collaborators

7 papers

physics.comp-ph2026

TorchNEP: Ultra-Efficient and Accurate Training of Neuroevolution Potentials

Yong-Chao Wu, Xiaoya Chang, Tero Mäkinen +5

Neuroevolution Potential (NEP) is one of the most efficient machine-learned interatomic potential frameworks for large-scale atomistic simulations. However, its original training s…

physics.comp-ph2026

NEPMaker: Active learning of neuroevolution machine learning potential for large cells

Junjie Wang, Shuning Pan, Haoting Zhang +4

Machine learning potentials (MLPs) achieve near first-principles accuracy but often fail for atomic environments outside the training distribution. Active learning can mitigate thi…

physics.comp-ph2026

GPU-MetaD: Full-Life-Cycle GPU Accelerated Metadynamics with Machine Learning Potentials

Haoting Zhang, Qiuhan Jia, Zhennan Zhang +6

Large-scale molecular dynamics simulations with high accuracy have been increasingly popular for their capability to bridge the gap between atomistic modeling and mesoscale phenome…

cond-mat.mtrl-sci2026

GPUMDkit: A User-Friendly Toolkit for GPUMD and NEP

Zihan Yan, Denan Li, Xin Wu +20

Machine-learned interatomic potentials have revolutionized molecular dynamics simulations by providing quantum-mechanical accuracy at empirical-potential speeds. The graphics proce…

physics.comp-ph2026

NEP-CG and NEP-AACG: Efficient coarse-grained and multiscale all-atom-coarse-grained neuroevolution potentials

Zheyong Fan, Wenjun Zhang, Zhenhao Zhang +3

Machine-learned coarse-grained (CG) models often suffer from noisy training data, limiting their accuracy and transferability. We propose a method to generate low-noise training da…

physics.comp-ph2026

qNEP: A highly efficient neuroevolution potential with dynamic charges for large-scale atomistic simulations

Zheyong Fan, Benrui Tang, Esmée Berger +13

Although electrostatics can be incorporated into machine-learned interatomic potentials, existing approaches are computationally very demanding, limiting large-scale, long-time sim…