# Allegro-FM: Towards Equivariant Foundation Model for Exascale Molecular Dynamics Simulations

Source: [Allegro-FM: Towards Equivariant Foundation Model for Exascale Molecular Dynamics Simulations](<https://www.sota2.com/research/paper/68fa495d1e209131ce936737>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T07:18:36.594Z

Authors: Ken-ichi Nomura, Shinnosuke Hattori, Satoshi Ohmura, Ikumi Kanemasu, Kohei Shimamura, Nabankur Dasgupta, Aiichiro Nakano, Rajiv K. Kalia, Priya Vashishta

Published: 2025-02-09T23:37:08.000Z

## Abstract

We present a foundation model for exascale molecular dynamics simulations by leveraging an E(3) equivariant network architecture (Allegro) and a set of large-scale organic and inorganic materials datasets merged by Total Energy Alignment (TEA) framework. Thanks to the large-scale training sets, the obtained model (Allegro-FM) is versatile for various materials simulations for diverse downstream tasks covering 89 elements in the periodic table. Allegro-FM exhibits excellent agreements with high-level quantum chemistry theories in describing structural, mechanical, and thermodynamic properties, while exhibiting emergent capabilities for structural correlations, reaction kinetics, mechanical strengths, fracture, and solid/liquid dissolution, for which the model has not been trained. Furthermore, we demonstrate the robust predictability and generalizability of Allegro-FM for chemical reactions using the Transition1x that consists of 10k organic reactions and 9.6 million configurations including transition state data, as well as calcium silicate hydrates as a testbed. With its computationally efficient, strictly-local network architecture, Allegro-FM scales up to multi-billion-atom systems with a parallel efficiency of 0.964 on the exaflop/s Aurora supercomputer at Argonne Leadership Computing Facility. The approach presented in this work demonstrates the potential of the foundation model for a novel materials design and discovery based on large-scale atomistic simulations.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.06073>)

[PDF](<https://arxiv.org/pdf/2502.06073.pdf>)
