso +3

The past few years have seen the development of ``universal'' machine-learning interatomic potentials (uMLIPs) capable of approximating the ground-state potential energy surface ac…

cs.LG2026

How unconstrained machine-learning models learn physical symmetries

Michelangelo Domina, Joseph William Abbott, Paolo Pegolo +2

The requirement of generating predictions that exactly fulfill the fundamental symmetry of the corresponding physical quantities has profoundly shaped the development of machine-le…

physics.chem-ph2026

How to Train a Shallow Ensemble

Moritz Schäfer, Matthias Kellner, Johannes Kästner +1

Shallow ensembles provide a convenient strategy for uncertainty quantification in machine learning interatomic potentials, that is computationally efficient because the different e…

physics.chem-ph2026

FlashMD: long-stride, universal prediction of molecular dynamics

Filippo Bigi, Sanggyu Chong, Agustinus Kristiadi +1

Molecular dynamics (MD) provides insights into atomic-scale processes by integrating over time the equations that describe the motion of atoms under the action of interatomic force…