π¨βπ Biography
Hi! I am Shenghao Xie, a second-year Ph.D. student from Insight Lab, Academy for Advanced Interdisciplinary Studies, Peking University, working with Prof. Lei Ma and Prof. Tiejun Huang. I also study at TSAIL Group, Department of Computer Science and Technology, Tsinghua University, advised by Prof. Hang Su and Prof. Jun Zhu. Previously, I received my B.E. degree from School of Cyber Science and Engineering, Wuhan University in 2024, and spent a wonderful time at HMI Lab, School of Computer Science, Peking University, supervised by Prof. Shanghang Zhang.
My research interests are primarily on Generative Models and their applications on Embodied AI and AI for Science.
I am open to both collaborations and discussions, please feel free to reach me out.
π₯ News
- 2025.9: Β π Our work ShapeLLM-Omni is accepted by NeurIPS 2025 (Spotlight)!
- 2024.10: Β π Our work EPT is accepted by MIA 2024 (AIFM Special Issue)!
π Selected Publications
(* denotes co-first author. β denotes project leader. β¨ denotes corresponding author. View the full publication list on google scholar.)
Exploring Representation Invariance in Finetuning
Wenqiang Zu, Shenghao Xie*, Hao Chen, Zhiqiang Chen, Liwen Hu, Yuanhao Xi, Yiming Liang, Junliang Ye, Bo Lei, Tiejun Huang, Guoqi Li, Lei Ma
- Equip finetuning with both generalization and adaptation.
π Honors and Awards
- 2024.06 Outstanding Bachelorβs Degree Thesis, Wuhan University.
- 2023.11 Lei Jun Computer Science Undergraduate Scholarship, Wuhan University.
- 2023.08 First Prize, National College Student Information Security Contest.
π» Internships
- 2023.09 - 2024.09, research intern, Beijing Academy of Artificial Intelligence (BAAI), Beijing, China. Mentor: Lei Ma, Tiejun Huang.
π Services
- Reviewer: CVPR, AAAI,TMI.
- TA: 2025 Spring, Artificial Intelligence, instructed by Prof. Shanghang Zhang.