433 citations · 433 across the 3 of their papers we have counts for
4 papers
Text-Vision Synergistic Token Caching: A Training-Free Framework for Efficient Vision-Language-Action Inference
Qianer Li, Chengjie Zhang, Jingwen Chen +3
Vision-Language-Action (VLA) models enable generalizable robotic control but remain computationally expensive. Token caching provides a training-free, plug-and-play acceleration al…
Can Single-View Mesh Reconstruction Generalize to Robot Camera Rotation?
Yu Zhan, Guangcheng Chen, Hanjing Ye +4
Single-view mesh reconstruction predicts object meshes and spatial layouts from a single observation, making it attractive for fast robot spatial reasoning and real-to-sim digital…
GCNGrasp-VP: Affordance-Guided View Planning for Efficient Task-Oriented Grasping
Zanjia Tong, Wenlong Dong, Chengjie Zhang +1
Task-oriented grasping performance degrades significantly when object views suffer from occlusions. Existing task-oriented grasping methods typically assume task-relevant regions a…
Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism
Zanjia Tong, Yuhang Chen, Zewei Xu +1
The loss function for bounding box regression (BBR) is essential to object detection. Its good definition will bring significant performance improvement to the model. Most existing…