- Handling New Class in Online Label Shift. (TKDE 2025)
- TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree. (ICML 2025)
- Adapting to Generalized Online Label Shift by Invariant Representation Learning. (KDD 2025)
- Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation. (ICML 2024)
- Learning with Asynchronous Labels. (TKDD 2024)
- Handling New Class in Online Label Shift. (ICDM 2023)
- Adaptive Learning for Weakly Labeled Streams.
Research Experience
Currently a Ph.D. student at the LAMDA Group, Nanjing University, under the guidance of Prof. Zhi-Hua Zhou and Prof. Yuan Jiang.
Education
- Sep 2016 - Jun 2020: Received B.Sc. degree from the School of Information and Communication Engineering, University of Electronic Science and Technology of China.
- Sep 2020: Admitted to study for an M.Sc. degree at Nanjing University without entrance examination, under the guidance of Professor Zhi-Hua Zhou.
- Sep 2023 - Now: Currently a Ph.D. student at the School of Artificial Intelligence, Nanjing University, and a member of the LAMDA Group, advised by Prof. Zhi-Hua Zhou and Prof. Yuan Jiang.
Background
Research interests include Machine Learning and Data Mining. Most recently, interested in: Efficient Machine Learning in Non-stationary and Open World Environments; Efficient Post-training for LLMs, including efficient Continual Fine-tuning and RLHF; Efficient LLM Inference and Reasoning.