Multi-task &
few-shot learning
Efficient learning across tasks through optimization, task balancing, and knowledge transfer.
Research Scientist · NTU, Singapore
Zhipeng Zhou 周志鹏
Ph.D. · University of Science and Technology of China
Learning under Conflicts.
Alibaba-NTU Global e-Sustainability CorpLab (ANGEL)
Nanyang Technological University
Email
Machine learning · Optimization · Mobile computing
01 / Profile
About me
I am a Research Scientist at Nanyang Technological University (NTU), working with Prof. Chunyan Miao.
I received my Ph.D. from the University of Science and Technology of China, advised by Prof. Wei Gong. Previously, I worked with Prof. Dong Yin during 2017–2020, and received my B.Eng. in Electronic and Information Engineering from Donghua University in 2017.
My research focuses on distribution shifts and efficient learning, with applications to large foundation models and mobile models.
02 / Research
Research interests
Multi-task &
Distribution shifts &
long-tailed recognition
Learning robust representations when data distributions and class frequencies are uneven.
Mobile computing &
intelligent sensing
Transfer and adaptation for WiFi-based human activity recognition and localization.
03 / Selected work
Selected publications
Delve into the Applicability of Advanced Optimizers for Multi-Task Learning
Continual Optimization with Symmetry Teleportation for Multi-Task Learning
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
Pareto Deep Long-Tailed Recognition: A Conflict-Averse Solution
04 / Recognition
Selected awards
DAAD AINeT Fellow, NeurIPS 2026 Top Reviewer
Outstanding Graduate of USTC, ICLR 2024 Financial Assistance Awardees
Student Travel Grant of IEEE INFOCOM 2022, Global Digital Technology Scholarship
Outstanding graduate of Shanghai, Tongqi Scholarship
National Scholarship, Donghua Scholarship
Sangma Scholarship, Donghua Scholarship