Oizmi Lab, Graduate School of Arts and Sciences, the University of Tokyo, M2
AMI AC SHARKS, 800m runner
Takahashi, S*., Sasaki, M*., Takeda, K. & Oizumi, M. Investigating fine- and coarse-grained structural correspondences between deep neural networks and human object image similarity judgments using unsupervised alignment. arXiv [cs.CV] (2025). (*equal contribution) [link]
Takahashi, S*., Sasaki, M*., Takeda, K. & Oizumi, M. Self-supervised learning facilitates neural representation structures that can be unsupervisedly aligned to human behaviors. in ICLR 2024 Workshop on Representational Alignment (2024). (*equal contribution) [link]
E-mail: soht121[at]g.ecc.u-tokyo.ac.jp