2 papers
cs.RO2026
GraphPoint: Semantic Entity Graphs and Point Trajectories for Compositional Robot Manipulation
Kang Luo, Hesheng Wang
Robot manipulation policies often struggle to generalize beyond their demonstrations, even when new instructions involve familiar objects and behaviors. When language and scenes ar…
cs.CV2026
Fusion4CA: Boosting 3D Object Detection via Comprehensive Image Exploitation
Kang Luo, Xin Chen, Yangyi Xiao +1
Nowadays, an increasing number of works fuse LiDAR and RGB data in the bird's-eye view (BEV) space for 3D object detection in autonomous driving systems. However, existing methods…