| 2025 | ICLR | How Gradient descent balances features: A dynamical analysis for two-layer neural networks. | Zhenyu Zhu, Fanghui Liu, Volkan Cevher |
| 2025 | ICML | LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently. | Yuanhe Zhang, Fanghui Liu, Yudong Chen |
| 2024 | AAAI | The Role of Over-Parameterization in Machine Learning - the Good, the Bad, the Ugly. | Fanghui Liu |
| 2024 | ECCV | Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy. | Tao Li, Weisen Jiang, Fanghui Liu, Xiaolin Huang, James T. Kwok |
| 2024 | ICLR | Efficient local linearity regularization to overcome catastrophic overfitting. | Elas Abad-Rocamora, Fanghui Liu, Grigorios Chrysos, Pablo M. Olmos, Volkan Cevher |
| 2024 | ICLR | Generalization of Scaled Deep ResNets in the Mean-Field Regime. | Yihang Chen, Fanghui Liu, Yiping Lu, Grigorios Chrysos, Volkan Cevher |
| 2024 | ICLR | Robust NAS under adversarial training: benchmark, theory, and beyond. | Yongtao Wu, Fanghui Liu, Carl-Johann Simon-Gabriel, Grigorios Chrysos, Volkan Cevher |
| 2024 | ICML | Revisiting Character-level Adversarial Attacks for Language Models. | Elas Abad-Rocamora, Yongtao Wu, Fanghui Liu, Grigorios Chrysos, Volkan Cevher |
| 2024 | ICML | High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization. | Yihang Chen, Fanghui Liu, Taiji Suzuki, Volkan Cevher |
| 2023 | ICML | What can online reinforcement learning with function approximation benefit from general coverage conditions? | Fanghui Liu, Luca Viano, Volkan Cevher |
| 2023 | ICML | Benign Overfitting in Deep Neural Networks under Lazy Training. | Zhenyu Zhu, Fanghui Liu, Grigorios Chrysos, Francesco Locatello, Volkan Cevher |
| 2021 | AISTATS | Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures. | Fanghui Liu, Xiaolin Huang, Yingyi Chen, Johan A. K. Suykens |
| 2021 | AISTATS | Kernel regression in high dimensions: Refined analysis beyond double descent. | Fanghui Liu, Zhenyu Liao, Johan A. K. Suykens |
| 2020 | AAAI | Random Fourier Features via Fast Surrogate Leverage Weighted Sampling. | Fanghui Liu, Xiaolin Huang, Yudong Chen, Jie Yang, Johan A. K. Suykens |
| 2019 | CPAIOR | A Counting-Based Approach to Scalable Micro-service Deployment. | Waldemar Cruz, Fanghui Liu, Laurent Michel |
| 2019 | ICAISC | Dense Multi-focus Fusion Net: A Deep Unsupervised Convolutional Network for Multi-focus Image Fusion. | Hafiz Tayyab Mustafa, Fanghui Liu, Jie Yang, Zubair Khan, Qiao Huang |
| 2018 | AAAI | Nonlinear Pairwise Layer and Its Training for Kernel Learning. | Fanghui Liu, Xiaolin Huang, Chen Gong, Jie Yang, Li Li |
| 2018 | CP | Securely and Automatically Deploying Micro-services in an Hybrid Cloud Infrastructure. | Waldemar Cruz, Fanghui Liu, Laurent Michel |
| 2018 | CP | A Complete Tolerant Algebraic Side-Channel Attack for AES with CP. | Fanghui Liu, Waldemar Cruz, Laurent Michel |
| 2018 | ICONIP | Deep-PUMR: Deep Positive and Unlabeled Learning with Manifold Regularization. | Xingyu Chen, Fanghui Liu, Enmei Tu, Longbing Cao, Jie Yang |
| 2017 | CP | A Tolerant Algebraic Side-Channel Attack on AES Using CP. | Fanghui Liu, Waldemar Cruz, Chujiao Ma, Greg Johnson, Laurent Michel |
| 2017 | ICIP | Visual tracking via structural patch-based dictionary pair learning. | Tao Zhou, Fanghui Liu, Harish Bhaskar, Jie Yang, Lei Chen, Ping Cai |
| 2017 | ICONIP | Robust Kernel Approximation for Classification. | Fanghui Liu, Xiaolin Huang, Cheng Peng, Jie Yang, Nikola K. Kasabov |
| 2017 | ICONIP | Correlation Filters with Adaptive Memories and Fusion for Visual Tracking. | Cheng Peng, Fanghui Liu, Haiyan Yang, Jie Yang, Nikola K. Kasabov |
| 2016 | ICASSP | Robust visual tracking via inverse nonnegative matrix factorization. | Fanghui Liu, Tao Zhou, Keren Fu, Irene Y. H. Gu, Jie Yang |
| 2016 | ICIP | Correlation filter tracking via bootstrap learning. | Kunqi Gu, Tao Zhou, Fanghui Liu, Jie Yang, Yu Qiao |
| 2016 | ICONIP | Incremental Robust Nonnegative Matrix Factorization for Object Tracking. | Fanghui Liu, Mingna Liu, Tao Zhou, Yu Qiao, Jie Yang |