About me

I am a MEXT-funded Ph.D. candidate at The University of Tokyo, working with Toshihiko Yamasaki. At the moment, I am interning as a Research Scientist at Sakana AI. Prior to my Ph.D. study, I received my Master’s degree from Peking University in 2021. Throughout my academic journey, I was also fortunate to have two wonderful internships at Adobe and SenseTime.

My research focuses on self-improving machine learning, primarily for vision data. I approach this challenge through two key aspects: learning algorithms and model design.

• On the algorithmic front, I develop methods to uncover and leverage the hidden self-supervision inherent within data, e.g., SAT, LEWEL, and SimMatch.
• On the model front, I design ‘fast learners’, foundational models that operate efficiently concerning both human- and self-supervisions, e.g., ISA, OCNet, and GreenMIM.

News

• 2025/01: I started an internship at Sakana AI, Tokyo.
• 2024/08: I gave an invited talk at MIRU 2024.
• 2024/07: One paper was accpted by ECCV 2024.
• 2023/07: One paper SimMatchv2 was accepted by ICCV 2023.
• 2023/05: I started an internship at Adobe, San Jose.
• 2023/03: Gave a talk on SAT (slides) at Waves in AI seminar.
• 2022/10: One paper (SAT) was accepted at T-PAMI.
• 2022/09: One paper (GreenMIM) was accepted at NeurIPS 2022.
• 2022/03: Two papers (LEWEL and SimMatch) were accepted at CVPR 2022.