Tao Li

20 papers A* 3Misc 1Journal 15Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Multi-head ensemble of smoothed classifiers for certified robustness.
Neural Networks
Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Xiaolin Huang, Jie Yang
2025 J jnl
Towards Natural Machine Unlearning.
IEEE Trans. Pattern Anal. Mach. Intell.
Zhengbao He, Tao Li, Xinwen Cheng, Zhehao Huang, Xiaolin Huang
2024 Misc conf
Better Generalization in Fast Training: Flat Trainable Weight in Subspace.
ICMLC
Zehao Lei, Yingwen Wu, Tao Li
2024 A* conf
Friendly Sharpness-Aware Minimization.
CVPR
Tao Li, Pan Zhou, Zhengbao He, Xinwen Cheng, Xiaolin Huang
2024 J jnl
Friendly Sharpness-Aware Minimization.
CoRR
Tao Li, Pan Zhou, Zhengbao He, Xinwen Cheng, Xiaolin Huang
2024 J jnl
Low-Dimensional Gradient Helps Out-of-Distribution Detection.
IEEE Trans. Pattern Anal. Mach. Intell.
Yingwen Wu, Tao Li, Xinwen Cheng, Jie Yang, Xiaolin Huang
2024 J jnl
Revisiting Random Weight Perturbation for Efficiently Improving Generalization.
CoRR
Tao Li, Qinghua Tao, Weihao Yan, Zehao Lei, Yingwen Wu, Kun Fang, Mingzhen He, Xiaolin Huang
2024 J jnl
Revisiting Random Weight Perturbation for Efficiently Improving Generalization.
Trans. Mach. Learn. Res.
Tao Li, Qinghua Tao, Weihao Yan, Yingwen Wu, Zehao Lei, Kun Fang, Mingzhen He, Xiaolin Huang
2024 J jnl
Towards robust neural networks via orthogonal diversity.
Pattern Recognit.
Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Jia Cai, Feipeng Cai, Xiaolin Huang, Jie Yang
2023 — conf
Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective.
CVPR Workshops
Zhengbao He, Tao Li, Sizhe Chen, Xiaolin Huang
2023 J jnl
Low Dimensional Trajectory Hypothesis is True: DNNs Can Be Trained in Tiny Subspaces.
IEEE Trans. Pattern Anal. Mach. Intell.
Tao Li, Lei Tan, Zhehao Huang, Qinghua Tao, Yipeng Liu, Xiaolin Huang
2023 J jnl
Low-Dimensional Gradient Helps Out-of-Distribution Detection.
CoRR
Yingwen Wu, Tao Li, Xinwen Cheng, Jie Yang, Xiaolin Huang
2023 A* conf
Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions.
ICLR
Tao Li, Zhehao Huang, Qinghua Tao, Yingwen Wu, Xiaolin Huang
2022 J jnl
Efficient Generalization Improvement Guided by Random Weight Perturbation.
CoRR
Tao Li, Weihao Yan, Zehao Lei, Yingwen Wu, Kun Fang, Ming Yang, Xiaolin Huang
2022 J jnl
On Multi-head Ensemble of Smoothed Classifiers for Certified Robustness.
CoRR
Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Xiaolin Huang, Jie Yang
2022 A* conf
Subspace Adversarial Training.
CVPR
Tao Li, Yingwen Wu, Sizhe Chen, Kun Fang, Xiaolin Huang
2022 J jnl
Trainable Weight Averaging for Fast Convergence and Better Generalization.
CoRR
Tao Li, Zhehao Huang, Qinghua Tao, Yingwen Wu, Xiaolin Huang
2021 J jnl
Subspace Adversarial Training.
CoRR
Tao Li, Yingwen Wu, Sizhe Chen, Kun Fang, Xiaolin Huang
2021 J jnl
Train Deep Neural Networks in 40-D Subspaces.
CoRR
Tao Li, Lei Tan, Qinghua Tao, Yipeng Liu, Xiaolin Huang
2020 J jnl
Learn Robust Features via Orthogonal Multi-Path.
CoRR
Kun Fang, Yingwen Wu, Tao Li, Xiaolin Huang, Jie Yang