Publications

Google Scholar

(* indicates equal contribution)

Journal Papers (Mathematics/ML)

• Yihang Gao, Michael K. Ng, Vincent Y. F. Tan. Low Tensor-Rank Adaptation of Kolmogorov–Arnold Networks, IEEE Transactions on Signal Processing, 2025+. paper

• Yihang Gao, Vincent Y. F. Tan. On the Convergence of (Stochastic) Gradient Descent for Kolmogorov–Arnold Networks, IEEE Transactions on Information Theory, 2025+. paper

• Yihang Gao*, Chuanyang Zheng*, Enze Xie, Han Shi, Tianyang Hu, Yu Li, Michael Ng, Zhenguo Li, Zhaoqiang Liu. AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures, Transactions on Machine Learning Research, 2025. paper

• Yihang Gao, Michael K. Ng, Mingjie Zhou. Approximating Probability Distributions by Using Wasserstein Generative Adversarial Networks, SIAM Journal on Mathematics of Data Science, 2023. paper

• Yihang Gao, Xuelei Lin, Michael K. Ng. Blind Deconvolution for Multiple Observed Images with Missing Values, Pacific Journal of Optimization, 2023. paper

• Yihang Gao and Michael K. Ng. Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks, Journal of Computational Physics, 2022. paper (arxiv)

Conference Papers (Computer Science/ML/AI)

• Guoxuan Chen and Han Shi and Jiawei Li and Yihang Gao and Xiaozhe Ren and Yimeng Chen and Xin Jiang and Zhenguo Li and Weiyang Liu and Chao Huang. SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator, 42nd International Conference on Machine Learning (ICML), 2025.

• Chuanyang Zheng, Yihang Gao, Han Shi, Jing Xiong, Jiankai Sun, Jingyao Li, Minbin Huang, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, Yu Li. DAPE V2: Process Attention Score as Feature Map for Length Extrapolation, The 63rd Annual Meeting of the Association for Computational Linguistics (ACL main), 2025.

• Chuanyang Zheng*, Yihang Gao*, Han Shi, Minbin Huang, Jingyao Li, Jing Xiong, Xiaozhe Ren, Michael K. Ng, Xin Jiang, Zhenguo Li, Yu Li. DAPE: Data-Adaptive Positional Encoding for Length Extrapolation, Advances in Neural Information Processing Systems 2024 (NeurIPS 2024). arxiv

• Yihang Gao, Yiqi Gu, Michael K. Ng. Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks, 40th International Conference on Machine Learning 2023 (ICML 2023). paper

• Yihang Gao, Man-Chung Yue, Michael K. Ng. Approximate Secular Equations for the Cubic Regularization Subproblem, Advances in Neural Information Processing Systems 2022 (NeurIPS 2022). paper / poster / slides

• Yihang Gao, Ka Chun Cheung, Michael K. Ng. SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition, IEEE Symposium Series on Computational Intelligence 2022 (IEEE SSCI 2022). paper (arxiv)