Mengyi Chen

About Me

I am currently a fourth-year Ph.D. student in Mathematics at the National University of Singapore, advised by Prof. Qianxiao Li. I also work closely with Prof. Peichen Zhong from the Department of Materials Science and Engineering at NUS. I received my B.Sc. in Mathematics and Applied Mathematics from the University of Chinese Academy of Sciences in 2023.

I am especially drawn to problems where machine learning can lead to real scientific discoveries.

🎓 I expect to graduate in mid-2027 and am open to research opportunities in both academia and industry. I am always happy to discuss research and potential collaborations.

Research Interests

Machine learning for multiscale modeling: methods for mesoscale and macroscale modeling of materials from microscopic data
Thermodynamics of complex materials: computing free energy and entropy for phase stability and synthesis
Ab initio phase-field models: phase transformations and microstructure evolution at realistic experimental scales and conditions

News

📅 [Nov. 2026] Will attend RSC FIRST 2026: AI in Chemistry in Xiamen, China.
📄 [Oct. 2026] New preprint: Learning ab initio phase-field models. Check out our project page!
📄 [Jun. 2026] New preprint: Interfacial melting as a thermodynamic indicator of solid-state synthesizability.
🎤 [Jun. 2026] Gave a talk on Scalable Learning of Macroscopic Stochastic Dynamics at AI4X-Accelerate 2026 in Singapore.

Selected Publications

arXiv

Learning Ab Initio Phase-Field Models

Mengyi Chen, Peichen Zhong, Zihan Zhang, Qianxiao Li

arXiv preprint arXiv:2610.01432, 2026.

🚀 Project Page ↗

Nat. Commun.

Interfacial Melting as a Thermodynamic Indicator of Solid-State Synthesizability

Zihan Zhang*, Mengyi Chen*, Qianxiao Li, Peichen Zhong

Nature Communications, in press, 2026.

ICML

Learning Permutation-Invariant Macroscopic Dynamics

Zhichao Han, Mengyi Chen, Qianxiao Li

International Conference on Machine Learning (ICML), 2026.

PRM

Scalable Learning of Macroscopic Stochastic Dynamics

Mengyi Chen, Pengru Huang, Kostya S. Novoselov, Qianxiao Li

Physical Review Materials, 10(3):033805, 2026.

NeurIPS

Learning Macroscopic Dynamics from Partial Microscopic Observations

Mengyi Chen, Qianxiao Li

Advances in Neural Information Processing Systems (NeurIPS), 2024.

NMI

A Predictive Machine Learning Force-Field Framework for Liquid Electrolyte Development

Sheng Gong, Yumin Zhang, Zhenliang Mu, Zhichen Pu, Hongyi Wang, Xu Han, Zhiao Yu, Mengyi Chen, Tianze Zheng, Zhi Wang, Lifei Chen, Zhenze Yang, Xiaojie Wu, Shaochen Shi, Weihao Gao, Wen Yan, Liang Xiang

Nature Machine Intelligence, 7(4):543–552, 2025.

Service

Co-organizer, ICLR 2025 Workshop on Machine Learning Multiscale Processes (MLMP), Singapore, 2025

Education

National University of Singapore, Ph.D. in Mathematics, Aug. 2023 – present (expected Aug. 2027)
Advisor: Prof. Qianxiao Li
Columbia University, Visiting Student, Department of Applied Physics and Applied Mathematics, Jan. 2022 – May 2022
University of Chinese Academy of Sciences, B.Sc. in Mathematics and Applied Mathematics, Sep. 2019 – Jun. 2023

Internships

ByteDance AML Research, Research Intern, Beijing, Dec. 2022 – Jul. 2023
Developed equivariant graph neural network models for machine-learning force fields in the BAMBOO project (ByteDance AI Molecular Simulation Booster)

Beyond Research

Outside research, I enjoy rock climbing 🧗 and playing the violin 🎻.