I am currently a 2nd-year Ph.D. student at MIL, the University of Tokyo, advised by Prof. Tatsuya Harada and Lect. Yusuke Mukuta. I also received B.S. and M.S from The University of Tokyo, advised by Prof. Tatsuya Harada and Lect. Yusuke Mukuta.

Research Interests

My research focuses on understanding and modeling human dynamics, particularly in human motion generation and prediction, 3D reconstruction, and time-series forecasting. Recently, I have been especially interested in leveraging multimodal LLMs to advance the modeling of complex human behaviors. My long-term goal is to develop embodied AI systems, including intelligent agents and robots that can perceive, understand, and predict human motion, enabling them to interact safely, naturally, and meaningfully with people.

Education

• [2024.04 - Present] Ph.D. in Mechano-Informatics, The University of Tokyo
• [2022.04 - 2024.03] M.S. in Mechano-Informatics, The University of Tokyo
• [2018.04 - 2022.03] B.S. in Mechano-Informatics, The University of Tokyo

Internship

• [2024.06 - 2024.07] Visiting Researcher at Princeton Vision & Learning Lab. Advisor: Prof. Jia Deng
• [2023.08 - 2023.09] Student Researcher at Google Research. Advisor: Dr. Yasuhisa Fujii
• [2023.08 - 2023.09] Research Intern at LINE. Advisor: Dr. Kent Fujiwara

Research

• Ryo Umagami, Liu Yue, Xuangeng Chu, Ryuto Fukushima, Tetsuya Narita, Yusuke Mukuta, Tomoyuki Takahata, Jianfei Yang, Tatsuya Harada. “Intend to Move: A Multimodal Dataset for Intention-Aware Human Motion Understanding.” NeurIPS2025 D&B. Project Page
• Ryo Umagami, Yu Ono, Yusuke Mukuta. Tatsuya Harada. “HiPerformer: Hierarchically Permutation-Equivariant Transformer for Time Series Forecasting.” arXiv:2305.08073, 2023. Paper

Misc

• I’m a track & field sprinter! I specialize in the 110m hurdles 🏃‍♂️