Igor Poltavsky, Mirela Puleva, Anton Charkin-Gorbulin, Grégory Fonseca, Ilyes Batatia, Nicholas J. Browning, Stefan Chmiela, Mengnan Cui, J. Thorben Frank, Stefan Heinen, Bing Huang, Silvan Käser, Adil Kabylda, Danish Khan, Carolin Müller, Alastair J. A. Price, Kai Riedmiller, Kai Töpfer, Tsz Wai Ko, Markus Meuwly, Matthias Rupp, Gábor Csányi, O. Anatole von Lilienfeld, Johannes T. Margraf, Klaus-Robert Müller and Alexandre Tkatchenko
Chem. Sci., 2025,16, 3738-3754
Abstract
We present a comprehensive analysis of the capabilities of modern machine learning force fields to simulate long-term molecular dynamics at near-ambient conditions for molecules, molecule-surface interfaces, and materials within TEA Challenge 2023.
Junmin Chen, Qian Gao, Miaofei Huang and Kuang Yu
Phys. Chem. Chem. Phys., 2025,27, 2294-2319
From themed collection:
2024 PCCP Reviews
Abstract
AI techniques provide unprecedented capabilities in molculear force field development, such as potential fitting, atom typification, and automatic optimization.
Pavlo O. Dral
Chem. Commun., 2024,60, 3240-3258
Abstract
AI-enhanced computational chemistry methods such as AIQM1 break through the limitations of the traditional quantum chemistry.
Igor Poltavsky, Anton Charkin-Gorbulin, Mirela Puleva, Grégory Fonseca, Ilyes Batatia, Nicholas J. Browning, Stefan Chmiela, Mengnan Cui, J. Thorben Frank, Stefan Heinen, Bing Huang, Silvan Käser, Adil Kabylda, Danish Khan, Carolin Müller, Alastair J. A. Price, Kai Riedmiller, Kai Töpfer, Tsz Wai Ko, Markus Meuwly, Matthias Rupp, Gábor Csányi, O. Anatole von Lilienfeld, Johannes T. Margraf, Klaus-Robert Müller and Alexandre Tkatchenko
Chem. Sci., 2025,16, 3720-3737
Abstract
Assessing the performance of modern machine learning force fields across diverse chemical systems to identify their strengths and limitations within the TEA Challenge 2023.
Tobias Kreiman and Aditi S. Krishnapriyan
Digital Discovery, 2026,5, 415-439
Abstract
We find common distribution shifts that pose challenges for universal machine learning interatomic potentials (MLIPs). We develop test-time refinement strategies that mitigate the shifts and provide insights into why MLIPs struggle to generalize.