FACTO: fast atom-centered tensor operator for accurate and efficient foundational machine-learned interatomic potentials
Abstract
High-throughput inference remains a central challenge for equivariant machine-learned interatomic potentials. Here we introduce FACTO, an atom-centered equivariant architecture that confines evolving learned state and dense channel mixing to atoms, expressing neighbor interactions as fully fusible reductions. We complement this design with custom register-accumulated aggregation kernels and tensor-core FP32 emulation, accelerating inference while retaining FP32-level energy conservation under emulated arithmetic in molecular dynamics. Comprehensive evaluations on Matbench Discovery, MLIP Arena and MatCalc demonstrate high throughput alongside strong predictive accuracy and physical reliability. On Matbench Discovery, the four FACTO-OAM variants show top-tier performance by overall rank sum among 46 models with complete scores, advancing the accuracy-throughput Pareto frontier. On MLIP Arena, FACTO achieves state- of-the-art stability under extreme heating and compression, alongside high fidelity in hydrogen combustion. On MatCalc, FACTO outperforms the compared baselines in structural and elastic predictions while retaining competitive accuracy for energetic and thermal properties.
Related
- Correcting the Liquid Densities of Universal Machine-Learning Interatomic Potentials Using Local-Number-Density Repulsion
- Foundation interatomic potentials learn the practical chemistry they were never taught
- pdb2reaction: End-to-End Reaction-Path Elucidation from PDB Structures Using Machine-Learning Interatomic Potentials
- Reference Conventions and Structure Types, Rather Than 4f Occupancy, Shape Lanthanide Errors in Universal Machine-Learning Interatomic Potentials
- Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials
BibTeX
@misc{liu2026facto,
title = {{FACTO: fast atom-centered tensor operator for accurate and efficient foundational machine-learned interatomic potentials}},
author = {Siyuan Liu and Chang Han and Sheng Gong and Yanping Yang and Tianze Zheng and Yu Xia and Kuang Yu and Shenzhen Xu and Wen Yan},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.03276},
eprint = {2611.03276},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.03276},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - FACTO: fast atom-centered tensor operator for accurate and efficient foundational machine-learned interatomic potentials
AU - Siyuan Liu
AU - Chang Han
AU - Sheng Gong
AU - Yanping Yang
AU - Tianze Zheng
AU - Yu Xia
AU - Kuang Yu
AU - Shenzhen Xu
AU - Wen Yan
PY - 2026
DA - 2026/11/02
PB - arXiv
DO - 10.48550/arxiv.2611.03276
UR - https://arxiv.org/abs/2611.03276
AB - High-throughput inference remains a central challenge for equivariant machine-learned interatomic potentials. Here we introduce FACTO, an atom-centered equivariant architecture that confines evolving learned state and dense channel mixing to atoms, expressing neighbor interactions as fully fusible reductions. We complement this design with custom register-accumulated aggregation kernels and tensor-core FP32 emulation, accelerating inference while retaining FP32-level energy conservation under emulated arithmetic in molecular dynamics. Comprehensive evaluations on Matbench Discovery, MLIP Arena and MatCalc demonstrate high throughput alongside strong predictive accuracy and physical reliability. On Matbench Discovery, the four FACTO-OAM variants show top-tier performance by overall rank sum among 46 models with complete scores, advancing the accuracy-throughput Pareto frontier. On MLIP Arena, FACTO achieves state- of-the-art stability under extreme heating and compression, alongside high fidelity in hydrogen combustion. On MatCalc, FACTO outperforms the compared baselines in structural and elastic predictions while retaining competitive accuracy for energetic and thermal properties.
ER -