Scholar
Tsuyoshi Okita
Google Scholar ID: xBmTiOMAAAAJ
Kyushu Institute of Technology
Citations & Impact
Citations
526
H-index
11
i10-index
15
Publications
20
Co-authors
20
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published several papers in 2025, such as 'Multi-instance Learning as Downstream Task of Self-Supervised Learning-based Pre-trained Model', 'Thoughts on Objectives of Sparse and Hierarchical Masked Image Model', 'Brain Hematoma Marker Recognition Using Multitask Learning: SwinTransformer and Swin-Unet', etc.
Research Experience
- Engaged in the development of deep learning algorithms (especially adversarial generative networks and Transformers) at Okita Lab, also involving quantum machine learning. Research areas include medical images, videos, smartphone sensors, etc.
Education
- Associate Professor at Kyushu Institute of Technology, Department of Artificial Intelligence, Graduate School of Computer Science and Systems Engineering.
Background
- Research interests include LLM/generative AI, deep learning algorithm development, Transformers, generative AI models (diffusion model, GAN), self-supervised learning, causal relationship-related learning, and physics-related learning. Interested in NLP, image/video, 1D signals, green energy, etc.
Miscellany
- Welcomes students interested in joining Okita Lab for Master's or Doctoral studies. Applicants should provide a CV, score sheets, TOEIC/TOEFL scores, Bachelor's thesis (original language is fine), papers, recommendation letters, etc. Only those with experience in Machine Learning/Deep Learning are sought.
