Research

研究

  • Home
  • 研究業績
  • 表現学習

    • 研究業績

    カテゴリー

    研究領域

    年

    • 国際会議
      理論 表現学習

      Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks

      [paper]

      Gnankan Landry Regis N’guessan, Bum Jun Kim

      Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), July 2026

    • 国際会議
      理論 表現学習

      Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models Against Gaussian Noise

      [paper]

      Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo

      Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), July 2026

    • 国際会議
      コンピュータービジョン 表現学習

      PUMPS: Skeleton-agnostic point-based universal motion pre-training for synthesis in human motion tasks

      [paper]

      Clinton Ansun Mo, Kun Hu, Chengjiang Long, Dong Yuan, Wan-Chi Siu, Zhiyong Wang

      Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2025), October 2025

    • 論文誌
      応用研究 表現学習

      手書き漢字の埋め込み表現による反復学習頻度最適化のための半減期予測

      小川竜欣, 河野慎, 謝志杰, 岸尚希, 落合桂一

      情報処理学会論文誌, Vol. 66, No. 9, pp. 1346-1356, 2025年9月

    • 国際会議
      LLM / NLP 表現学習

      Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

      [paper]

      Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      Advances in Neural Information Processing Systems (NeurIPS 2025), December 2025

    • 論文誌
      世界モデル 生成モデル 表現学習

      Efficient Object-Centric Representation Learning using Masked Generative Modeling

      [paper]

      Akihiro Nakano, Masahiro Suzuki, Yutaka Matsuo

      Transactions on Machine Learning Research (TMLR), 2025

    • 国際会議
      表現学習

      CityNav: A Large-Scale Dataset for Real-World Aerial Navigation

      [paper] [slide] [poster] [misc]

      Jungdae Lee*, Taiki Miyanishi*, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Yutaka Matsuo, Nakamasa Inoue (* denotes equally contributed)

      International Conference on Computer Vision (ICCV 2025)

    • 論文誌
      機械学習一般 表現学習

      Disappearance of Timestep Embedding: A Case Study on Neural ODE and Diffusion Models

      [paper] [misc]

      Bum Jun Kim, Yoshinobu Kawahara, Sang Woo Kim

      Transactions on Machine Learning Research (TMLR), 2025

    • 論文誌
      コンピュータービジョン 応用研究 表現学習

      Rethinking Domain-Specific Pre-Training by Supervised or Self-Supervised Learning for Chest Radiograph Classification: A Comparative Study Against ImageNet Counterparts in Cold-Start Active Learning

      [paper]

      Han Yuan, Mingcheng Zhu, Rui Yang, Han Liu, Irene Li, Chuan Hong

      Health Care Science, Vol. 4, No. 2, pp. 110-143, April 2025

    • 論文誌
      機械学習一般 表現学習

      Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks

      [paper]

      Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

      Transactions on Machine Learning Research (TMLR), 2025