Molecular Foundation Models
Foundation models that learn universal representations from large-scale molecular data.
Specially Appointed Assistant Professor
Nara Institute of Science and Technology (NAIST) ARWIT Promotion Center (cross-appointed with Data-driven Science Creative Center)
Member of the Chemoinformatics Laboratory
Specialty: Cheminformatics
I develop data-driven methods and foundation models to accelerate molecular discovery and design.
Foundation models that learn universal representations from large-scale molecular data.
Language models over chemical strings (e.g., SMILES) for molecular generation and prediction.
Molecular design and optimization combining experimental data with machine learning.