Group Leader, Physics of Intelligence Program at Harvard University

Hidenori Tanaka received his bachelor's degree in physics from Kyoto University, Japan. He then received his Ph.D. in theoretical condensed matter physics from Harvard University, where he was advised by David Nelson and Michael Brenner. He then switched to theoretical neuroscience and machine learning with Surya Ganguli and Daniel Fisher at Stanford. He is currently a Group Leader at the NTT Physics & Informatics Lab, where he physically leads the Intelligent Systems Group at Harvard's Center for Brain Science through an industry-academic collaboration.
- Emergent capabilities in AI models: mechanisms underlying in-context learning and its limitations.
- Theory of human-AI communication: mathematical frameworks for relationships between humans and AI, inspired by psychiatry and psychology.
- Physics of networks of minds: explore how different designs of AI systems will affect collective “phases” in human-AI societies by generalizing opinion dynamics models.
- Strong foundation in mathematics and machine learning.
- Proficiency in programming.
- Ability to engage with interdisciplinary ideas from physics, neuroscience, and psychology.
- Interest in theoretical questions on AI alignment and human-AI interaction.
- Prior research experience is highly desirable.