About Me

I'm a third-year Ph.D. student in the School of Intelligence Science and Technology at Peking University. My research interests include:

• Mechanism and applications of (multimodal) LLMs, including in-context learning (ICL), reasoning, and perception of multimodal LLMs.
• Out-of-distribution (OOD) generalization, including theoretical analysis and algorithm design across various models and scenarios, such as classical computer vision tasks, graph data, and the generalization behavior of LLMs.

🔥News

• 2025.11 Monet released on arXiv (Reasoning in latent visual space).
• 2025.02 One paper accepted to CVPR 2025 (Audio-Visual Instance Segmentation).
• 2025.01 One paper accepted to ICLR 2025 (Analysis of in-context learning on OOD tasks).

🎓Education

• B.S. in Intelligence Science and Technology, EECS
Peking University2019~2023
• Ph.D. Candidate in ML & Computer Vision, SIST
Peking University2023~present

Main Publications

1. Monet: Reasoning in Latent Visual Space Beyond Images and Language
   Qixun Wang, Yang shi, Yifei Wang, Yuanxing Zhang, Pengfei Wan, Kun Gai, Xianghua Ying, Yisen Wang
   Arxiv preprint 2025
   papercode
2. Can In-context Learning Really Generalize to Out-of-distribution Tasks?
   Qixun Wang, Yifei Wang, Xianghua Ying, Yisen Wang
   ICLR 2025 2025
   papercode
3. Dissecting the Failure of Invariant Learning on Graphs
   Qixun Wang, Yifei Wang, Yisen Wang, Xianghua Ying
   NeurIPS 2024 2024
   papercode
4. Improving Out-of-distribution Robustness by Adversarial Training with Structured Priors
   Qixun Wang*, Yifei Wang*, Hong Zhu, Yisen Wang
   NeurIPS 2022 (Spotlight) 2022
   papercode

💼Experience

• Reviewer: ICML, ICLR, NeurIPS, AAAI, TMLR
• TA: Computer Vision (SIST, PKU), Spring 2024

🏆Awards

• The Third-Class Scholarship of Peking University (2025)
• Merit Student at Peking University (2025)
• Outstanding Graduate of Peking University (2023)
• Yanchuang Capital Scholarship (Top 6%) (2022)
• Merit Student at Peking University (Top 6%) (2022)
• Academic Innovation Award at Peking University (Top 1%) (2022)
• Award for Academic Excellence (2021)