avatar

Yunbei Zhang

Ph.D. Student
yunbeizhang.ml[at]gmail.com


About Me

Hi, I’m Yunbei Zhang (张云贝), a Ph.D. student in Computer Science at Tulane University, advised by Prof. Jihun Hamm. My current research is focused on Trustworthy ML, Test/Inference-time Learning, and Efficient Model Reprogramming.

Prior to my doctoral studies, I graduated with a B.S. in Mathematics from Osaka University, where I was advised by Prof. Masaaki Wada and Prof. Seidai Yasuda. My undergraduate education also includes two years at Peking University; in 2015, I made a deliberate choice to withdraw and forge my own path, a decision that ultimately led me to where I am today.

News

Publications (* indicates equal contribution)

  1. ICML'25
    DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
    Yunbei Zhang, Akshay Mehra, Shuaicheng Niu, Jihun Hamm
    International Conference on Machine Learning (ICML), 2025.
    PDF Code

  2. ACM MM'25
    eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases
    Janet Wang, Xin Hu, Yunbei Zhang*, Diabate Almamy, Vagamon Bamba, Konan Amos Sébastien Koffi, Yao Koffi Aubin, Zhengming Ding, Jihun Hamm, Rie R. Yotsu
    33rd ACM International Conference on Multimedia (ACM MM), 2025.

  3. ACM MM'25
    Visual Instance-aware Prompt Tuning
    Xi Xiao*, Yunbei Zhang*, Xingjian Li, Tianyang Wang, Xiao Wang, Yuxiang Wei, Jihun Hamm, Min Xu
    33rd ACM International Conference on Multimedia (ACM MM), 2025.
    PDF

  4. USENIX'25
    SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation
    Yunsung Cheung, Yunbei Zhang, Nassir Marrouche, Jihun Hamm
    USENIX Security Symposium (USENIX), 2025.
    PDF

  5. ICMLW'25
    Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback
    Janet Wang*, Yunbei Zhang*, Zhengming Ding, Jihun Hamm
    2nd Workshop on Models of Human Feedback for AI Alignment at ICML 2025. [Oral]
    PDF Code

  6. ICMLW'25
    Describe Anything in Medical Images
    Xi Xiao*, Yunbei Zhang*, Thanh-Huy Nguyen*, Ba-Thinh Lam, Janet Wang, Jihun Hamm et al.
    ICML 2025 Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences, 2025.
    PDF

  7. WACV'25
    OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation
    Yunbei Zhang, Akshay Mehra, Jihun Hamm
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025. [Oral]
    PDF Code

  8. NeurIPS'24
    Understanding the Transferability of Representations via Task-Relatedness
    Akshay Mehra, Yunbei Zhang, Jihun Hamm
    Neural Information Processing Systems (NeurIPS), 2024.
    PDF Code

  9. CVPRW'24
    Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport
    Akshay Mehra, Yunbei Zhang, Jihun Hamm
    2024 IEEE CVPR Workshop on Fair, Data-efficient, and Trusted Computer Vision.
    PDF Code

  10. CVPRW'24
    Achieving Reliable and Fair Skin Lesion Diagnosis via Unsupervised Domain Adaptation
    Janet Wang, Yunbei Zhang, Zhengming Ding, Jihun Hamm
    2024 IEEE CVPR Workshop on Domain adaptation, Explainability, Fairness in AI for Medical Image Analysis.
    PDF

  11. WACV'24
    On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization
    Akshay Mehra, Yunbei Zhang, Bhavya Kailkhura, Jihun Hamm
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.
    PDF Code

Honors and Awards

Services