About me

I am an Assistant Professor and Principal Investigator at the National Institute of Informatics, jointly affiliated with SOKENDAI. I also work part-time as a Research Scientist at Sakana AI. I received my Ph.D. from Yamasaki Lab at The University of Tokyo in 2025 and my M.S. from Peking University, and I have interned at Sakana AI, Adobe, and SenseTime. My research targets self-improving machine learning, with a focus on generative models for vision and language. I currently approach this through three complementary fronts:

• Model / Architecture front: I design efficient foundation model for vision and language tasks, including generative autoregressive and diffusion transformers, and novel architectures that better exploit structure in data and computation.
• Algorithm / Data-efficiency front: I develop data-efficient learning algorithms that uncover and leverage hidden self-supervision in visual and multi-modal data, including semi-/self-/weakly supervised methods and robust training under limited or noisy labels.
• Weight Space Learning front: I study neural networks in weight space, including model merging, composition, and generation. The goal is to understand and exploit the structure and knowledge of model weights for instant adaptations and model recycle.

Opportunity

I offer funded positions for interns, PhD students, and postdocs; if interested, email your CV, a brief research background, and the topics you would like to pursue in my group to me.

1. Intern students through the NII International Internship Program with >100 universities;
2. Ph.D. students through the Informatics Program at SOKENDAI / NII;
3. Ph.D./Postdoc via DAAD IFI for students at German universities and German nationals.
4. Research Assistants from universities in Japan at NII.

News

• 2025/11: I will be serving as an Area Chair at ICML 2026.
• 2025/04: I’ve joined NII and SOKENDAI as an Assistant Professor & Principal Investigator.
• 2025/03: Graduated from The University of Tokyo.
• 2025/01: I started an internship at Sakana AI as a Research Scientist, Tokyo.
• 2024/08: I gave an invited talk at MIRU 2024.
• 2024/07: One paper (SCOMatch) was accpted by ECCV 2024.
• 2023/07: One paper SimMatchv2 was accepted by ICCV 2023.
• 2023/05: I started an internship at Adobe as a Research Scientist, 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.