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

      PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining

      Machel Reid and Mikel Artetxe.

      7th Workshop on Representation Learning for NLP (non-archival), ACL 2022.

    • 国際会議
      世界モデル 強化学習

      Generalized Decision Transformer for Offline Hindsight Infomation Matching

      Hiroki Furuta, Yutaka Matsuo, and Shixiang Shane Gu

      International Conference on Learning Representations 2022 (ICLR2022, Spotlight).

    • 国際会議
      世界モデル

      Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following

      Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo

      Workshop on Novel Ideas in Learning-to-Learn through Interaction, EMNLP 2021.

    • 国際会議
      コンピュータービジョン 理論 表現学習

      Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization

      Yusuke Iwasawa, and Yutaka Matsuo.

      Advances in Neural Information Processing Systems 2021 (NeurIPS2021, Spotlight). December 2021.

    • 国際会議
      強化学習 理論 表現学習

      Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

      Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, and Shixiang Shane Gu.

      Advances in Neural Information Processing Systems 2021 (NeurIPS2021). December 2021.

    • 国際会議
      LLM / NLP

      AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages

      Machel Reid, Junjie Hu, Graham Neubig and Yutaka Matsuo

      The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021). November 2021. Association for Computational Linguistics.

    • 国際会議
      LLM / NLP

      Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers

      Machel Reid, Edison Marrese-Taylor and Yutaka Matsuo.

      Findings of The 2021 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2021). Association for Computational Linguistics. 

    • 国際会議
      コンピュータービジョン

      Alignment-free Object-level Scene Change Detection using Deep Object Matching

      Kento Doi, Ryuhei Hamaguchi, Yusuke Iwasawa, Masaki Onishi, Yutaka Matsuo, Ken Sakurada.

      IEEE Robotics and Automatation Society (IROS2022)

    • 国際会議
      強化学習 理論 表現学習

      Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning

      Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, and Shixiang Shane Gu

      International Conference on Machine Learning 2021 (ICML2021).

    • 国際会議
      強化学習 理論 表現学習

      Identifying Co-Adaptation of Algorithmic and implementational Innovations in Deep Reinforcement Learning: Taxonomy of Inference-based Algorithms

      Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu.

      International Conference on Machine Learning 2021 (ICML2021).