Research Focus
Exploring the intersection of computer vision and natural language processing, with a focus on multimodal evaluation metrics and context-aware image captioning.
- Designing instruction-tuned multimodal LLMs and evaluation pipelines that balance academic rigor with deployability.
- Building curated Japanese-language datasets for captioning, reasoning, and cultural understanding in vision-language systems.
Education
-
2024 – Present
Ph.D., Tokyo Institute of Technology
Focusing on novel evaluation metrics for multimodal systems and cross-modal representation learning.
-
2022 – 2024
M.Eng., Tokyo Institute of Technology
Developed context-aware image captioning models that generate descriptions based on user preferences.
-
2018 – 2022
B.Eng., Tokyo Institute of Technology
Created improved evaluation metrics for grammatical error correction systems.
Publications
International Conferences & Workshops
- Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs
- Building instruction-tuning datasets from human-written instructions with open-weight large language models
- Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model
- LegalViz: Legal Text Visualization by Text To Diagram Generation
- COM Kitchens: An Unedited Overhead-view Procedural Videos Dataset as a Vision-Language Benchmark
- Query-based Image Captioning from Multi-context 360-degree Images
- IMPARA: Impact-Based Metric for GEC Using Parallel Data
Domestic Conferences
- llm-jp-eval-mm: 日本語視覚言語モデルの自動評価基盤
- 日本の文化常識・日常生活知識理解のための視覚言語ベンチマーク MECHA-Ja の構築
- LLM-jp-3 VILA: 日本語マルチモーダルデータセット及び強力な日本語マルチモーダルモデルの構築
- 多言語での判例事実概要からの法的関係性のグラフ可視化
- Swallowコーパスv2: 教育的な日本語ウェブコーパスの構築
- 新聞記事からつくる時事と社会に強い日本語LLM
- 模倣学習による大規模言語モデルの指示チューニング
- 調理作業理解のための言語資源付き固定視点映像データセットの構築
- 視覚的文脈を利用した視覚言語モデルによる画像キャプション生成自動評価手法
- QuIC-360◦: 360◦ 画像に対するクエリ指向画像説明文生成のためのデータセット構築
- IMPARA: パラレルデータにおける修正の影響度に基づいた文法誤り訂正の自動評価法
Awards & Fellowships
- Young Scientist Award, ANLP (2025)
- Committee Special Awarded Paper, ANLP (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
-
Programming
-
Research Areas
-
Languages