NII Kurita Lab NII 栗田研

National Institute of Informatics / SOKEN University 国立情報学研究所 / 総合研究大学院大学情報学コース

top_pic.jpg

Coffee machine manipulation demo by a bimanual robot Aloha Stationary

双腕ロボットAloha Stationaryでのコーヒーマシン操作デモ

Kurita Lab at the National Institute of Informatics studies real-world applications of large language models and foundation models. The lab was established in April 2024 and hosted students from April 2025. Our goal is to connect symbolic information such as text with physical, non-symbolic information obtained from cameras and other sensors, and to apply advanced reasoning technologies represented by large language models to real-world and physical environments. To this end, we work on research projects in language models and vision-language models, embodied AI and robotic foundation models, and AI for Science.
NII栗田研は国立情報学研究所にて大規模言語モデルや基盤モデル技術の実世界応用に取り組む研究室です。2024年4月に発足し2025年4月より学生の受け入れを開始しました。 テキストのようなシンボル情報とカメラ・センサなどから得られる物理情報・非シンボル情報を対応付けること、さらに、大規模言語モデルに代表される高度な推論技術を実世界・物理世界に応用することを目標に、言語モデル・視覚言語モデル、Embodied AI・ロボット基盤モデル、AI for Science などの研究プロジェクトを進めています。

News ニュース

May 01, 2026 2026年5月1日 Chi Zhang joined our lab as a Specially Appointed Researcher. Welcome!
Feb 21, 2026 2026年2月21日 Our paper is accepted to CVPR2026!
Daichi Yashima, Shuhei Kurita, Yusuke Oda, Komei Sugiura, “ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding”, CVPR2026. arXiv
Feb 01, 2026 2026年2月1日 Our paper is accepted to ICRA2026!
Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, Shinsuke Mori, “Developing Vision-Language-Action Model from Egocentric Videos”, ICRA2026. arXiv
Sep 27, 2025 2025年9月27日 Our paper is accepted to ACMMM2025!
Mahiro Ukai, Shuhei Kurita, Nakamasa Inoue, “STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models”, ACMMM2025. paper
Jun 26, 2025 2025年6月26日 Three papers are accepted to ICCV2025!
Kanoko Goto, Takumi Hirose, Mahiro Ukai, Shuhei Kurita, Nakamasa Inoue, “Referring Expression Comprehension for Small Objects”, paper.
Jungdae Lee, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Yutaka Matsuo and Nakamasa Inoue, “CityNav: A Large-Scale Dataset for Real-World Aerial Navigation”, paper.
Shunsuke Yasuki, Taiki Miyanishi, Nakamasa Inoue, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Masato Taki, Yutaka Matsuo, “GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields”, paper.

Latest posts 最新記事

Mar 29, 2026 2026年3月29日 2025 Annual Report 2025年度活動報告

Selected publications 主な論文

  1. CVPR
    ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
    Daichi Yashima, Shuhei Kurita, Yusuke Oda, and 1 more author
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    To appear
  2. ICRA
    Developing Vision-Language-Action Model from Egocentric Videos
    Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, and 1 more author
    In IEEE International Conference on Robotics and Automation (ICRA), 2026
    To appear
  3. CVPR
    Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision
    Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, and 1 more author
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
  4. ICCV
    RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D
    Shuhei Kurita, Naoki Katsura, and Eri Onami
    In IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  5. CVPR
    ScanQA: 3D Question Answering for Spatial Scene Understanding
    Daichi Azuma*, Taiki Miyanishi*, Shuhei Kurita*, and 1 more author
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    * Equally contributed.
  6. ACL
    Neural Joint Model for Transition-based Chinese Syntactic Analysis
    Shuhei Kurita, Daisuke Kawahara, and Sadao Kurohashi
    In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), 2017