Research

研究

  • Home
  • 研究業績

    • 研究業績

    カテゴリー

    研究領域

    年

    • 国際会議
      コンピュータービジョン

      MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation

      [paper]

      Yuta Oshima*, Daiki Miyake*, Kohsei Matsutani, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta (*Equal Contribution)

      The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026), June 2026

    • 国際会議
      ロボティクス

      M2oE: Modular Mixture of Experts for Multi-Morphology Reinforcement Learning of Modular Robots

      Chang Liu, Qinchao Xu, Satoshi Yagi, Satoshi Yamamori, Yaonan Zhu, Yusuke Iwasawa, Kazuya Yoshida, Jun Morimoto

      IEEE International Conference on Robotics & Automation (IEEE ICRA 2026), June 2026

    • 国際会議
      LLM / NLP

      Mechanism of Task-oriented Information Removal in In-context Learning

      [paper]

      Hakaze Cho, Haolin Yang, Gouki Minegishi, Naoya Inoue

      International Conference on Learning Representations 2026 (ICLR2026), April 2026

    • 国際会議
      LLM / NLP

      RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs

      [paper]

      Kohsei Matsutani, Shota Takashiro, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      International Conference on Learning Representations 2026 (ICLR2026), April 2026

    • 国際会議

      C-Voting: Confidence-Based Test-Time Voting without Explicit Energy Functions

      [paper]

      Kenji Kubo, Shunsuke Kamiya, Masanori Koyama, Kohei Hayashi, Yusuke Iwasawa, Yutaka Matsuo

      International Conference on Learning Representations 2026 (ICLR2026), April 2026

    • 国際会議
      LLM / NLP 強化学習

      Does “Do Differentiable Simulators Give Better Policy Gradients?” Give Better Policy Gradients?

      [paper]

      Ku Onoda, Paavo Parmas, Manato Yaguchi, Yutaka Matsuo

      International Conference on Learning Representations 2026 (ICLR2026), April 2026

    • 国際会議
      生成モデル

      Quantization-Aware Diffusion Models For Maximum Likelihood Training

      [paper]

      Shohei Taniguchi, Masahiro Suzuki, Yutaka Matsuo

      International Conference on Learning Representations 2026 (ICLR2026), April 2026

    • 国際会議
      LLM / NLP 強化学習

      Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learnin

      [paper]

      Ru Wang, Wei Huang, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo

      International Conference on Learning Representations 2026 (ICLR2026), April 2026

    • 国際会議
      機械学習一般

      MMA:Benchmarking Multi-ModalLarge Language Models in Ambiguity Context

      Ru Wang*, Selena Song*, Yuquan Wang, Liang Ding, Mingming Gong, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo (*Equal Contribution)

      The Third Conference on Parsimony and Learning(CPAL 2026), March 2026

    • 国際会議
      機械学習一般

      Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization

      [paper]

      Ru Wang, Wei Huang, Selena Song, Haoyu Zhang, Qian Niu, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo

      The Third Conference on Parsimony and Learning(CPAL 2026), March 2026