Kyoto University · Graduate School of Informatics · 助教

Research keywordslong-context LLMs・retrieval-augmented prompting・hallucination mitigation・vision-language models・probability calibration・dynamic graph anomalies・post-hoc softmax calibration

This is a public-data preview. Personalized fit, contact angles, and saved workflows require sign-in.

• Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models2025 · 2025年02月24日
• Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax2025 · 2025年06月12日
• Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs2025 · 2025年09月22日
• Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs2025 · 2025年02月18日

• Official profile
• Lab page