Profile
Hello! I am Takuya Matsuyama, a second-year master's student at the Graduate School of Frontier Biosciences at Osaka University. I am currently affiliated with the Perception and Cognitive Neuroscience Laboratory (Nishimoto Lab), where I am working on elucidating brain functions using Vision, Audio, and Language AI.
Tags
All Audio AI Computational Neuroscience Computer Vision Generative AI Image AI Large Language Model (LLM) Music AI Video AIPapers
Preprint
Tag: Large Language Model (LLM), Generative AI, Computer Vision, Image AI, and Computational Neuroscience Takuya Matsuyama, Shinji Nishimoto†, Yu Takagi†
LaVCa: LLM-assisted Visual Cortex Captioning
arxiv, 2025
[Project page]
Publication
Tag: Large Language Model (LLM), Generative AI, and Computational Neuroscience Yuko Nakagi*, Takuya Matsuyama*, Naoko Koide-Majima, Hiroto Yamaguchi, Rieko Kubo, Shinji Nishimoto†‡, Yu Takagi†‡
Unveiling Multi-level and Multi-modal Semantic Representations in the Human Brain using Large Language Models
EMNLP2024
[Project page]
Preprint
Tag: Image AI, Computer Vision, and Computational Neuroscience Takuya Matsuyama*, Kota S Sasaki, Shinji Nishimoto*
Applicability of scaling laws to vision encoding models (Open Access)
arxiv, 2023
[Code]
Preprint
Tag: Generative AI, Music AI, Audio AI, and Computational Neuroscience Timo I. Denk*†, Yu Takagi*†, Takuya Matsuyama, Andrea Agostinelli, Tomoya Nakai, Christian Frank, Shinji Nishimoto
Brain2Music: Reconstructing Music from Human Brain Activity (Open Access)
arxiv, 2023
[Project page]
Conferences
Conference (not peer reviewed)
Tag: Video AI, Computer Vision, and Computational Neuroscience Takuya Matsuyama, Kota S Sasaki, Shinji Nishimoto
The first-person perspective contributes to the acquisition of visual representation in the human brain: Analysis using Deep Neural Networks
Neuro2023, Sendai, Japan, August 2023
Contests
Machine Learning Contest @ Kaggle
Tag: Large Language Model (LLM) LLM Prompt Recovery
Ranked 85th out of 2175 teams.🥈
Machine Learning Contest @ CodaLab
Tag: Image AI, Computer Vision, and Computational Neuroscience Alogonauts Project 2023 Challenge
Ranked 8th out of 107 teams.
Experience
Research Internship
Tag: Generative AI, Computer Vision, and Computational Neuroscience 2023 August - 2023 September (1 month)
NTT R&D
EEG-based Image Generation using Generative AI
Posts tagged "Audio AI"
Preprint
Tag: Generative AI, Music AI, Audio AI, and Computational Neuroscience Timo I. Denk*†, Yu Takagi*†, Takuya Matsuyama, Andrea Agostinelli, Tomoya Nakai, Christian Frank, Shinji Nishimoto
Brain2Music: Reconstructing Music from Human Brain Activity (Open Access)
arxiv, 2023
[Project page]
Posts tagged "Computational Neuroscience"
Preprint
Tag: Large Language Model (LLM), Generative AI, Computer Vision, Image AI, and Computational Neuroscience Takuya Matsuyama, Shinji Nishimoto†, Yu Takagi†
LaVCa: LLM-assisted Visual Cortex Captioning
arxiv, 2025
[Project page]
Publication
Tag: Large Language Model (LLM), Generative AI, and Computational Neuroscience Yuko Nakagi*, Takuya Matsuyama*, Naoko Koide-Majima, Hiroto Yamaguchi, Rieko Kubo, Shinji Nishimoto†‡, Yu Takagi†‡
Unveiling Multi-level and Multi-modal Semantic Representations in the Human Brain using Large Language Models
EMNLP2024
[Project page]
Research Internship
Tag: Generative AI, Computer Vision, and Computational Neuroscience 2023 August - 2023 September (1 month)
NTT R&D
EEG-based Image Generation using Generative AI
Conference (not peer reviewed)
Tag: Video AI, Computer Vision, and Computational Neuroscience Takuya Matsuyama, Kota S Sasaki, Shinji Nishimoto
The first-person perspective contributes to the acquisition of visual representation in the human brain: Analysis using Deep Neural Networks
Neuro2023, Sendai, Japan, August 2023
Preprint
Tag: Image AI, Computer Vision, and Computational Neuroscience Takuya Matsuyama*, Kota S Sasaki, Shinji Nishimoto*
Applicability of scaling laws to vision encoding models (Open Access)
arxiv, 2023
[Code]
Machine Learning Contest @ CodaLab
Tag: Image AI, Computer Vision, and Computational Neuroscience Alogonauts Project 2023 Challenge
Ranked 8th out of 107 teams.
Preprint
Tag: Generative AI, Music AI, Audio AI, and Computational Neuroscience Timo I. Denk*†, Yu Takagi*†, Takuya Matsuyama, Andrea Agostinelli, Tomoya Nakai, Christian Frank, Shinji Nishimoto
Brain2Music: Reconstructing Music from Human Brain Activity (Open Access)
arxiv, 2023
[Project page]
Posts tagged "Computer Vision"
Preprint
Tag: Large Language Model (LLM), Generative AI, Computer Vision, Image AI, and Computational Neuroscience Takuya Matsuyama, Shinji Nishimoto†, Yu Takagi†
LaVCa: LLM-assisted Visual Cortex Captioning
arxiv, 2025
[Project page]
Research Internship
Tag: Generative AI, Computer Vision, and Computational Neuroscience 2023 August - 2023 September (1 month)
NTT R&D
EEG-based Image Generation using Generative AI
Conference (not peer reviewed)
Tag: Video AI, Computer Vision, and Computational Neuroscience Takuya Matsuyama, Kota S Sasaki, Shinji Nishimoto
The first-person perspective contributes to the acquisition of visual representation in the human brain: Analysis using Deep Neural Networks
Neuro2023, Sendai, Japan, August 2023
Preprint
Tag: Image AI, Computer Vision, and Computational Neuroscience Takuya Matsuyama*, Kota S Sasaki, Shinji Nishimoto*
Applicability of scaling laws to vision encoding models (Open Access)
arxiv, 2023
[Code]
Machine Learning Contest @ CodaLab
Tag: Image AI, Computer Vision, and Computational Neuroscience Alogonauts Project 2023 Challenge
Ranked 8th out of 107 teams.
Posts tagged "Generative AI"
Preprint
Tag: Large Language Model (LLM), Generative AI, Computer Vision, Image AI, and Computational Neuroscience Takuya Matsuyama, Shinji Nishimoto†, Yu Takagi†
LaVCa: LLM-assisted Visual Cortex Captioning
arxiv, 2025
[Project page]
Publication
Tag: Large Language Model (LLM), Generative AI, and Computational Neuroscience Yuko Nakagi*, Takuya Matsuyama*, Naoko Koide-Majima, Hiroto Yamaguchi, Rieko Kubo, Shinji Nishimoto†‡, Yu Takagi†‡
Unveiling Multi-level and Multi-modal Semantic Representations in the Human Brain using Large Language Models
EMNLP2024
[Project page]
Research Internship
Tag: Generative AI, Computer Vision, and Computational Neuroscience 2023 August - 2023 September (1 month)
NTT R&D
EEG-based Image Generation using Generative AI
Preprint
Tag: Generative AI, Music AI, Audio AI, and Computational Neuroscience Timo I. Denk*†, Yu Takagi*†, Takuya Matsuyama, Andrea Agostinelli, Tomoya Nakai, Christian Frank, Shinji Nishimoto
Brain2Music: Reconstructing Music from Human Brain Activity (Open Access)
arxiv, 2023
[Project page]
Posts tagged "Image AI"
Preprint
Tag: Large Language Model (LLM), Generative AI, Computer Vision, Image AI, and Computational Neuroscience Takuya Matsuyama, Shinji Nishimoto†, Yu Takagi†
LaVCa: LLM-assisted Visual Cortex Captioning
arxiv, 2025
[Project page]
Preprint
Tag: Image AI, Computer Vision, and Computational Neuroscience Takuya Matsuyama*, Kota S Sasaki, Shinji Nishimoto*
Applicability of scaling laws to vision encoding models (Open Access)
arxiv, 2023
[Code]
Machine Learning Contest @ CodaLab
Tag: Image AI, Computer Vision, and Computational Neuroscience Alogonauts Project 2023 Challenge
Ranked 8th out of 107 teams.
Posts tagged "Large Language Model (LLM)"
Preprint
Tag: Large Language Model (LLM), Generative AI, Computer Vision, Image AI, and Computational Neuroscience Takuya Matsuyama, Shinji Nishimoto†, Yu Takagi†
LaVCa: LLM-assisted Visual Cortex Captioning
arxiv, 2025
[Project page]
Machine Learning Contest @ Kaggle
Tag: Large Language Model (LLM) LLM Prompt Recovery
Ranked 85th out of 2175 teams.🥈
Publication
Tag: Large Language Model (LLM), Generative AI, and Computational Neuroscience Yuko Nakagi*, Takuya Matsuyama*, Naoko Koide-Majima, Hiroto Yamaguchi, Rieko Kubo, Shinji Nishimoto†‡, Yu Takagi†‡
Unveiling Multi-level and Multi-modal Semantic Representations in the Human Brain using Large Language Models
EMNLP2024
[Project page]
Posts tagged "Music AI"
Preprint
Tag: Generative AI, Music AI, Audio AI, and Computational Neuroscience Timo I. Denk*†, Yu Takagi*†, Takuya Matsuyama, Andrea Agostinelli, Tomoya Nakai, Christian Frank, Shinji Nishimoto
Brain2Music: Reconstructing Music from Human Brain Activity (Open Access)
arxiv, 2023
[Project page]
Posts tagged "Video AI"
Conference (not peer reviewed)
Tag: Video AI, Computer Vision, and Computational Neuroscience Takuya Matsuyama, Kota S Sasaki, Shinji Nishimoto
The first-person perspective contributes to the acquisition of visual representation in the human brain: Analysis using Deep Neural Networks
Neuro2023, Sendai, Japan, August 2023
Education
2023 April -
Osaka University
Graduate School of Frontier Biosciences
Supervisor:
Shinji Nishimoto
2019 April - 2023 March
Osaka University
Division of Biophysical Engineering,
Department of Systems Science,
School of Engineering Science,
Supervisor:
Shinji Nishimoto
Skills
Programing Languages
Python, C, MATLAB, R, HTML, CSS
Tools
VS Code, git, Docker, Singularity