Zhenyi Wang

Associate Professor at the Southern University of Science and Technology

prof_pic.jpg

I’m Zhenyi Wang. I am currently an Associate Professor in the Department of Biomedical Engineering at the Southern University of Science and Technology (SUSTech). Before that, I was an Assistant Professor of Computer Science at the University of Central Florida (UCF), also a member of UCF’s Artificial Intelligence Institute. Previously, I was a Postdoctoral Associate at University of Maryland, College Park, working with Prof. Heng Huang. I received my PhD from Department of Computer Science and Engineering at University at Buffalo in 2023, working with Prof. Mingchen Gao.

Research Summary: My long-term research goal is to develop artificial general intelligence (AGI) that is data-efficient, capable of continual learning and trustworthy. Specifically, I have developed algorithms across the following research areas: (1) Biologically and Neuroscience-Inspired Continual Learning. (2) AI safety for responsible AGI, focusing on protecting model intellectual property and ensuring appropriate usage through applicability authorization mechanisms. (3) Data-efficient learning, including limited labeled data learning and data-free multi-task model merge.

Specifically:

  • Continual Learning: (1) Memorization and Generalization Trade-Off [ICML2022], (2) Generalized Distributionally Robust Memory Evolution [TPAMI2023], (3) Low-Rank Memory Parameterization [NeurIPS2023], (4) Beneficial Forgetting: A Biology-Inspired Approach to Continual Learning [ICLR2024], (5) Homeostatic Synaptic Scaling: Old Task and New Task Trade-Off [NeurIPS2024]
  • AI Safety and Trustworthy AI: Deep Model Intellectual Property Protection: (1) Model Extraction Aggregation [ICML2023], (2) Sparse Model Inversion [ICML2024], (3) Applicability/Usage Authorization [ICLR2024], (4) Efficient Model Extraction Defense [NeurIPS2023, ICML2024, ICLR2025]

  • Data-Efficient Learning:

    [1] Limited Labeled Data Learning: (1) Bayesian Meta Sampling for Few-Shot Learning Uncertainty Adaptation [ICLR2020], (2) Neural Tangent Kernel for Inner-Loop-Free Few-Shot Learning [ICLR2021], (3) Few-Shot Learning in Evolving Domains [ICCV2021, CVPR2022]

    [2] Model Merge and Reuse: (1) Adaptive Model Merging [ICLR2024], (2) Representation Surgery [ICML2024], (3) Model Grouping [ICML2024]

  • Large Language Models:: Multi-modality foundation model distillation [ICLR2025, NeurIPS2025, ICLR2026, ECCV2026, ICML2026]

Please refer to Google Scholar for more papers

I am looking for Postdocs/PhD/Master/Undergraduate/Research Assistant students with strong self-motivation. Please email me your CV and transcripts if you are interested. Email me: wangzhenyineu@gmail.com