Tao Li

Orcid: 0000-0002-8010-1447

According to our database¹, Tao Li authored at least 12 papers between 2020 and 2025.

Collaborative distances:

Dijkstra number² of five.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

Multi-head ensemble of smoothed classifiers for certified robustness.

[BibT_eX]

[DOI]

Neural Networks, 2025

2024

Low-Dimensional Gradient Helps Out-of-Distribution Detection.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., December, 2024

Revisiting Random Weight Perturbation for Efficiently Improving Generalization.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2024

Towards robust neural networks via orthogonal diversity.

[BibT_eX]

[DOI]

Pattern Recognit., 2024

Better Generalization in Fast Training: Flat Trainable Weight in Subspace.

[BibT_eX]

[DOI]

Zehao Lei

Yingwen Wu

Tao Li

Proceedings of the 2024 16th International Conference on Machine Learning and Computing, 2024

2023

Low Dimensional Trajectory Hypothesis is True: DNNs Can Be Trained in Tiny Subspaces.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., March, 2023

Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Efficient Generalization Improvement Guided by Random Weight Perturbation.

[BibT_eX]

[DOI]

CoRR, 2022

Trainable Weight Averaging for Fast Convergence and Better Generalization.

[BibT_eX]

[DOI]

CoRR, 2022

Subspace Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Train Deep Neural Networks in 40-D Subspaces.

[BibT_eX]

[DOI]

CoRR, 2021

2020

Learn Robust Features via Orthogonal Multi-Path.

[BibT_eX]

[DOI]

CoRR, 2020

Tao Li

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...