Qixun Wang (王启迅)
 |
Ph.D. Student |
About me
I'm an second-year Ph.D. student in the School of Intelligence Science and Technology, Peking University.
Research interests
- Mechanism and applications of large language models (LLMs) and multimodal LLMs.
Including in-context learning (ICL), hallucination, complex reasoning and test-time scaling techniques.
- Theory and algorithmic design of out-of-distribution (OOD) generalization.
Including generalization problems across various machine learning models and scenarios, like domain generalization (DG) in computer vision tasks, graph OOD generalization, and generalization of LLMs.
Educations
B.S in In Intelligence Science and Technology, School of EECS, Peking University (PKU)[2019.9 ~ 2023.6]
Ph.D. Candidate in Machine Learning and Computer Vision, School of Intelligence Science and Technology, Peking University (PKU) Advisors: Xianghua Ying , Yisen Wang[2023.9 ~ 2028.9 (expected)]
Publications
Can In-context Learning Really Generalize to Out-of-distribution Tasks?
Qixun Wang, Yifei Wang, Xianghua Ying, Yisen Wang
ICLR 2025
[paper] [code]2024
Dissecting the Failure of Invariant Learning on Graphs.
Qixun Wang, Yifei Wang, Yisen Wang, Xianghua Ying
NeurIPS 2024
[pdf] [code]2024
Improving Out-of-distribution Robustness by Adversarial Training with Structured Priors.
Qixun Wang* , Yifei Wang*, Hong Zhu, Yisen Wang
NeurIPS 2022 Spotlight, top 5%
[pdf] [code] [slide]2022
Experiences
- Reviewer of TMLR
- Reviewer of ICML 2025
- Reviewer of ICLR 2025
- Reviewer of NeurIPS 2024
- Teaching Assistant of the Computer Vision course of SIST, PKU, 2024 Spring.
Paper list & notes of LLM & VLM maintained by me [link]
Paper list & notes of OOD Generalization & some other topics maintained by me [link]
Selected Awards
- Outstanding graduate of Peking University (2023)
- Yanchuang Capital Scholarship (top 6%) (2022)
- Merit Student at PKU (top 6%) (2022)
- Academic Innovation Award at PKU (top 1%) (2022)
- Award for Academic Excellence at PKU (2021)