Taisei Hanyu Data-verified
Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.
Researcher
faculty
Research Areas
Links
Biography and Research Information
OverviewAI-generated summary
Taisei Hanyu's research centers on the development and application of advanced artificial intelligence models, particularly transformers, for complex data analysis and scene understanding. He has co-authored publications on AerialFormer, a multi-resolution transformer designed for aerial image segmentation, and SolarFormer, a multi-scale transformer focused on solar photovoltaic profiling. Hanyu has also contributed to research on Open-Fusion, a system for real-time open-vocabulary 3D mapping and queryable scene representation, and the development of clutter-resistant vision-language-action models through object-centric and geometry grounding.
His work involves collaborations with researchers at the University of Arkansas at Fayetteville, including Chase Rainwater, Minh Quan Tran, Minh Trần, and Anh Tran, with whom he has multiple shared publications. Hanyu's research output to date includes 11 publications with an h-index of 3 and 33 total citations. His recent activity indicates ongoing engagement in the field, with publications extending into 2025.
Metrics
- h-index: 8
- Publications: 22
- Citations: 242
Selected Publications
-
Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective (2026)
-
SolarFormer++: Multi-scale Transformer for Solar PV Profiling and Obstruction Localization for Degradation Mitigation (2025)
-
AerialFormer: Multi-Resolution Transformer for Aerial Image Segmentation (2024)
Collaboration Network
Top Collaborators
- AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
- SolarFormer++: Multi-scale Transformer for Solar PV Profiling and Obstruction Localization for Degradation Mitigation
- SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation
- Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective
- Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding
Showing 5 of 6 shared publications
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
- AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
- SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation
- Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
- SolarFormer++: Multi-scale Transformer for Solar PV Profiling and Obstruction Localization for Degradation Mitigation
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
- SolarFormer++: Multi-scale Transformer for Solar PV Profiling and Obstruction Localization for Degradation Mitigation
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- SolarFormer++: Multi-scale Transformer for Solar PV Profiling and Obstruction Localization for Degradation Mitigation
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
- SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation
- Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective
- SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation
- Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding
- Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding
- SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation
- Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding
- Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding
- AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
- SolarFormer++: Multi-scale Transformer for Solar PV Profiling and Obstruction Localization for Degradation Mitigation
- AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
- SolarFormer++: Multi-scale Transformer for Solar PV Profiling and Obstruction Localization for Degradation Mitigation
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- SolarFormer: Multi-scale Transformer for Solar PV Profiling
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
Similar Researchers
Based on overlapping research topics