Delin Qu
Papers
1
Total Citations
15
H-Index
1
About
Delin Qu is a leading researcher at the intersection of computer vision, robotics, and embodied AI, with a core focus on spatial reasoning for visual-language-action models. His most influential work, "SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models" (2025), has already garnered 15 citations, reflecting its immediate impact on the field. Qu’s major contribution lies in pioneering a novel framework that re-discretizes pre-learned action grids to capture robot-specific spatial movements, enabling seamless adaptation across diverse real-world setups. This breakthrough addresses a critical challenge in robotics: bridging the gap between simulated training and real-world deployment. Through extensive evaluations, his work demonstrates exceptional in-distribution generalization and out-of-distribution adaptation, setting a new standard for robust, transferable robotic control. Qu’s research is pivotal for advancing embodied agents that can understand and act within complex, dynamic environments, making him a rising star in spatial AI and robot learning.
Research Focus
Key Achievements
Top Papers
- 1