M.Sc. in Artificial Intelligence · Institute of Science Tokyo
2025–present (expected 2027) Research focus: mechanistic interpretability of large language models, linguistic generalization, syntactic structure, and internal representations.
Curriculum Vitae
Research focus: mechanistic interpretability of large language models, linguistic generalization, syntactic structure, and internal representations.
Major in Computational Linguistics, minor in Comparative Linguistics.
Thesis: Two Heads or One? Mechanisms Driving Performance in Multi-Agent LLM Reasoning
Under review (ARR 2026 / EMNLP 2026) · Under review
言語処理学会 (NLP) 2026, poster
ML / Interpretability
NLP / Speech
General
English · French · German · Japanese (JLPT N1 — summer 2026)
Plus a bit of Spanish, Mandarin, Korean, Kinyarwanda.