Koshiro Aoki

Waseda University

M.S. in Computer Science
Adviser: Daisuke Kawahara

Waseda University

B.S. in Computer Science
GPA: 3.8/4. Dean's Award.

Research Fellow

Supervised Program for Alignment Research (SPAR)

Research on introspection in large language models, mentored by Lydia Nottingham and Andrew Tran.

Research Assistant

Waseda University

Research on differences between the internal representations of the human brain and language models as part of a JST CREST project.

Research Contractor

The University of Tokyo

Research on interpretability and defenses of adversarial attacks on robot foundation models.

Technical Assistant

Research and Development Center for Large Language Models, National Institute of Informatics (NII)

Research on bottom-up interpretability of training dynamics in large language models.

In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?

Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi, Yusuke Haruki, Daisuke Kawahara

The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026 Findings)
Trustworthy AI for Good (AI4GOOD) Workshop @ ICML 2026 Spotlight

Bottom-Up Interpretability of Pretraining Dynamics via Loss Curve Decomposition

Koshiro Aoki, Masaru Isonuma, Max Müller-Eberstein, Yusuke Oda, Hirokazu Kiyomaru, Takashi Kodama, Chaoran Liu, Yohei Oseki, Yusuke Miyao, Daisuke Kawahara

Third Conference on Language Modeling (COLM 2026)

Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models

Yukiya Horiba, Koshiro Aoki, Shunsuke Yasuki, Bum Jun Kim, Taiki Miyanishi

The Science of Physical AI Safety (SPAIS) Workshop @ CoRL 2026

Crosscoders Identify Shared or Specific Features between the Human Brain and Language Models

Koshiro Aoki, Itsuki Hamada, Naho Orita, Daisuke Kawahara, Hiromu Sakai

Mechanistic Interpretability Workshop @ ICML 2026

Evaluating the Impact of SAE-based Language Steering on LLM Performance

Sebastian Zwirner, Wentao Hu, Koshiro Aoki, Daisuke Kawahara

EACL 2026 Student Research Workshop

Testing Simulation Theory in LLMs' Theory of Mind

Koshiro Aoki, Daisuke Kawahara

IJCNLP-AACL 2025 Student Research Workshop Oral

Mechanistic Interpretability: A New Trend in Interpretability Research

Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi, Hakaze Cho

Transactions of the Japanese Society for Artificial Intelligence Best Paper Award

Spotlight Paper

Trustworthy AI for Good (AI4GOOD) Workshop @ ICML 2026

Best Paper Award

The Japanese Society for Artificial Intelligence 40th Anniversary Commemorative Paper Award

Dean's Award for Excellence

School of Fundamental Science and Engineering, Waseda University

Young Researcher Encouragement Award

The 32nd Annual Meeting of the Association for Natural Language Processing

Oral Presentation

IJCNLP-AACL 2025 Student Research Workshop

Encouragement Award

The 20th Young Researcher Association for NLP Studies

Sponsored Award

The 31st Annual Meeting of the Association for Natural Language Processing