Hoang Van Pham

VinUniversity, Vietnam.

prof_pic.jpg

Hi! I’m Hoang. I’m currently a Research Assistant at VinUniversity working with Prof. Khoa D Doan. Prior to that, I was an AI resident at FPT Software AI Center where I was advised by Prof. Long Tran-Thanh, Prof. Dung Le Duy, and Dr. Anh Ta-The. Previously, I was a member of Data Science Lab in Hanoi University of Science and Technology where I earned my Engineering Degree in Computer Science.

Research: My research interests include but are not limited to:

  • Trustworthy AI: I focus on investigating the robustness of models against backdoor attacks. Besides, I am interested in watermarking models or generated data.
  • Efficient Deep Learning: I am interested in improving model training/deployment through efficient transfer learning, reducing model size, and utilizing synthetic datasets.

news

Aug 12, 2024 A paper on Resilient Backdoor Attack is accepted at ECCV 2024 (Oral presentation)
Sep 23, 2023 A paper on Understanding Pruning at Initialization is accepted as poster at NeurIPS 2023
Oct 21, 2022 I am doing visiting research at University of Warwick

selected publications

  1. Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?
    Hoang Pham, The-Anh Ta, Shiwei Liu, and 4 more authors
    In Advances in Neural Information Processing Systems 2023
  2. Adaptive infinite dropout for noisy and sparse data streams
    Ha Nguyen*, Hoang Pham*, Son Nguyen, and 2 more authors
    Machine Learning 2022
  3. Pruning Deep Equilibrium Models
    Hoang Pham*, Tuc Nguyen*, Anh Ta-The, and 2 more authors
    ICML 2022 Workshop on Sparse Neural Networks 2022
  4. Auxiliary local variables for improving regularization/prior approach in continual learning
    Linh Ngo Van*, Nam Le Hai*, Hoang Pham*, and 1 more author
    In Pacific-Asia Conference on Knowledge Discovery and Data Mining 2022