Publications

Preprints and Submitted

J. He, X. Liu and J. Xu. Self-Composing Neural Operators with Depth and Accuracy Scaling via Adaptive Train-and-Unroll Approach. ArXiv: 2508.20650, 2025.
Y. Yang and J. He*. Deep Neural Networks with General Activations: Super-Convergence in Sobolev Norms. ArXiv:2508.05141, 2025.
H. Wu, Y. Gao, R. Shu, K. Wang, R. Gou, C. Wu, X. Liu, J. He, S. Cao, J. Fang, X. Shi, F. Tao, Q. Song, S. Ji, Y. Xiang, Y. Sun, J. Li, F. Xu, H. Dong, H. Wang, F. Zhang, P. Zhao, X. Wu, Q. Wen, D. Chen, and X. Huang. Advanced Long-term Earth System Forecasting by Learning the Small-scale Nature. ArXiv:2505.19432, 2025.
J. He, L. Liu and R. Tsai. Data-induced Multiscale Losses and Efficient Multirate Gradient Descent Schemes. ArXiv:2402.03021, 2024.
J. He, T. Mao and J. Xu. Expressivity and Approximation Properties of Deep Neural Networks with ${rm ReLU}^k$ Activation. ArXiv:2312.16483, 2025.
J. He and J. Xu. Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions. ArXiv:2312.14276, 2025.

Published and Accepted

J. He. On the Optimal Expressive Power of ReLU DNNs and Its Application in Approximation with Kolmogorov Superposition Theorem. IEEE Transactions on Neural Networks and Learning Systems, 36(8) 13886 - 13899, 2025. DOI: 10.1109/TNNLS.2024.3514126 [ArXiv].
G. Bao, Y. Zhao, J. He and Y. Zhang. Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection. The Thirteenth International Conference on Learning Representations (ICLR 2025). [ArXiv:2412.11506].
J. Zhu, H. Huang, Z. Lin, J. Liang, Z. Tang, K. Almubarak, M. Alharthi, B. An, J. He, X. Wu, F. Yu, J. Chen, Z. Ma, Y. Du, Y. Hu, H. Zhang, E. Alghamdi, L. Zhang, R. Sun, H. Li, J. Xu, B. Wang. Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion. ACL 2025 Oral.
J. Liang, Z. Cai, J. Zhu, H. Huang, K. Zong, B. An, M. Alharthi, J. He, L. Zhang, H. Li, B. Wang and J. Xu. Alignment at Pre-training! Towards Native Alignment for Arabic LLMs. The 38th International Conference on Neural Information Processing Systems (NeurIPS 2024).
Y. Yang and J. He*: Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss. The 41st International Conference on Machine Learning (ICML 2024), ArXiv:2402.00152, 2024.
H. Huang, F. Yu, J. Zhu, X. Sun, H. Cheng, D. Song, Z. Chen, M. Alharthi, B. An, J. He, Z. Liu, Z. Zhang, J. Chen, J. Li, B. Wang, L. Zhang, R. Sun, X. Wan, H. Li, J. Xu. AceGPT, Localizing Large Language Models in Arabic. NAACL 2024, ArXiv:2309.12053, 2024.
J. He, X. Liu and J. Xu. MgNO: Efficient Parameterization of Linear Operators via Multigrid. The Twelfth International Conference on Learning Representations (ICLR 2024). [Video Record], [ArXiv], [ResearchGate].
L. Liu, J. He and R. Tsai. Linear Regression on Manifold Structured Data: The Impact of Extrinsic Geometry on Solutions. Topological, Algebraic and Geometric Learning Workshops at ICML2023. PMLR 221:557-576, Published PDF 2023. [ArXiv].
J. Zhu*, J. He* and Q. Huang. An Enhanced V-cycle MgNet Model for Operator Learning in Numerical Partial Differential Equations. Computational Geosciences 2023. DOI:10.1007/s10596-023-10211-8 [ArXiv].
J. Zhu, J. He, L. Zhang and J. Xu. FV-MgNet: Fully Connected V-cycle MgNet for Interpretable Time Series Forecasting. Journal of Computational Science 69: 102005, 2023. https:doi.org10.1016j.jocs.2023.102005 [ArXiv].
J. He, J. Xu, L. Zhang and J. Zhu. An Interpretive Constrained Linear Model for ResNet and MgNet. Neural Networks. 162: 384-392, 2023. https:doi.org10.1016j.neunet.2023.03.011 [ArXiv].
J. He, R. Tsai and R. Ward. Side Effects of Learning from Low-dimensional Data Embedded in a Euclidean Space. Research in the Mathematical Sciences. 10(13), 2023. https:doi.org10.1007s40687-023-00378-y [ArXi].
J. He, L. Li and J. Xu. ReLU Deep Neural Networks from the Hierarchical Basis Perspective. Computers & Mathematics with Applications. 120: 105-114, 2022. https:doi.org10.1016j.camwa.2022.06.006. [ArXiv]
J. He, L. Li and J. Xu. Approximation Properties of Deep ReLU CNNs. Research in the Mathematical Sciences. 9(38), 2022. https:doi.org10.1007s40687-022-00336-0. [Springer Nature SharedIt] [ArXiv]
Q. Chen, W. Hao and J. He. Power Series Expansion Neural Network. Journal of Computational Science. 59, 2022. https:doi.org10.1016j.jocs.2021.101552. [ArXiv]
Q. Chen, W. Hao and J. He. A Weight Initialization Based on the Linear Product Structure for Neural Networks. Applied Mathematics and Computation. 415, 2022. https:doi.org10.1016j.amc.2021.126722. [ArXiv]
J. He, X. Jia, J. Xu, L. Zhang and L. Zhao. Make Regularization Effective in Training Sparse CNN. Computational Optimization and Applications. 77: 163–182, 2020. https:doi.org10.1007s10589-020-00202-1. [ArXiv]
J. He, L. Li, J. Xu, and C. Zheng. ReLU Deep Neural Networks and Linear Finite Elements. Journal of Computational Mathematics. 38(3): 502-527, 2020. https:doi:10.4208/jcm.1810-m2018-0096. [ArXiv] [ESI Highly Cited Paper in Mathematics (November/December 2022)]
J. He, K. Hu and J. Xu. Generalized Gaffney Inequality and Discrete Compactness for Discrete Differential Forms. Numerische Mathematik. 143: 781–795, 2019. https:doi.org10.1007s00211-019-01076-0. [ArXiv]
J. He and J. Xu. MgNet: A Unified Framework of Multigrid and Convolutional Neural Network. Science China Mathematics. 62(7): 1331–1354, 2019. https:doi.org10.1007s11425-019-9547-2. [ArXiv]

*: equal contributions or corresponding author.