Research

研究

  • Home
  • 研究業績
  • LLM / NLP

    • 研究業績

    カテゴリー

    研究領域

    年

    • 国際会議
      LLM / NLP

      Batch-wise Adaptive Pruning: Periodic Neuron Activation-Aware Weight Pruning for Language Reasoning Model

      Yongmin Kim, Shota Takashiro, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      Proceedings of the 3rd Conference on Language Modeling (COLM 2026), October 2026

    • 国際会議
      LLM / NLP 医療AI

      JMedEthicBench: A Multi-Turn Adversarial Benchmark for Japanese Medical Ethics Alignment in LLMs

      [paper]

      Junyu Liu, Zirui Li, Qian Niu, Zequn Zhang, Yue Xun, Wenlong Hou, Shujun Wang, Yusuke Iwasawa, Yutaka Matsuo, Kan Hatakeyama-Sato

      Proceedings of the 3rd Conference on Language Modeling (COLM 2026), October 2026

    • 国際会議
      LLM / NLP

      AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning

      [paper]

      Haoyu Zhang, Jiaxian Guo, Dong Yang, Yusuke Iwasawa, Yutaka Matsuo

      Annual Conference of the International Speech Communication Association (Interspeech 2026), September 2026

    • 論文誌
      LLM / NLP ロボティクス

      LLM-guided Adaptive Compensator: Bringing Adaptivity to Robotic Feedback Control with Large Language Model

      [paper]

      Zhongchao Zhou, Yuxi Lu, Yaonan Zhu, Yifei Zhao, Qian Niu, Bin He, Liang He, Wenwei Yu, Yusuke Iwasawa

      IEEE Transactions on Automation Science and Engineering (T-ASE), 2026

    • 論文誌
      LLM / NLP 応用研究

      When medical AI fails outside English

      [paper]

      Irene Li, Hardy Kagimoto, Yusuke Iwasawa, Yutaka Matsuo, Ethan Goh

      BMJ Digital Health & AI, Vol. 2, No. 1, e000038, Editorial (Invited), 2026

    • 国際会議
      LLM / NLP

      Steering at the Source: Style Modulation Heads for Robust Persona Control

      [paper]

      Yoshihiro Izawa, Gouki Minegishi, Koshi Eguchi, Sosuke Hosokawa, Kenjiro Taura

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

    • 国際会議
      LLM / NLP

      Emergent Analogical Reasoning in Transformers

      [paper]

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

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

    • 国際会議
      LLM / NLP

      Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise

      [paper]

      Keno Harada, Lui Yoshida, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      Proceedings of the 30th Conference on Computational Natural Language Learning (CoNLL 2026), July 2026

    • 国際会議
      LLM / NLP

      Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models

      Qi Cao, Takeshi Kojima, Andrew Gambardella, Helinyi Peng, Yutaka Matsuo, Yusuke Iwasawa

      The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), Findings, July 2026

    • 国際会議
      LLM / NLP

      Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks

      Sunil Kumar Maurya, Xin Liu

      The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), Main, Long, July 2026