I am currently a Ph.D. candidate at the City University of Hong Kong (CityUHK) and advised by Professors Yu Zhang (张宇), Ying Wei (魏颖), and Kede Ma (马柯德). Prior to this, I obtained a Bachelor’s degree in Computer Science and Technology from SUSTech in 2022, under the supervision of Professor Xuan Song (宋轩). My research mainly focuses on improving the efficiency and adaptability of large-scale AI models, particularly in LLMs (PEFT,RLVR,KVCache), deep generative models, transfer learning (continual learning, meta-learning, and domain adaptation), and AI for science.
Contact me: 12250063 [at] mail.sustech.edu.cn
Google Scholar / OpenReview / ORCID / Github
🆕 News
- [Sept. 2025] One papers got accepted by NeurIPS 2025.
- [Jun. 2025] One papers got accepted by ICCV 2025.
- [May 2025] Two papers got accepted by ICML 2025.
- [Jan. 2025] Two papers got accepted by ICLR 2025, one as an oral presentation (top 1.8%).
- [Dec. 2024] One paper got accepted by AAAI 2025 for oral presentation (top 3.7%).
- [Sept. 2024] One paper got accepted by NeurIPS 2024.
- [Jan. 2024] One paper got accepted by ICLR 2024 for spotlight presentation.
📕 Selected Publications
Explore the full list of publications here.
-
Zhan Zhuang, Xiequn Wang, Wei Li, Yulong Zhang, Qiushi Huang, Shuhao Chen, Xuehao Wang, Yanbin Wei, Yuhe Nie, Kede Ma, Yu Zhang, Ying Wei. Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation. In: Proceedings of the Forty-Second International Conference on Machine Learning (ICML), Vancouver, Canada, 2025.
-
Zhan Zhuang, Yu Zhang, and Ying Wei. Gradual Domain Adaptation via Gradient Flow. In: Proceedings of the Twelfth International Conference on Learning Representations (ICLR), Vienna, Austria, 2024. (Spotlight)
-
Zhan Zhuang, Yulong Zhang, Xuehao Wang, Jiangang Lu, Ying Wei, Yu Zhang. Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models. In: Proceedings of the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024.