About Me

I am a PhD student in VITA group at the University of Texas at Austin advised by Prof. Zhangyang Wang. My research focuses on machine learning and computer vision, especially improving the generalization ability of deep neural networks in complex and unpredictable real-world environments. I also have experience in other fields including image segmentation, model compression, federated learning, machine learning privacy, and style transfer.

Education

Ph.D. in Electrical and Computer Engineering
University of Texas at Austin
08/2018-Present
B.S. in Electronic Engineering
Tsinghua University
08/2014-06/2018

Professional Experience

Applied Scientist Intern
Amazon.com Services Inc. (AWS AI)
Advisor: Dr. Aston Zhang, Dr. Mu Li, Dr. Alex Smola
06/2022- · Santa Clara
Applied Scientist Intern
Amazon.com Services Inc. (AWS AI)
Advisor: Dr. Aston Zhang, Dr. Mu Li, Dr. Alex Smola
05/2021-02/2022 · East Palo Alto
Research Intern
NVIDIA Corporation (AI Platform)
Advisor: Dr. Zhiding Yu, Dr. Anima Anandkumar
05/2020-08/2020 · Santa Clara
Research Intern
Kwai Inc. (Ytech AI Lab)
Advisor: Dr. Ji Liu
05/2019-08/2019 · Seattle

Selected Publications

Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, and Zhangyang Wang. “Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork.”
In Advances in Neural Information Processing Systems (NeurIPS), 2022.
[pdf] [code]
Haotao Wang, Aston Zhang, Yi Zhu, Shuai Zheng, Mu Li, Alex Smola, and Zhangyang Wang. “Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition.”
In International Conference on Machine Learning (ICML), 2022. Long presentation
[pdf] [code]
Haotao Wang, Aston Zhang, Shuai Zheng, Xingjian Shi, Mu Li, and Zhangyang Wang. “Removing Batch Normalization Boosts Adversarial Training.”
In International Conference on Machine Learning (ICML), 2022.
[pdf] [code]
Junyuan Hong, Haotao Wang, Zhangyang Wang, and Jiayu Zhou. “Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization.”
In International Conference on Learning Representations (ICLR), 2022.
[pdf] [code]
Haotao Wang, Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Animashree Anandkumar, and Zhangyang Wang. “AugMax: Adversarial Composition of RandomAugmentations for Robust Training.”
In Advances in Neural Information Processing Systems (NeurIPS), 2021.
[pdf] [code]
Haotao Wang*, Tianlong Chen*, Shupeng Gui, Ting-Kuei Hu, Ji Liu, and Zhangyang Wang. “Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free.”
In Advances in Neural Information Processing Systems (NeurIPS), 2020.
[pdf] [code] *Equal contributions.
Zhenyu Wu*, Haotao Wang*, Zhaowen Wang, Hailin Jin, and Zhangyang Wang. “Privacy-Preserving Deep Visual Recognition: An Adversarial Learning Framework and A New Dataset.”
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020.
[pdf] [project homepage] [code and dataset] *Equal contributions.
Haotao Wang, Shupeng Gui, Haichuan Yang, Ji Liu, and Zhangyang Wang. “GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework.”
In European Conference on Computer Vision (ECCV), 2020. Spotlight Oral
[pdf] [code]
Haotao Wang, Tianlong Chen, Zhangyang Wang, and Kede Ma. “I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively.”
In International Conference on Learning Representations (ICLR), 2020.
[pdf] [code]
Shupeng Gui*, Haotao Wang*, Haichuan Yang, Chen Yu, Zhangyang Wang, and Ji Liu. “Model Compression with Adversarial Robustness: A Unified Optimization Framework.”
In Advances in Neural Information Processing Systems (NeurIPS), 2019.
[pdf] [code] *Equal contributions.
Sina Mohseni, Haotao Wang, Zhiding Yu, Chaowei Xiao, Zhangyang Wang, and Jay Yadawa. “Practical Machine Learning Safety: A Survey and Primer.”
ACM Computing Surveys, 2022.
[pdf]
Junyuan Hong, Haotao Wang, Zhangyang Wang, and Jiayu Zhou. “Federated robustness propagation: Sharing adversarial robustness in federated learning.”
Preprint.
[pdf]