Curriculum Vitae

Role

Project Assistant Professor, Matsuo Laboratory, The University of Tokyo
Senior Researcher, Matsuo Institute
Lecturer, ZEN University

Short Bio

Makoto Kawano received his B.A. from the Faculty of Environment and Information Studies, Keio University, in 2014, his master’s degree from the Graduate School of Interdisciplinary Information Studies, The University of Tokyo, in 2016, and his Ph.D. from the Graduate School of Media and Governance, Keio University, in 2019. During his doctoral studies, he was supported by the JSPS Research Fellowship for Young Scientists (DC1). He joined the Matsuo Laboratory at The University of Tokyo as a Project Researcher in 2019, became a Project Assistant Professor in 2022, and has also served as a Lecturer at ZEN University and a Senior Researcher at Matsuo Institute since 2025. His research interests include transfer learning, deep generative models, foundation models, robotics, autonomous driving, world models, and machine learning for real-world data.

Download PDF CV

Education

  • Ph.D. in Media and Governance, Keio University, 2019
  • Master’s Degree in Interdisciplinary Information Studies, The University of Tokyo, 2016
  • B.A. in Environment and Information Studies, Keio University, 2014

Professional Experience

  • Lecturer, ZEN University, 2025-
  • Senior Researcher, Matsuo Institute, 2025-
  • Project Assistant Professor, Matsuo Laboratory, The University of Tokyo, 2022-
  • Project Researcher, Matsuo Laboratory, The University of Tokyo, 2019-2022

Research Interests

  • Machine learning for real-world data
  • Transfer learning
  • Deep generative models
  • Foundation models
  • Representation learning
  • Continual learning
  • Knowledge distillation
  • World models
  • Robotics and autonomous driving
  • Wearable sensing and human performance analytics

Selected Publications

Journal Articles

  1. Tatsuyoshi Ogawa, Makoto Kawano, Zhijie Xie, Naoki Kishi, Keiichi Ochiai, “Half-life Prediction for Optimizing Spaced Repetition Frequency Using Embedded Representations of Handwritten Kanji,” IPSJ Journal, vol.66, no.9, 2025.
  2. Wataru Kumagai, Akiyoshi Sannai, Makoto Kawano, “Universal Approximation with Neural Networks on Function Spaces,” Journal of Experimental & Theoretical Artificial Intelligence, 2022.
  3. Hirono Kawashima, Makoto Kawano, Tadasu Ogoshi, Jin Nakazawa, “Capacity Control Considering Class Difficulty in Continual Learning for Image Classification with Deep Learning,” Computer Software, 2022.
  4. Makoto Kawano, Takuro Yonezawa, Yutaro Okino, Jin Nakazawa, “CityInspector: An In-vehicle Edge-based Road Damage Inspection System for Extending Daily Municipal Operations,” IPSJ Journal, vol.60, no.10, pp.1796-1808, 2019.
  5. Tomoki Tanimura, Makoto Kawano, Takuro Yonezawa, Jin Nakazawa, “GANonymizer: A Video Anonymization Method Using Object Detection and Adversarial Generation,” IPSJ Journal, vol.60, no.10, pp.1829-1844, 2019.

Conference and Workshop Highlights

  1. Nam Ky Giang, Victor C.M. Leung, Makoto Kawano, Takuro Yonezawa, Jin Nakazawa, Rodger Lea, Matt Broadbent, “CityFlow: Exploiting Edge Computing for Large Scale Smart City Applications,” IEEE International Conference on Big Data and Smart Computing, 2019.
  2. Makoto Kawano, Takuro Yonezawa, Tomoki Tanimura, Nam Ky Giang, Matthew Broadbent, Rodger Lea, Jin Nakazawa, “CityFlow: Supporting Spatial-Temporal Edge Computing for Urban Machine Learning Applications,” The Third International Conference on IoT in Urban Space, 2018.
  3. Makoto Kawano, Takuro Yonezawa, Jin Nakazawa, “Deep on Edge: Opportunistic Road Damage Detection with City Official Vehicles,” The Third International Conference on Smart Portable, Wearable, Implantable and Disability-oriented Devices and Systems, 2016.
  4. Makoto Kawano, Kazuhiro Ueda, “Where Are You Talking From?: Estimating the Location of Tweets Using Recurrent Neural Networks,” The Second International Conference on IoT in Urban Space, 2016.
  5. Makoto Kawano, Atsuya Ishizu, Sota Nakamura, Tatsuki Matsunaga, Yasuki Watanabe, Ayuki Inoue, Toshiki Tsuzuku, Yasuhiro Noda, “A Study on Data Collection Strategies for World Model Learning,” The 39th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI2025), 2025.

For a fuller list, see the Publications section.

Invited Talks

  • Invited Talk on Physical AI, HUMAI Summer Camp, 2025
  • “The Impact of Generative AI: Expanding Technologies and Use Cases of Generative AI,” 2023
  • Tier IV X Research Seminar, 2020
  • The Applied Physics Society 2nd Oyo Seminar, 2020
  • T4X Perception Study Group Presentation, 2020
  • The University of Tokyo Homecoming Day Special Forum Related Event, “Frontiers of AI Research,” 2019
  • The 4th Young Symposium on Statistics and Machine Learning, Invited Talk, 2019

Grants

  • JSPS Research Fellowship for Young Scientists (DC1), 2016-2019
    “Research on Understanding and Predicting Urban Context Using Participatory Sensing and Sensor Data”
  • JSPS Grant-in-Aid for Early-Career Scientists, 2020-2023
    “Development and Practical Application of Data-efficient Urban Inspection Technology for Improving Municipal Operations”

Awards

  • Outstanding Paper Award, 2024
    Toshiharu Maeba, Makoto Kawano, Yutaka Matsuo, “Knowledge Distillation from Vision Transformers to Convolutional Neural Networks,” IPSJ SIG Ubiquitous Computing Systems.
  • Best Paper Award, 2022
    Itsuki Okimura, Machel Reid, Makoto Kawano, Yutaka Matsuo, “On the Impact of Data Augmentation on Downstream Performance in Natural Language Processing,” ACL Workshop on Insights from Negative Results in NLP.
  • Student Encouragement Award, 2020
    Hirono Kawashima, Makoto Kawano, Wataru Kumagai, Kota Matsui, Jin Nakazawa, “Continual Learning Based on Amortized Inference,” JSAI2020.
  • Student Presentation Award, 2018
    Hirono Kawashima, Makoto Kawano, Takuro Yonezawa, Jin Nakazawa, “Log Analysis of the Fujisawa City Call Center for Understanding Citizens' Interests,” DEIM 2018.
  • Microsoft Award, Leave a Nest
  • Best Paper Award, 2017
    Makoto Kawano, Takuro Yonezawa, Jin Nakazawa, “Deep on Edge: Opportunistic Road Damage Detection with City Official Vehicles.”

Teaching Experience

  • Lecturer, ZEN University, 2025-
  • Lecturer, “World Model Endowed Course” (Lecture 12: Autonomous Driving), Matsuo Laboratory, 2025
  • Lecturer, “AI Management Endowed Course II: Recent AI Trends,” Matsuo Laboratory, 2023-2025
  • Lecturer, “Deep Learning: Introductory Course” (Lecture 2: Fundamentals of Machine Learning), The University of Tokyo, 2019-2025
  • Part-time Lecturer, Keio University, “Information Literacy 1/2,” 2016-2019

Academic Service and Social Activities

  • Organizer, Organized Session “Physical AI in the Foundation Model Era”, JSAI Annual Conference, 2026
  • Judge, “The 1st HUMAI Essay Final Review,” Genron Cafe, April 5, 2026
  • Organizing Member, HUMAI Program, The Second Matsuo Lab / ZEN University, 2025-
  • Editorial Committee Member, IPSJ Journal (Foundations and Theory / FWG)
  • Organizer, Organized Session “World Models,” JSAI Annual Conference, 2022-2025
  • Deputy Examiner for Master’s Thesis, 2021-2022
  • Organizer, NeurIPS Meetup Japan 2020
  • Web Chair, The 2nd EAI International Conference on IoT in Urban Space, 2016

Administrative and Internal Activities

  • Faculty in charge, Deep Learning Cross-disciplinary Research Meeting, 2019
  • Organizer, DLHacks, 2018
  • Organizer, External Seminar Series, until 2021
  • Organizer, Poster Day, 2023 and 2024

Books

  • Ian Goodfellow, Yoshua Bengio, Aaron Courville, supervised by Yusuke Iwasawa, Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo; translated by Masashi Asono, Hiroki Kurotaki, Jun Hozumi, Naoki Nonaka, Makoto Kawano, Shoji Tomiyama, Takahiro Kakuta, Deep Learning, KADOKAWA / Chukei Publishing, 2018.

Theses

  • Bachelor’s Thesis (2014): “A Method for Real-world Event Classification Based on Follow-set Analysis in Social Networks”
  • Master’s Thesis (2016): “Transportation Mode and Location Estimation by Automatic Feature Extraction”
  • Ph.D. Thesis (2019): “Towards Affordable Urban Computing through Deep Learning”