Haodong Lu
University of New South Wales
I am Haodong Lu, currently in my third year as a PhD student at the University of New South Wales, Australia, under the supervision of Dr. Dong Gong and Prof. Lina Yao, and work closely with CSIRO's Data61 as a scholarship recipient. I am also a recipient of the 2024 Google PhD Fellowship. Before that, I completed both my Honours and BSc. degrees at the University of New South Wales.
My earlier work focused on Out-of-Distribution Detection and Continual Learning in Computer Vision and Multi-Modal foundation models. More recently, I have shifted toward advancing Large Language Models, particularly in the areas of pre-training, post-training, and test-time scaling. I aim to build reliable, efficient, and scalable foundation models for real-world applications.
Selected Publications
-
PreprintAdaptive Rank, Reduced Forgetting: Knowledge Retention in Continual Learning Vision-Language Models with Dynamic Rank-Selective LoRAPreprint. Under ReviewICLRLearning with Mixture of Prototypes for Out-of-Distribution DetectionIn the 12th International Conference on Learning Representations (ICLR), 2024.CVPRSelf-Expansion of Pre-trained Models with Mixture of Adapters for Continual LearningComputer Vision and Pattern Recognition Conference (CVPR), 2025PreprintIncremental Multi-modal Prompt Tuning with Textual Prototypes for Continual LearningPreprint. Under Review.WWWBalancing Plasticity and Stability via Dual-Branch Learning in Online Continual LearningThe ACM Web Conference (WWW) - short paper track, 2025
Awards
- Google PhD Fellowship, Machine Intelligence Track, Google, 2024
- Outstanding Reviewer, ACM Multimedia, 2024
- Data61 PhD Scholarship coupled with a Top-up Scholarship, CSIRO’s Data61, 2022
- Dean’s Honours List, University of New South Wales, 2020
Services
I have served as a reviewer for the following conferences and journals:
- Conferences: ICML, ICCV, NeurIPS, ICLR, ACMMM, CVPR
- Journals: IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)