I am an incoming Assistant Professor in the School of Computer Science at the University of Bristol, starting in January 2026. I am also a visiting scientist at the RIKEN Center for Advanced Intelligence Project (RIKEN-AIP) and a member of the European Laboratory for Learning and Intelligent Systems (ELLIS).

My research focuses on trustworthy machine learning, including the design, analysis, and evaluation of reliable learning algorithms under various data corruptions, across diverse data modalities, and under real-world constraints. I work on both the theoretical foundations of machine learning and its applications in core AI areas such as computer vision and reinforcement learning, as well as real-world problems in healthcare.

Research Interests

• Weakly Supervised Learning: Advancing learning paradigms that enable models to perform reliably under imperfect supervision, including but not limited to corrupted labels, distribution shifts, and selection bias.
• Representation Learning: Developing principled approaches for learning robust, interpretable and transferable representations that effectively fuse information from diverse data modalities.
• Machine Learning for Social Good: Designing responsible models and algorithms that remain effective while supporting fairness, privacy, and broader societal benefit.

Previously, I was a postdoctoral fellow in the Foundations of Machine Learning Systems Group at the University of Tübingen, Germany, working with Prof. Robert Williamson. I received my Ph.D. in Machine Learning from the University of Tokyo, Japan, under the supervision of Prof. Masashi Sugiyama.

News

• [Dec 2025] I will visit HKUST (GZ) and Wuhan University to give invited talks.
• [Dec. 2025] I will serve as an Area Chair of ICML 2026.

Contact

Merchant Venturers Building (MVB)
Woodland Road
Bristol, BS8 1UB
United Kingdom