Research

研究

  • Home
  • 研究業績
  • 国際会議

    • 研究業績

    カテゴリー

    研究領域

    年

    • 国際会議
      LLM / NLP

      Revealing Redundant Syntax in Large Language Models through Multi-Hop Dependency Paths

      [paper]

      Masaki Sashida, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo.

      The 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), March 2026.

    • 国際会議
      生成モデル

      One-shot Portrait Stylizaiton via Geometric Alignment

      [paper]

      Xinrui Wang, Zilin Guo, Zhuoru Li, Jinze Yu, Heng Zhang, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo

      Proceedings of The IEEE/CVF Winter Conference on Applications of Computer Vision 2026 (WACV2026), March 2026.

    • 国際会議
      理論 生成モデル

      Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model

      [paper]

      Kotaro Ikeda, Masanori Koyama, Jinzhe Zhang, Kohei Hayashi, Kenji Fukumizu

      Advances in Neural Information Processing Systems 38 (NeurIPS 2025), December 2025.

    • 国際会議
      ロボティクス 強化学習

      The Impact of VR and 2D Interfaces on Human Feedback in Preference-Based Robot Learning

      [paper]

      Jorge de Heuvel, Daniel Marta, Simon Holk, Iolanda Leite, Maren Bennewitz

      Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025), October 2025

    • 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

    • 国際会議
      LLM / NLP

      KokushiMD-10: Benchmark for Evaluating Large Language Models on Ten Japanese National Healthcare Licensing Examinations

      [paper] [slide] [poster]

      Junyu Liu, Kaiqi Yan, Tianyang Wang, Qian Niu, Momoko Nagai-Tanima, Tomoki Aoyama

      Clinical MLLMs Workshop (MICCAI 2025), October 2025.

    • 国際会議
      LLM / NLP

      Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models

      [paper]

      Hirohane Takagi*, Gouki Minegishi*, Shota Kizawa, Issey Sukeda, Hitomi Yanaka (*Equal Contribution)

      The 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2025), Main, November 2025

    • 国際会議
      LLM / NLP

      Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data

      [paper]

      Yohei Kobashi, Fumiya Uchiyama, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo

      The 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2025), Main, November 2025

    • 国際会議
      LLM / NLP 理論

      When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars

      [paper]

      Rei Higuchi, Ryotaro Kawata, Naoki Nishikawa, Kazusato Oko, Shoichiro Yamaguchi, Sosuke Kobayashi, Seiya Tokui, Kohei Hayashi, Daisuke Okanohara, Taiji Suzuki

      Conference on Language Modeling (COLM 2025), October 2025

    • 国際会議
      強化学習 理論

      Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

      [paper]

      Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Wataru Kumagai, Kazumi Kasaura, Kenta Hoshino, Yohei Hosoe, Yutaka Matsuo.

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