Cover Image

How unconstrained machine-learning models learn physical symmetries

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Domina, Michelangelo, Abbott, Joseph William, Pegolo, Paolo, Bigi, Filippo, Ceriotti, Michele
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Materials Science Chemical Physics Computational Physics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Representing spherical tensors with scalar-based machine-learning models
by: Domina, Michelangelo, et al.
Published: (2025)

Pushing the limits of unconstrained machine-learned interatomic potentials
by: Bigi, Filippo, et al.
Published: (2026)

High-quality, high-information datasets for universal atomistic machine learning
by: Malosso, Cesare, et al.
Published: (2026)

A general formalism for machine-learning models based on multipolar-spherical harmonics
by: Domina, Michelangelo, et al.
Published: (2025)

The dark side of the forces: assessing non-conservative force models for atomistic machine learning
by: Bigi, Filippo, et al.
Published: (2024)

Learning the action for long-time-step simulations of molecular dynamics
by: Bigi, Filippo, et al.
Published: (2025)

PET-MAD, a lightweight universal interatomic potential for advanced materials modeling
by: Mazitov, Arslan, et al.
Published: (2025)

A universal machine learning model for the electronic density of states
by: How, Wei Bin, et al.
Published: (2025)

Comparing the latent features of universal machine-learning interatomic potentials
by: Chorna, Sofiia, et al.
Published: (2025)

Smooth, exact rotational symmetrization for deep learning on point clouds
by: Pozdnyakov, Sergey N., et al.
Published: (2023)

Probing the effects of broken symmetries in machine learning
by: Langer, Marcel F., et al.
Published: (2024)

FlashMD: long-stride, universal prediction of molecular dynamics
by: Bigi, Filippo, et al.
Published: (2025)

Massive Atomic Diversity: a compact universal dataset for atomistic machine learning
by: Mazitov, Arslan, et al.
Published: (2025)

Resolving the Body-Order Paradox of Machine Learning Interatomic Potentials
by: Chong, Sanggyu, et al.
Published: (2025)

Latent Ewald summation for machine learning of long-range interactions
by: Cheng, Bingqing
Published: (2024)

Adaptive energy reference for machine-learning models of the electronic density of states
by: How, Wei Bin, et al.
Published: (2024)

How accurate are foundational machine learning interatomic potentials for heterogeneous catalysis?
by: Kempen, Luuk H. E., et al.
Published: (2025)

MBD-ML: Many-body dispersion from machine learning for molecules and materials
by: Moerman, Evgeny, et al.
Published: (2026)

Long-range electrostatics for machine learning interatomic potentials is easier than we thought
by: Kim, Dongjin, et al.
Published: (2025)

Errors that matter: Uncertainty-aware universal machine-learning potentials calibrated on experiments
by: Kellner, Matthias, et al.
Published: (2026)

PAL -- Parallel active learning for machine-learned potentials
by: Zhou, Chen, et al.
Published: (2024)

Multimodal machine learning with large language embedding model for polymer property prediction
by: Zhang, Tianren, et al.
Published: (2025)

Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning
by: Bigi, Filippo, et al.
Published: (2025)

Reducing cross-sample prediction churn in scientific machine learning
by: Prastalo, Gordan, et al.
Published: (2026)

Interpolation and differentiation of alchemical degrees of freedom in machine learning interatomic potentials
by: Nam, Juno, et al.
Published: (2024)

Polarizable atomic multipoles for learning long-range electrostatics
by: Kim, Dongjin, et al.
Published: (2026)

Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models
by: Cázares-Trejo, Leonardo, et al.
Published: (2025)

Machine learning interatomic potential can infer electrical response
by: Zhong, Peichen, et al.
Published: (2025)

Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
by: Schwalbe-Koda, Daniel, et al.
Published: (2024)

Grad DFT: a software library for machine learning enhanced density functional theory
by: Casares, Pablo A. M., et al.
Published: (2023)

Constructing accurate machine-learned potentials and performing highly efficient atomistic simulations to predict structural and thermal properties
by: Liu, Junlan, et al.
Published: (2024)

Breaking scaling relations with inverse catalysts: a machine learning exploration of trends in $\mathrm{CO_2}$ hydrogenation energy barriers
by: Kempen, Luuk H. E., et al.
Published: (2025)

Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
by: Suman, Divya, et al.
Published: (2025)

Machine learning frontier orbital energies of nanodiamonds
by: Kirschbaum, Thorren, et al.
Published: (2022)

Machine learning Hubbard parameters with equivariant neural networks
by: Uhrin, Martin, et al.
Published: (2024)

Predicting band gap from chemical composition: A simple learned model for a material property with atypical statistics
by: Ma, Andrew, et al.
Published: (2025)

A machine-learning framework for accelerating spin-lattice relaxation simulations
by: Briganti, Valerio, et al.
Published: (2024)

Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations
by: Timmerman, Lucas R., et al.
Published: (2024)

Accelerating point defect simulations using data-driven and machine learning approaches
by: Mannodi-Kanakkithodi, Arun, et al.
Published: (2026)

Can machines learn density functionals? Past, present, and future of ML in DFT
by: Akashi, Ryosuke, et al.
Published: (2025)