Scholar
Fei Zhu
Google Scholar ID: fjZ1CBwAAAAJ
Institute of Automation, CAS; Hong Kong Institute of Science & Innovation, CAS
Citations & Impact
Citations
1,676
H-index
17
i10-index
22
Publications
20
Co-authors
20
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Invited Talks:
- - Unknown Rejection in Open Environment, Biomedical Engineering Distinguished Lecture Series, Southern University of Science and Technology, August, 2024
- - Deep Continual Learning, School of Computer Science and Engineering, Nanjing University of Science and Technology, January, 2025
- - Open-Environment Continual Learning, Zhongguancun Research Institute of Artificial Intelligence, Beijing, February, 2025
- - Continual Learning in Multimodal Large Language Model, VALSE 2025 Continual Learning Forum, Zhuhai, June, 2025
- - Continual Learning: Theory, Methods and Applications, 2025 Chinese Society of Image and Graphics Young Scientist Conference, Qingdao, September, 2025
- - Recent Advance of Continual Learning, Shenzhen Graduate School of Peking University, October, 2025
- Selected Publications:
- - [NeurIPS 2025 Spotlight Paper] RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
- - [NeurIPS 2025] C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
- - [TPAMI 2025] PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning
- - [TPAMI 2024] Revisiting Confidence Estimation: Towards Reliable Failure Prediction
- - [TPAMI 2023] Learning by Seeing More Classes
- - [Neural Networks 2023] Imitating the Oracle: Towards Calibrated Model for Class Incremental Learning
- - [CVPR 2024] RCL: Reliable Continual Learning for Unified Failure Detection
- - [CVPR 2023 Highlight Paper (Top 2.5%)] OpenMix: Exploring Outlier Samples for Misclassification Detection
- - [ECCV 2022] Rethinking Confidence Calibration for Failure Prediction
- - [CVPR 2021 Oral Paper (Top 4%)] Prototype Augmentation and Self-Supervision for Incremental Learning
- - [NeurIPS 2021] Class-Incremental Learning via Dual Augmentation
- - [IEEE/CAA JAS 2023 Invited Reviews] Class Incremental Learning: A Review and Performance Evaluation (In Chinese)
Research Experience
- Currently an Assistant Professor at the Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, working with Prof. Zhaoxiang Zhang and Prof. Gaofeng Meng.
Education
- Ph.D. in Pattern Recognition and Intelligent Systems from the Institute of Automation, Chinese Academy of Sciences, advised by Prof. Cheng-Lin Liu and Prof. Xu-Yao Zhang; B.E. degree from Tsinghua University.
Background
- Research Interests: Theoretical and applied aspects of dynamic learning, especially for foundation models such as MLLMs and LLMs; keen on utilizing these models to facilitate applications in biomedicine and embodied robotics. Related ML topics: continual pre-training, continual post-training, reinforcement fine-tuning, AI alignment. Focused applications: biomedicine and healthcare, robot learning and embodied AI.
Miscellany
- Contact: Email zhfei2018@gmail.com, WeChat 17888841931
