Taisei Hanyu Source Confirmed

Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.

Researcher

University of Arkansas at Fayetteville

faculty

8 h-index 22 pubs 242 cited

Is this your profile? Verify and claim your profile

Biography and Research Information

OverviewAI-generated summary

Taisei Hanyu's research focuses on the intersection of computer vision, robotics, and machine learning, with a particular emphasis on 3D scene representation and manipulation. His recent work includes the development of "Open-Fusion," a system for real-time, open-vocabulary 3D mapping and queryable scene representation, and "SolarFormer," a multi-scale Transformer model designed for solar photovoltaic profiling. Hanyu has also explored "AerialFormer" for multi-resolution aerial image segmentation and investigated clutter-resistant vision-language-action models grounded in object-centric and geometric principles. His research extends to rethinking memory state progression in robotic manipulation from an object-centric perspective.

Hanyu collaborates with several researchers at the University of Arkansas at Fayetteville, including Chase Rainwater, Anh Tran, Anthony L. Gunderman, and Trong Thang Pham, with whom he has co-authored multiple publications. His work has resulted in 10 publications and 31 citations, with an h-index of 3, indicating recent and ongoing activity in his field.

Metrics

  • h-index: 8
  • Publications: 22
  • Citations: 242

Selected Publications

  • SolarFormer++: Multi-scale Transformer for Solar PV Profiling and Obstruction Localization for Degradation Mitigation (2025) DOI
  • AerialFormer: Multi-Resolution Transformer for Aerial Image Segmentation (2024) DOI

Collaborators

Researchers in the database who share publications

Similar Researchers

Based on overlapping research topics