Research program
“Nothing in life is to be feared, it is only to be understood. Now is the time to understand more, so that we may fear less.”
— Marie Curie
What could alignment mean in an ecology of natural and artificial minds? We approach this question by studying emergent phenomena across networks of networks: from neurons to minds, and from minds to societies, using AI as an empirical ground to fundamentally rethink the nature of intelligence itself.
Social Dynamics of Agents
Education, Mental Health, and Alignment
Selected Works
All publicationsDynamics of Concept Learning and Compositional Generalization
Yongyi Yang, Core Francisco Park, Ekdeep Singh Lubana, Maya Okawa, Wei Hu, Hidenori Tanaka
ICLR 2025
A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
Ekdeep Singh Lubana, Kyogo Kawaguchi, Robert P. Dick, Hidenori Tanaka
ICLR 2025
Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
Maya Okawa, Ekdeep Singh Lubana, R.P. Dick, Hidenori Tanaka
NeurIPS 2023
From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction
Hidenori Tanaka, A. Nayebi, N. Maheswaranathan, L. McIntosh, S.A. Baccus, Surya Ganguli
arXiv · 2019
News
All newsFebruary 2026
Joining CBAI as a mentor
Hidenori Tanaka joined the Cambridge Boston Alignment Initiative Summer Research Fellowship in AI Safety as a mentor.
October 2025
Harvard's Dr. Mai Uchida joins the Physics of AI Group
NTT Research announced that Dr. Mai Uchida will collaborate with the Physics of AI Group on psychiatry, mental health, and safe human-AI systems.
April 2025
Five group works accepted at ICLR 2025
Including studies on competition dynamics in in-context learning, percolation models of emergence, and concept learning dynamics.
November 2024
Joining MATS as a mentor
Hidenori Tanaka joined the ML Alignment & Theory Scholars (MATS) program as a mentor.