Haoyue BAI

I am a Ph.D. student at the Computer Sciences Department, University of Wisconsin-Madison, working with Prof. Robert Nowak. Prior to that, I obtained my bachelor's degree at Zhejiang University and my master's degree at The Hong Kong University of Science and Technology, supervised by Prof. S.-H. Gary Chan.

My research focuses on foundations and algorithms for trustworthy AI and developing reliable machine learning in the open-world:

  • Out-of-distribution (OOD) learning: enhancing model robustness and generalizability regarding distribution shifts and detecting OOD data, such as semantic/covariate shifts. Quantifying distribution shifts in the wild, including correlation/diversity shifts.

  • Machine learning techniques with provable guarantees to ensure reliable and well-understood deployment of AI systems.

  • Understanding and addressing safety issues in foundation models.

  • Data-efficient machine learning: selecting the most informative data for efficient learning with human feedbacks.

  • Junior PhD/master/undergraduate students: If you would like to chat about life, career plan, graduate school applications, or research ideas related to AI/ML, feel free to email me to schedule a meeting. I will dedicate 30 mins every week, especially for students from underrepresented groups or whoever is in need.

    Contact: haoyue.bai [at] wisc [dot] edu

    Google Scholar  /  Twitter  /  Linkedin

    profile photo
    Recent Updates

    * One first-authored journal paper OLHF accepted to TMLR 2025.

    * One first-authored paper on Black-box AI Generated Content Detection accepted to CVPR 2025.

    * One journal paper ALOE accepted to TMLR 2025.

    * One first-authored paper AHA accepted to NeurIPS 2024.

    * Received $5000 grant in API credits from OpenAI Researcher Access Program for supporting my research on trustworthy AI.

    * Thanks OpenAI Superalignment Fellowship (acceptance rate about Top 1%) for supporting my research on frontier topics of foundation models!

    * One (co)first-authored paper HYPO accepted to ICLR 2024.

    Selected Publications
    AHA: Adaptive Human-Assisted Out-of-Distribution Generalization and Detection
    Haoyue Bai, Jifan Zhang, Robert Nowak,
    Neural Information Processing Systems (NeurIPS), 2024
    paper / code

    Our approach strategically labels examples within a novel maximum disambiguation region, where the number of semantic and covariate OOD data roughly equalizes. By labeling within this region, we can maximally disambiguate the two types of OOD data, thereby maximizing the utility of the fixed labeling budget.

    Provable Out-of-Distribution Generalization in Hypersphere
    Haoyue Bai*, Yifei Ming*, Julian Katz-Samuels, Yixuan Li
    International Conference on Learning Representations (ICLR), 2024
    paper / code

    This paper provably learns domain-invariant representations in a hyperspherical space for OOD generalization.

    Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
    Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
    Selected into UW-Madison CS762. [link]
    International Conference on Machine Learning (ICML), 2023
    paper / code

    This paper bridges the gap between OOD generalization and OOD detection in one coherent framework.

    OoD-bench: Benchmarking and Understanding Out-of-Distribution Generalization Datasets and Algorithms
    Nanyang Ye, Kaican Li, Haoyue Bai, Runpeng Yu, Lanqing Hong, Fengwei Zhou, Zhenguo Li, Jun Zhu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    Selected as Oral Presentation [Top 4%].
    paper / code

    This benchmark may serve as a strong foothold that can be resorted to by future OoD generalization research.

    NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization
    Haoyue Bai, Fengwei Zhou, Lanqing Hong, Nanyang Ye, S.-H. Gary Chan, Zhenguo Li
    IEEE International Conference on Computer Vision (ICCV), 2021
    paper / code

    This work takes the first step to understand the OoD generalization of neural network architectures systematically.

    DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation
    Haoyue Bai*, Rui Sun*, Lanqing Hong, Fengwei Zhou, Nanyang Ye, Han-Jia Ye, S.-H. Gary Chan, Zhenguo Li
    The AAAI Conference on Artificial Intelligence (AAAI), 2021
    paper / code

    This work designs a general OoD generalization framework to tackle possible correlation shift and diversity shift in the real world.

    A Survey on Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal
    Haoyue Bai, Jiageng Mao, S.-H. Gary Chan
    Neurocomputing, 2022
    paper / code

    This paper provides an up-to-date review of recent crowd counting approaches, and educate new researchers in this field the design principles and trade-offs.

    Other Research Experience

    2024.5 -- 2024.8. NEC Laboratories America, Princeton.
    Research Scientist Intern.
    Advisor: Dr. Yiyou Sun.

    2022.9 -- 2023.12. University of Wisconsin-Madison, Madison.
    Research Assistant.
    Advisor: Prof. Sharon Yixuan Li.

    2021.6 -- 2021.9. The Chinese University of Hong Kong, Hong Kong.
    Research Assistant.
    Advisor: Prof. Bolei Zhou.

    2018.1 -- 2018.6. The Hong Kong University of Science and Technology, Hong Kong.
    Visiting Student.
    Advisor: Prof. Shueng-Han Gary Chan.

    2017.7 -- 2017.8. The Hong Kong University, Hong Kong.
    Summer Intern.
    Advisor: Prof. Lucas C.K. Hui.

    Honors and Awards

    2024 OpenAI Superalignment Fellowship (Acceptance rate about Top 1%)
    Research Travel Grant, The Hong Kong University of Science and Technology
    Outstanding Graduates, Zhejiang University
    Alibaba-Zhejiang News Scholarship
    First-Class Academic Scholarship, Zhejiang University (Top 3%)
    First-Class Scholarship for Outstanding Students, Zhejiang University (Top 3%)
    Outstanding Student Leader Awards, Zhejiang University (Top 6%)

    Review Experience

    Conference Reviewer
    Internation Conference on Machine Learning (ICML) 2023, 2024, 2025.
    International Conference on Learning Representations (ICLR) 2023, 2024.
    Conference on Neural Information Processing Systems (NeurIPS) 2023, 2024.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022, 2023, 2024.
    European Conference on Computer Vision (ECCV) 2022, 2024.
    International Conference on Computer Vision (ICCV) 2023.
    AAAI Conference on Artificial Intelligence (AAAI) 2022.

    Journal Reviewer
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2024.
    IEEE Transactions on Image Processing (TIP) 2024.
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2024.
    IEEE Transactions on Cybernetics.

    Teaching Assistant

    University of Wisconsin–Madison
    COMP CS400: Data Science Programming III (Spring 2024)

    University of Wisconsin–Madison
    COMP CS220: Data Science Programming I (Fall 2022)

    The Hong Kong University of Science and Technology
    COMP2611: Computer Organization (Fall 2019, Spring 2019)


    Thanks to Jon Barron for website template.