| Anchor function: a type of benchmark functions for studying language models Z Zhang, Z Wang, J Yao, Z Zhou, X Li, ZQJ Xu arXiv preprint arXiv:2401.08309, 2024 | 3 | 2024 |
| An upper limit of decaying rate with respect to frequency in linear frequency principle model T Luo, Z Ma, Z Wang, ZJ Xu, Y Zhang Mathematical and Scientific Machine Learning, 205-214, 2022 | 3 | 2022 |
| A deep learning-based model reduction (DeePMR) method for simplifying chemical kinetics Z Wang, Y Zhang, E Zhao, Y Ju, ZQJ Xu, T Zhang arXiv preprint arXiv:2201.02025, 2022 | 3 | 2022 |
| Towards understanding how transformer perform multi-step reasoning with matching operation Z Wang, Y Wang, Z Zhang, Z Zhou, H Jin, T Hu, J Sun, Z Li, Y Zhang, ... arXiv preprint arXiv:2405.15302, 2024 | 2 | 2024 |
| Fourier-domain variational formulation and its well-posedness for supervised learning T Luo, Z Ma, Z Wang, ZQJ Xu, Y Zhang arXiv preprint arXiv:2012.03238, 2020 | 2 | 2020 |
| Loss Jump During Loss Switch in Solving PDEs with Neural Networks Z Wang, L Zhang, Z Zhang, ZQJ Xu arXiv preprint arXiv:2405.03095, 2024 | | 2024 |
