Citation

If you use TorchNEP in your research, please cite:

@misc{wu2026torchne,
      title={TorchNEP: Ultra-Efficient and Accurate Training of Neuroevolution Potentials},
      author={Yong-Chao Wu and Xiaoya Chang and Tero Mäkinen and Amin Esfandiarpour and Jian-Li Shao and Tapio Ala-Nissila and Zheyong Fan and Mikko Alava},
      year={2026},
      eprint={2606.19557},
      archivePrefix={arXiv},
      primaryClass={physics.comp-ph},
      url={https://arxiv.org/abs/2606.19557},
}

The training inputs and trained models of the paper are available in TorchNEP_models.

NEP itself is developed in GPUMD; please also cite the NEP papers listed there.

License

TorchNEP is free software under the GNU General Public License v3.0 or later.