Long-Kai Huang is an Assistant Professor in the Department of Computer Science at HKBU. Before joining HKBU, he was a Senior Researcher at the Machine Learning Center of Tencent AI Lab and at Tencent AI for Life Science Lab. He received his Ph.D. in Computer Science and Engineering from NTU, Singapore, and his B.Eng. in Automation from Sun Yat-Sen University in Guangzhou.
His research lies at the intersection of machine learning theory and applications. He is particularly interested in understanding how modern AI models learn, store, and transfer knowledge, and in using these insights to develop more effective and efficient learning algorithms. His work focuses on continual learning, meta-learning, and efficient training and inference for large foundation models. He is also interested in applying AI to scientific discovery, especially in life science domains such as single-cell omics, protein design, and drug discovery.
He has published more than 35 papers in top venues, including ICLR, ICML, NeurIPS, TKDE, Nature-branded journals, and Cell. He received the ICLR 2024 Best Paper Award Honorable Mention. He has also served as Area Chair for ICLR, ICML, and NeurIPS.
For prospective Ph.D. students and RAs: If you are interested in joining Long-Kai's Research Group, please fill out this application form.
- Efficient Training and Inference of Transformer Models
- AI for Scientific discovery (single-cell omics, protein design, and drug discovery)
- Continual Learning, Meta-Learning and Transfer Learning
- Learning Mechanisms
- B He*, C Qin*, Y Zhao*, LK Huang*, Z Wu, F Wang, F Wu, F Yang, J Yao. "Functional Protein Design and Enhancement with Ontology Reinforcement Iteration". In Nature Communications. 2026
- LK Huang†, R Zhu, B He, J Yao. “Steering Protein Language Models.” In ICML, 2025
- Z Mo, LK Huang, SJ Pan. “Parameter and Memory Efficient Pretraining via Low-rank Riemannian Optimization.” In ICLR, 2025
- Y Wu*, H Wang*, P Zhao, Y Zheng, Y Wei, LK Huang†. “Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization.” In ICML, 2024
- Y Wu, LK Huang†, R Wang, D Meng, Y Wei. “Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction.” In ICLR, 2024.
- LK Huang, J Huang, Y Rong, Q Yang, Y Wei. “Frustratingly Easy Transferability Estimation.” In ICML, 2022
- H Yao*, LK Huang*, L Zhang, Y Wei, L Tian, J Zou, J Huang. “Improving Generalization in Meta-learning via Task Augmentation.” In ICML, 2021
- LK Huang and SJ Pan. “Communication-Efficient Distributed PCA by Riemannian Optimization.” In ICML, 2020
HKBU Scholars
