Hirohane Takagi
Hirohane Takagi

高木 洋羽

About

I am a master’s student in computer science at the University of Tokyo, Japan.
My interests lie in reliable control of generative models through learning from limited information and human–AI collaboration. I strive to engage in both theoretical exploration and practical application development.

Interests
  • Statistical Machine Learning
  • Large Language Models
  • Explainable AI, Interprretability
Education

  • MSc Computer Science (ongoing)

    The University of Tokyo

  • BEng Mathematical Engineering

    The University of Tokyo

Refereed Conference Papers

  1. Hirohane Takagi, Atsushi Nitanda. (2026, April). Alternating Diffusion for Proximal Sampling with Zeroth Order Queries. The 14th International Conference on Learning Representations.
    Conference Page

  2. Hirohane Takagi*, Gouki Minegishi*, Shota Kizawa, Issey Sukeda, Hitomi Yanaka. (2025, December). Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models. In Proceedings of International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (pp. 1098-1115).
    Paper, Arxiv, Code (GitHub) Conference Poster
    Also featured in the AIP Symposium poster

  3. Hirohane Takagi, Shoji Moriya, Takuma Sato, Manabu Nagao, Keita Higuchi. (2025, March). A Framework for Efficient Development and Debugging of Role-Playing Agents with Large Language Models. In Proceedings of the 30th International Conference on Intelligent User Interfaces (pp. 70-88).
    Paper, PFN Tech Blog (Japanese)

Domestic Conference Papers (国内発表)

  1. 高木洋羽, 佐藤大地, 長谷川貴巨, 大福泰樹, 武田峻悟, 山内有倫, 高橋孝樹, 国藤靖彦, 機械学習と波形補正を用いたスマートメーター計測値からPV出力と実需要への分離推定, 令和7年電気学会全国大会, (2025.3).
    要旨(6-102)，松尾研究所と東京電力パワーグリッドの共同研究⚡️
    Blog記事 @ 松尾研究所, Zenn

  2. 峰岸剛基*, 高木洋羽*, 木澤翔太*, 助田一晟, 谷中瞳, 大規模言語モデルにおいて数値属性間で共有されるスケーリングベクトルの解析とその応用, 言語処理学会第31回年次大会, (2025.3).
    予稿，プログラム (A6-2) (口頭発表), 若手奨励賞 (20件/487件)🎉

  3. 高木洋羽, 守屋彰二, 佐藤拓真, 永尾学, 樋口啓太, 大規模言語モデルを用いたロールプレイエージェントの効率的な開発と動作検証のためのフレームワーク, インタラクション2025, (2025.3).
    予稿 (査読あり), 登壇発表 (Youtube), Webカタログ (17)

Other Activities

Book Reviewing

  • Joined the volunteer review of Deep Learning from Scratch Series, which first introduced me to Python and deep learning, as a small way of giving something back.
    • Vol. 5: Generative Models — 『ゼロから作るDeep Learning ❺―生成モデル編』
    • Vol. 6: LLMs — 『ゼロから作るDeep Learning❻—LLM編』)

GDG Tokyo / GDGoC