Scholar
Mitsuhiko Nakamoto
Google Scholar ID: wIDVzroAAAAJ
UC Berkeley
Citations & Impact
Citations
675
H-index
10
i10-index
10
Publications
13
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- Papers published: 'Steering Your Diffusion Policy with Latent Space Reinforcement Learning' (CoRL 2025, oral presentation); 'Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance' (CoRL 2024); 'SuSIE: Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models' (ICLR 2024); 'Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning' (NeurIPS 2023).
Research Experience
- Currently a third-year CS Ph.D. student at the BAIR Lab, UC Berkeley; spent a summer in Professor Yutaka Matsuo's Lab before moving to Berkeley; a research intern at TRI in Cambridge, MA during the summer of 2025.
Education
- Ph.D.: University of California, Berkeley, Computer Science, advised by Professor Sergey Levine; B.S.: University of Tokyo, graduated in March 2022, advised by Professor Yoshimasa Tsuruoka.
Background
- Research interests: data-driven approaches to solving real-world robotic tasks, including offline reinforcement learning (RL), online RL fine-tuning, and imitation learning. Summary: The goal is to develop algorithms that empower robots with both high-level dexterity and generalization capabilities, and to incorporate them into everyday life.
Miscellany
- Contact: Email, Google Scholar, GitHub, Twitter; Personal interests not mentioned.
