Saved in:
Bibliographic Details
Main Authors: Yang, Han, Liu, Xixian, Hu, Chenxi, Zhou, Yichi, Shi, Yu, Liu, Chang, Tan, Junfu, Li, Jielan, Li, Guanzhi, Wang, Qian, Zhu, Yu, Chen, Zekun, Chen, Shuizhou, Thiemann, Fabian, Zeni, Claudio, Horton, Matthew, Pinsler, Robert, Fowler, Andrew, Zügner, Daniel, Xie, Tian, Sun, Lixin, Chen, Yicheng, Kong, Lingyu, Bai, Yeqi, Gunceler, Deniz, Noé, Frank, Hao, Hongxia, Lu, Ziheng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.07927
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913171853279232
author Yang, Han
Liu, Xixian
Hu, Chenxi
Zhou, Yichi
Shi, Yu
Liu, Chang
Tan, Junfu
Li, Jielan
Li, Guanzhi
Wang, Qian
Zhu, Yu
Chen, Zekun
Chen, Shuizhou
Thiemann, Fabian
Zeni, Claudio
Horton, Matthew
Pinsler, Robert
Fowler, Andrew
Zügner, Daniel
Xie, Tian
Sun, Lixin
Chen, Yicheng
Kong, Lingyu
Bai, Yeqi
Gunceler, Deniz
Noé, Frank
Hao, Hongxia
Lu, Ziheng
author_facet Yang, Han
Liu, Xixian
Hu, Chenxi
Zhou, Yichi
Shi, Yu
Liu, Chang
Tan, Junfu
Li, Jielan
Li, Guanzhi
Wang, Qian
Zhu, Yu
Chen, Zekun
Chen, Shuizhou
Thiemann, Fabian
Zeni, Claudio
Horton, Matthew
Pinsler, Robert
Fowler, Andrew
Zügner, Daniel
Xie, Tian
Sun, Lixin
Chen, Yicheng
Kong, Lingyu
Bai, Yeqi
Gunceler, Deniz
Noé, Frank
Hao, Hongxia
Lu, Ziheng
contents Accurate property characterization is a major bottleneck in materials design. While first-principles methods and task-specific machine-learning models have driven important progress, they remain fundamentally limited in scalability and generalizability across the vast space of structures and properties relevant to real-world materials design. We present MatterSim-MT, a multi-task foundation model for in silico materials simulation and property characterization. The model is pretrained on over 35 million first-principles-labeled structures covering 89 elements, temperatures up to 5000 K and pressures up to 1000 GPa, and is fine-tuned on various properties including Bader charges, magnetic moments, Born effective charges, and dielectric matrices. Out of the box, MatterSim-MT not only serves as a foundation model for predicting material structure, dynamics and thermodynamics, its multi-task architecture also enables a wide range of complex simulations that cannot be captured by potential energy surfaces alone. For example, we demonstrate pressure-dependent LO-TO phonon splitting in SiC with close agreement with experiment, electric hysteresis in ferroelectric BaTiO3, and the cationic-to-anionic redox transition during delithiation of a Li-rich cathode material. Finally, we show that MatterSim-MT scales well with more data and parameters, can be efficiently fine-tuned to higher levels of theory, and can be efficiently extended to new systems via active learning. Overall, we believe this approach provides a scalable route to accurate in silico materials characterization.
format Preprint
id arxiv_https___arxiv_org_abs_2605_07927
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MatterSim-MT: A multi-task foundation model for in silico materials characterization
Yang, Han
Liu, Xixian
Hu, Chenxi
Zhou, Yichi
Shi, Yu
Liu, Chang
Tan, Junfu
Li, Jielan
Li, Guanzhi
Wang, Qian
Zhu, Yu
Chen, Zekun
Chen, Shuizhou
Thiemann, Fabian
Zeni, Claudio
Horton, Matthew
Pinsler, Robert
Fowler, Andrew
Zügner, Daniel
Xie, Tian
Sun, Lixin
Chen, Yicheng
Kong, Lingyu
Bai, Yeqi
Gunceler, Deniz
Noé, Frank
Hao, Hongxia
Lu, Ziheng
Materials Science
Accurate property characterization is a major bottleneck in materials design. While first-principles methods and task-specific machine-learning models have driven important progress, they remain fundamentally limited in scalability and generalizability across the vast space of structures and properties relevant to real-world materials design. We present MatterSim-MT, a multi-task foundation model for in silico materials simulation and property characterization. The model is pretrained on over 35 million first-principles-labeled structures covering 89 elements, temperatures up to 5000 K and pressures up to 1000 GPa, and is fine-tuned on various properties including Bader charges, magnetic moments, Born effective charges, and dielectric matrices. Out of the box, MatterSim-MT not only serves as a foundation model for predicting material structure, dynamics and thermodynamics, its multi-task architecture also enables a wide range of complex simulations that cannot be captured by potential energy surfaces alone. For example, we demonstrate pressure-dependent LO-TO phonon splitting in SiC with close agreement with experiment, electric hysteresis in ferroelectric BaTiO3, and the cationic-to-anionic redox transition during delithiation of a Li-rich cathode material. Finally, we show that MatterSim-MT scales well with more data and parameters, can be efficiently fine-tuned to higher levels of theory, and can be efficiently extended to new systems via active learning. Overall, we believe this approach provides a scalable route to accurate in silico materials characterization.
title MatterSim-MT: A multi-task foundation model for in silico materials characterization
topic Materials Science
url https://arxiv.org/abs/2605.07927