Saved in:
Bibliographic Details
Main Authors: Reschützegger, Thiago, Aykent, Sarp, Perin, Gabriel Jacob, Nunes, Bruno Henrique, Cipcigan, Flaviu, Ferreira, Rodrigo Neumann Barros, Steiner, Mathias, Thiemann, Fabian L.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.15492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911391744524288
author Reschützegger, Thiago
Aykent, Sarp
Perin, Gabriel Jacob
Nunes, Bruno Henrique
Cipcigan, Flaviu
Ferreira, Rodrigo Neumann Barros
Steiner, Mathias
Thiemann, Fabian L.
author_facet Reschützegger, Thiago
Aykent, Sarp
Perin, Gabriel Jacob
Nunes, Bruno Henrique
Cipcigan, Flaviu
Ferreira, Rodrigo Neumann Barros
Steiner, Mathias
Thiemann, Fabian L.
contents Foundational machine-learned interatomic potentials have emerged as powerful tools for atomistic simulations, promising near first-principles accuracy across diverse chemical spaces at a fraction of the cost of quantum-mechanical calculations. However, the most accurate equivariant architectures rely on Clebsch-Gordan tensor products whose computational cost scales steeply with angular resolution, creating a trade-off between model expressiveness and inference speed that ultimately limits practical applications. Here we introduce Geodite, an equivariant message-passing architecture that replaces tensor products while incorporating physical priors to ensure smooth, well-behaved potential energy surfaces. Trained on the Materials Project trajectories dataset of inorganic crystals, Geodite-MP achieves accuracy competitive with leading methods on benchmarks for materials stability prediction, thermal conductivity, phonon-derived properties, and nanosecond-scale molecular dynamics, while running $3\text{--}5\times$ faster than models performing similarly. By combining predictive accuracy, computational efficiency, and physicality, Geodite enables faster large-scale atomistic simulations and high-throughput screening that would otherwise be computationally prohibitive.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Equivariant Interatomic Potentials without Tensor Products
Reschützegger, Thiago
Aykent, Sarp
Perin, Gabriel Jacob
Nunes, Bruno Henrique
Cipcigan, Flaviu
Ferreira, Rodrigo Neumann Barros
Steiner, Mathias
Thiemann, Fabian L.
Computational Physics
Foundational machine-learned interatomic potentials have emerged as powerful tools for atomistic simulations, promising near first-principles accuracy across diverse chemical spaces at a fraction of the cost of quantum-mechanical calculations. However, the most accurate equivariant architectures rely on Clebsch-Gordan tensor products whose computational cost scales steeply with angular resolution, creating a trade-off between model expressiveness and inference speed that ultimately limits practical applications. Here we introduce Geodite, an equivariant message-passing architecture that replaces tensor products while incorporating physical priors to ensure smooth, well-behaved potential energy surfaces. Trained on the Materials Project trajectories dataset of inorganic crystals, Geodite-MP achieves accuracy competitive with leading methods on benchmarks for materials stability prediction, thermal conductivity, phonon-derived properties, and nanosecond-scale molecular dynamics, while running $3\text{--}5\times$ faster than models performing similarly. By combining predictive accuracy, computational efficiency, and physicality, Geodite enables faster large-scale atomistic simulations and high-throughput screening that would otherwise be computationally prohibitive.
title Equivariant Interatomic Potentials without Tensor Products
topic Computational Physics
url https://arxiv.org/abs/2601.15492