Hi! I'm Issa Sugiura

Research Interests

My research centers on multimodality, especially vision-language models (VLMs). I have led and contributed to projects across the full pipeline of VLM development, including:

• constructing large-scale training datasets (e.g., WAON, Jagle)
• developing reliable evaluation benchmarks (e.g., JAMMEval)
• building Japanese-centric VLMs (e.g., LLM-jp-4-VL 9B beta)

I like to learn by building things.

Hobby: I enjoy reading and traveling.

Education

• Apr 2026 – Mar 2029

  Doctoral Program (Expected)

  Course of Artificial Intelligence, Department of Computer Science, School of Computing

  Institute of Science Tokyo, Japan

• Apr 2024 – Mar 2026

  Master's Degree

  Course of Communications and Computer Engineering, Graduate School of Informatics

  Kyoto University, Japan

• Apr 2020 – Mar 2024

  Bachelor's Degree

  Software Science Course, Department of Information and Computer Sciences, School of Engineering Science

  Osaka University, Japan · GPA 3.57/4.00

Experience

• Apr 2026 – present

  Research Assistant @ Institute of Science Tokyo

  Research on VLMs.

• Dec 2024 – present

  Student Intern @ Sakana AI

  Research on evaluating real-world task performance of large language models, with a focus on the financial domain.

• Apr 2024 – present

  Research Assistant @ Research and Development Center for Large Language Models, National Institute of Informatics

  Research on training and evaluation of Japanese multimodal models.

• Feb 2024 – Apr 2024

  Student Intern @ LLM-jp, National Institute of Informatics

  Research on memorization in large language models.

• Mar 2022 – Apr 2024

  Technical Assistant @ Center for Quantum Information and Quantum Biology, Osaka University

  Research on quantum computation and quantum chemistry.

Publications

International Conference

• EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements

  Issa Sugiura, Takashi Ishida, Taro Makino, Chieko Tazuke, Takanori Nakagawa, Kosuke Nakago, David Ha

  ICLR 2026, Apr 2026 | Paper | Dataset | Code

• Developing Japanese CLIP Models Leveraging an Open-weight LLM for Large-scale Dataset Translation

  Issa Sugiura, Shuhei Kurita, Yusuke Oda, Daisuke Kawahara, Naoaki Okazaki

  NAACL Student Research Workshop 2025, Apr 2025 | Paper | Code | Model | Dataset

• Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model

  Keito Sasagawa, Koki Maeda, Issa Sugiura, Shuhei Kurita, Naoaki Okazaki, Daisuke Kawahara

  NAACL 2025 Demo Track, Apr 2025 | Paper

• A Comprehensive Analysis of Memorization in Large Language Models

  Hirokazu Kiyomaru*, Issa Sugiura*, Daisuke Kawahara, Sadao Kurohashi (*equal contribution)

  INLG 2024, Sep 2024 | Paper | Code

Journal

• Removing Mislabeled Data from Trained Models via Machine Unlearning

  Issa Sugiura, Shingo Okamura, Naoto Yanai

  IEICE Transactions on Information and Systems, Aug 2025 | Paper

Preprints

• HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers

  Issa Sugiura, Shuhei Kurita, Yusuke Oda, Naoaki Okazaki

  arXiv, Jun 2026 | Paper | Dataset | Code

• Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models

  Issa Sugiura, Keito Sasagawa, Keisuke Nakao, Koki Maeda, Ziqi Yin, Zhishen Yang, Shuhei Kurita, Yusuke Oda, Ryoko Tokuhisa, Daisuke Kawahara, Naoaki Okazaki

  arXiv, Apr 2026 | Paper | Dataset | Code

• JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation

  Issa Sugiura, Koki Maeda, Shuhei Kurita, Yusuke Oda, Daisuke Kawahara, Naoaki Okazaki

  arXiv, Apr 2026 | Paper | Dataset | Code

• WAON: Large-Scale and High-Quality Japanese Image-Text Pair Dataset for Vision-Language Models

  Issa Sugiura, Shuhei Kurita, Yusuke Oda, Daisuke Kawahara, Yasuo Okabe, Naoaki Okazaki

  arXiv, Oct 2025 | Paper | WAON | WAON-Bench | Code

• Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens

  Issa Sugiura, Shuhei Kurita, Yusuke Oda, Ryuichiro Higashinaka

  arXiv, Sep 2025 | Paper | Model | Code | Demo

• llm-jp-modernbert: A ModernBERT Model Trained on a Large-Scale Japanese Corpus with Long Context Length

  Issa Sugiura, Kouta Nakayama, Yusuke Oda

  arXiv, Apr 2025 | Paper | Model | Code

• LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

  LLM-jp (incl. Issa Sugiura; 80 authors, listed in alphabetical order)

  arXiv, Jul 2024 | Paper

Domestic Conference (Non-Refereed)

• Jagle: 視覚言語モデルのための大規模日本語マルチモーダル事後学習データセットの構築

  杉浦一瑳, 笹川慶人, 中尾圭佑, 前田航希, Yin Ziqi, Yang Zhishen, 栗田修平, 小田悠介, 徳久良子, 河原大輔, 岡崎直観

  JSAI 2026, 2026年6月 | Paper | Poster | Project Page

• Llama-Mimi: 意味・音響トークンを交互配置した音声言語モデル

  最優秀賞

  杉浦一瑳, 栗田修平, 小田悠介, 東中竜一郎

  NLP2026, 2026年3月 | Paper | Model | Code | Demo

• JAMMEval: 再アノテーションによる日本語VQA評価データセットの信頼性向上

  杉浦一瑳, 前田航希, 栗田修平, 小田悠介, 河原大輔, 岡崎直観

  NLP2026, 2026年3月 | Paper

• WAON: 視覚言語モデルのための大規模かつ高品質な日本語画像・テキスト対データセット

  委員特別賞

  杉浦一瑳, 栗田修平, 小田悠介, 河原大輔, 岡部寿男, 岡崎直観

  NLP2026, 2026年3月 | Paper | Project Page

• Common Crawlを用いた大規模音声音響データセットの構築

  浅井航平, 杉浦一瑳, 中田亘, 栗田修平, 高道慎之介, 小川哲司, 東中竜一郎

  日本音響学会 2025年秋季研究発表会, 2025年9月 | Code

• オープンLLMによる翻訳を活用した日本語CLIPの開発

  杉浦一瑳, 栗田修平, 小田悠介, 河原大輔, 岡崎直観

  NLP2025, 2025年3月 | Paper | Model | Dataset | Code

• ロススパイクの影響分析

  杉浦一瑳, 栗田修平, 小田悠介

  NLP2025, 2025年3月 | Paper

• llm-jp-eval-mm: 日本語視覚言語モデルの自動評価基盤

  若手奨励賞

  前田航希*, 杉浦一瑳*, 栗田修平, 小田悠介, 岡崎直観

  NLP2025, 2025年3月 | Paper | Code

• 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

  委員特別賞

  笹川慶人, 前田航希, 杉浦一瑳, 栗田修平, 岡崎直観, 河原大輔

  NLP2025, 2025年3月 | Paper

• 大規模言語モデルの事前学習ツールjax-llmの開発とinput-methodへの応用

  杉浦一瑳

  YANS2024, 2024年9月 | Draft Paper | Poster | Code (jax-llm) | Code (input-method)

• ミスラベルデータの忘却による学習済みモデルの汎化性能の向上手法の提案

  LINEヤフースポンサー賞

  杉浦一瑳, 岡村真吾, 山下恭佑, 矢内直人

  DEIM2024, 2024年2月 | Paper | Slide | Code

Models / Systems

• LLM-jp-4-VL 9B beta (2026)

  Developed a 9B Japanese vision-language model achieving competitive performance on Japanese benchmarks.

  Blog | Model

Certifications / Qualifications

• Oct 19, 2025 TOEIC L&R: L 420 + R 425 = 845
• Aug 2022 Security Camp organized by IPA (Information-technology Promotion Agency), Web Security Course