Hiroki Furuta

Hiroki Furuta

Ph.D. Student at The University of Tokyo

I am a Ph.D. student in Technology Management for Innovation at The University of Tokyo, advised by Yutaka Matsuo. I am also a Student Researcher at Google DeepMind, hosted by Heiga Zen and Izzeddin Gur. I was also received BEng and MEng at The University of Tokyo, and closely mentored by Shixiang Shane Gu.

My research interest has focused on data-driven control towards real-world applications (e.g. robotics, web automation), and scalable decision making with large-scale foundation models.

Recent Preprints

  1. Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo.
    Interpreting Grokked Transformers in Complex Modular Arithmetic
    arXiv preprint arXiv:2402.16726, 2024.
    ICLR 2024 Workshop Bridging the Gap Between Practice and Theory in Deep Learning $^{*}$ (Oral).
    [arxiv] [code]

  2. Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John Canny, Ian Fischer.
    A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
    arXiv preprint arXiv:2402.09727, 2024.
    [arxiv] [website]

  3. Hiroki Furuta, Yutaka Matsuo, Aleksandra Faust, Izzeddin Gur.
    Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
    arXiv preprint arXiv:2311.18751, 2023.
    [arxiv] [code]

Conference Publications

  1. Open X-Embodiment Collaboration, et al.
    Open X-Embodiment: Robotic Learning Datasets and RT-X Models
    IEEE International Conference on Robotics and Automation (ICRA 2024).
    [arxiv] [website]

  2. Izzeddin Gur*, Hiroki Furuta*, Austin Huang, Mustafa Safdari, Yutaka Matsuo, Douglas Eck, Aleksandra Faust. (*Equal Contribution)
    A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
    International Conference on Learning Representations (ICLR 2024) (Oral, 1.2% of 7262 submissions).
    [arxiv]

  3. Hiroki Furuta, Kuang-Huei Lee, Ofir Nachum, Yutaka Matsuo, Aleksandra Faust, Shixiang Shane Gu, Izzeddin Gur.
    Multimodal Web Navigation with Instruction-Finetuned Foundation Models
    International Conference on Learning Representations (ICLR 2024).
    [arxiv] [website]

  4. Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo, Shixiang Shane Gu.
    A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
    International Conference on Learning Representations (ICLR 2023) (Notable-top-25%, 8% of 4966 submissions).
    [arxiv] [code] [website]

  5. Hiroki Furuta, Yutaka Matsuo, Shixiang Shane Gu.
    Generalized Decision Transformer for Offline Hindsight Information Matching
    International Conference on Learning Representations (ICLR 2022) (Spotlight, 5% of 3391 submissions).
    [arxiv] [code] [website]

  6. Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu.
    Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning
    Neural Information Processing Systems (NeurIPS 2021).
    [arxiv] [code]

  7. Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, Shixiang Shane Gu.
    Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
    International Conference on Machine Learning (ICML 2021).
    [arxiv] [code]

  8. Tatsuya Matsushima*, Hiroki Furuta*, Yutaka Matsuo, Ofir Nachum, Shixiang Gu. (*Equal Contribution)
    Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
    International Conference on Learning Representations (ICLR 2021).
    [openreview] [code]

Journal Publications

  1. So Kuroki, Tatsuya Matsushima, Junpei Arima, Hiroki Furuta, Yutaka Matsuo, Shixiang Shane Gu, Yujin Tang.
    Collective Intelligence for 2D Push Manipulations With Mobile Robots
    IEEE Robotics and Automation Letters (RA-L), 2023.
    [paper]

Please check Publications for further details.

Talks

  1. Hiroki Furuta. “Opportunities and Challenges of Language Model Agents in Web Automation”. Berkeley Artificial Intelligence Research Lab, 2023.

  2. Hiroki Furuta. “Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning”. NeurIPS Meetup Japan 2021 $^{*}$, 2021.

Academic Activitites

  1. Reviewer for Neural Information Processing Systems (NeurIPS), 2021, 2022 (Top Reviewer), 2023 (Top Reviewer).

  2. Reviewer for International Conference on Learning Representations (ICLR), 2022 (Highlighted Reviewer), 2023, 2024.

  3. Reviewer for International Conference on Machine Learning (ICML), 2021, 2022, 2023, 2024.

  4. Reviewer for Transactions on Machine Learning Research (TMLR).

  5. Reviewer for Advanced Robotics (AR).

  6. Co-organizer for Ecological Theory of RL Workshop at NeurIPS 2021.

  7. Program Committee for Foundation Models for Decision Making Workshop at NeurIPS 2022, 2023.

Honors & Awards

  • Forbes JAPAN 30 UNDER 30 2023 (August, 2023)
  • The Japan Society for the Promotion of Science Research Fellow (DC1) (April, 2022 - March, 2025)
  • Dean’s Award (from Graduate School of Engineering, The University of Tokyo, 2022)
  • Toyota/Dwango Scholarship for Advanced Artificial Intelligence Researcher (April, 2021 - March, 2022)

Education & Experience

  • Student Researcher at Google DeepMind (June, 2023 - Present)
  • Student Researcher at Google Research, Brain Team (July, 2022 - May, 2022)
  • MEng from The University of Tokyo (March, 2022)
  • BEng from The University of Tokyo (March, 2020)