Hoang Van Pham
Hi! I’m Hoang. I’m a first year CS PhD student at the University of Warwick where I was fortunately supervised by Prof. Long Tran-Thanh. Before that, I spent 6 months as 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 neural network pruning/compressing 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
- Flatness-aware Sequential Learning Generates Resilient BackdoorsIn Proceedings of the European Conference on Computer Vision (ECCV) Sep 2024
- Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?In Advances in Neural Information Processing Systems Sep 2023
- Adaptive infinite dropout for noisy and sparse data streamsMachine Learning Sep 2022
- Pruning Deep Equilibrium ModelsICML 2022 Workshop on Sparse Neural Networks Sep 2022
- Auxiliary local variables for improving regularization/prior approach in continual learningIn Pacific-Asia Conference on Knowledge Discovery and Data Mining Sep 2022