Under Review
- Wu, H., Wang, Wei., Malepathirana, T., Seneviratne, S., Oetomo, D., Halgamuge, S. TT-MPD: Test Time Model Pruning and Distillation.
- Wu, H., Zhuang, B. LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation.
- Wu, H., Wang, Wei., Malepathirana, S., Oetomo, D., Halgamuge, S. Neural Growth Policy Design: The Regularization Effect Perspective.
Conference papers
- Wu, H., Wang, W., Malepathirana, T., Senanayake, D., Oetomo, D., Halgamuge, S. (2024). When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks. In Proceedings of the Thirty-Eight AAAI Conference on Artificial Intelligence (AAAI-24). AAAI. [PDF]
- Wu, H., Zhuang, B. (2024). Fast and Accurate Continual Test Time Domain Adaptation. In ACM MM Workshop on Continual Learning 2024. [PDF]
