Research

  • Home
  • Publications

    • Publications

    Category

    Research Area

    Year

    • Journals
      LLM / NLP

      Continual Pre-training on Character-Level Noisy Texts Makes Decoder-based Language Models Robust Few-shot Learners

      [paper]

      Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa

      Transactions of the Association for Computational Linguistics (TACL)

    • International Conferences
      Robotics

      A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics

      Takeshi Kojima (*), Yaonan Zhu (*), Yusuke Iwasawa (*), Toshinori Kitamura, Gang Yan, Shu Morikuni, Ryosuke Takanami, Alfredo Solano, Tatsuya Matsushima, Akiko Murakami, Yutaka Matsuo. (*) Equal Contribution

      The 34th International Joint Conference on Artificial Intelligence – Survey Track (IJCAI 2025 Survey Track)

    • Journals
      Machine Learning in General Representation Learning

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

      [paper]

      Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

      Transactions on Machine Learning Research (TMLR)

    • International Conferences
      LLM / NLP

      Lost in the Distance: Large Language Models Struggle to Capture Long-Distance Relational Knowledge

      [paper]

      Meiyun Wang, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      The 2025 Annual Conference of the Nations of the Americas Chapter of the ACL (NAACL 2025)

    • International Conferences
      LLM / NLP

      Language Models can Categorize System Inputs for Performance Analysis

      [paper]

      Dominic Sobhani, Ruiqi Zhong, Edison Marrese-Taylor, Keisuke Sakaguchi, Yutaka Matsuo

      Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)

    • International Conferences

      Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form

      [paper] [poster]

      Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Masashi Hamaya, Paavo Parmas, Yutaka Matsuo

      International Conference on Learning Representations (ICLR 2025)

    • International Conferences
      LLM / NLP

      Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

      [paper] [poster]

      Gouki Minegishi, Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo

      International Conference on Learning Representations (ICLR 2025)

    • Journals
      LLM / NLP

      Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web

      [paper] [web]

      Hiroki Furuta, Yutaka Matsuo, Aleksandra Faust, Izzeddin Gur.

      Transactions on Machine Learning Research (TMLR).

    • Journals
      ML General

      Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials

      [paper] [web]

      Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

      Transactions on Machine Learning Research (TMLR).

    • Awards
      Robotics

      Advanced Robotics Best Survey Paper Award, 2024

      Tadahiro Taniguchi, Shingo Murata, Masahiro Suzuki, Dimitri Ognibene, Pablo Lanillos, Emre Ugur, Lorenzo Jamone, Tomoaki Nakamura, Alejandra Ciria, Bruno Lara, Giovanni Pezzulo,