Shota Takashiro — accepted AI-conference papers

2026

CLIP-like Model as a Foundational Density Ratio Estimator

Fumiya Uchiyama, Rintaro Yanagi, Shohei Taniguchi, Shota Takashiro, Masahiro Suzuki, Hirokatsu Kataoka +2

CVPR 2026

Density ratio estimation is a core concept in statistical machine learning because it provides a unified mechanism for tasks such as importance weighting, divergence estimation, and likelihood-free inference, but its potential in vision and language models has not been fully explored. Modern vision-

Cited by 0 Source ↗code ↗Scholar ↗

2026

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

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

ICLR 2026poster

Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape reasoning capabilities remains largely elusive. Going beyond an…

Cited by 0 Source ↗Scholar ↗

2025

Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning

Shota Takashiro, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo

ACL 2025finding

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information to authorized internal users, such as employees or trusted p…

Cited by 0 Source ↗PDF ↗Scholar ↗