Wataru Shimaya

The University of Tokyo

Papers

1

Total Citations

3

H-Index

1

About

Wataru Shimaya is a researcher at the forefront of robotic perception and developmental learning, with a focus on enabling machines to understand the world through compositional and transformation-invariant representations. His key research areas include unsupervised learning of object-centric representations, Lie group theory for modeling continuous transformations, and the application of these principles to robotic vision and cognitive development. Shimaya’s major contribution is the development of the Shape-invariant Lie Group Transformer, a novel framework that disentangles patterns and transformations from image sequences without supervision—a critical step toward equipping robots with the human-like ability to parse the world into stable objects and dynamic changes. Though his most-cited paper currently holds 3 citations, its foundational nature and the growing interest in compositional learning suggest significant future impact. His work bridges advanced mathematics and practical robotics, offering a path toward more adaptable and intelligent autonomous systems. Shimaya’s research is particularly notable for its ambition to reverse-engineer the developmental learning processes observed in humans, making it highly relevant for students and researchers in cognitive robotics, computer vision, and representation learning.

Research Focus

Key Achievements

1
H-Index
1
Papers
3
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
Disentangling Patterns and Transformations from One Sequence of Images with Shape-invariant Lie Group Transformer
3 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: The University of Tokyo

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago