Multimodal Evaluation & Metrics
Building reliable evaluation protocols for vision-language models, with a focus on grounding and cultural nuance in Japanese contexts.
Research Themes研究テーマ
Instruction-Tuned Multimodal LLMs
Curating instruction datasets and training recipes that keep open-weight models aligned and deployable.
Structured Generation & Understanding
Teaching models to produce and consume structured outputs such as captions, diagrams, and graphs for real-world tasks.
Publications論文
日本語視覚言語モデルのタスク横断評価と実証的分析
自然言語処理 · 2026
日本語に対応する VLM の能力を総合的・体系的に測る評価基盤 llm-jp-eval-mm を構築し、日本語 10 種・英語 9 種のデータセットを統合した一貫評価プロトコルで国内外 32 種の VLM を実証分析した。
Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models
arXiv preprint · 2026
JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation
arXiv preprint · 2026
JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding
International Conference on Document Analysis and Recognition (ICDAR 2026) · 2026
A diagnostic benchmark for evaluating Japanese scene text understanding in vision-language models across STVQA, receipt KIE, and handwriting OCR.
JaWildText: 日本語文字認識性能評価のための実世界画像データセット
言語処理学会第32回年次大会 (NLP2026) · 2026
日本語の実世界画像における文字認識と下流タスクを一体的に評価するためのデータセット JaWildText を提案する。高密度 STVQA、レシート KIE、手書き文字 OCR の 3 つの課題を収録し、公開 VLM および OCR 特化モデルの評価を通じて、日本語読字性能になお改善余地があることを示した。NLP2026 委員特別賞受賞論文。
Talks & Workshops招待講演・ワークショップ
Experience職歴・インターン
-
Sakana AI
Applied Research Engineer (Internship)
Jan 2026 – Present
-
National Institute of Informatics
Research Assistant
Jun 2024 – Present
-
Cierpa & Company
Engineering Internship
Jul 2024 – Mar 2025
-
RIKEN AIP
Research Part-timer
Jul 2022 – Aug 2024
-
OMRON SINIC X
Research Internship
Jun 2023 – Jan 2024
-
Tokyo Institute of Technology
Research Assistant
Dec 2021 – Dec 2022
-
NTT Research Institute
Summer Internship
Aug 2022 – Sep 2022
-
Future Corporation
Strategic AI Group
Feb 2021 – Mar 2022
Education学歴
2024 – Present
Ph.D., Tokyo Institute of Technology
Vision and Language, Evaluation
Advisors:指導教員： Naoaki Okazaki
Focusing on novel evaluation metrics for multimodal systems and cross-modal representation learning.
2022 – 2024
M.Eng., Tokyo Institute of Technology
Vision and Language: Image Captioning
Advisors:指導教員： Naoaki Okazaki
Developed context-aware image captioning models that generate descriptions based on user preferences.
2018 – 2022
B.Eng., Tokyo Institute of Technology
NLP: Grammatical Error Correction
Advisors:指導教員： Naoaki Okazaki, Masahiro Kaneko (Mentor)
Created improved evaluation metrics for grammatical error correction systems.
Awards & Fellowships受賞・フェローシップ
- Young Scientist Award, ANLP (2025)
- Committee Special Awarded Paper, ANLP (2026, 2025, 2023)
- Program for Development of Co-creative Experts towards Top-level AI Research (Science Tokyo BOOST) for Science and Engineering fields (2024–2027)
- Awarded Paper, ANLP (2022)
Skills & Expertiseスキル・専門分野
Programming
- Python
- PyTorch
- Java
Research Areas
- Computer Vision
- Natural Language Processing
- Multimodal Learning
- Image Captioning
- Evaluation Metrics
Languages
- Japanese (Native)
- English (Professional)