Kohei Uehara's Website


About me
I am Kohei Uehara (上原 康平), an Assistant Professor at Machine Intelligence Lab, the University of Tokyo. I'm also working as a part-time researcher at Accessibility Lab, Miraikan (The National Museum of Emerging Science and Innovation). My research interest focuses on machine learning across vision and language, Large Language Models (LLMs), Accessibility, and Human-Computer Interaction (HCI).
Current Positions

Education

Projects
Asagi - Japanese Vision&Language Model

Asagi is a Japanese Vision&Language Model. The architecture of Asagi is based on LLaVA, which consists of a vision encoder, a language decoder, and a 2-layer MLP for projecting visual features into the language feature space.
We used Japanese LLMs as the language decoder, and the vision encoder is based on the SigLIP model.
We synthesized a large-scale Japanese Vision & Language dataset, consisting of approximately 20 million image-text pairs.
The model is publicly available on the Hugging Face Model Hub.
Please check the project page for more details.

Asagi

Publications
Journal and International Conference
Domestic Conference
Others

Competitions

Lectures
Invited Talks

Work Experiences

Grants & Fellowships

Professional Activities

Links
Google Scholar Citations

last update: February 24, 2025