Shan Gao

This work proposes Caption-once, Frames-onDemand (CFD), a budget-aware edge-cloud agentic framework that turns visual access into a first-class, query-conditioned cost, capping per-query frame consumption regardless of video length.

GrabVG achieves a remarkable 67.31% accuracy in UAV visual grounding, outperforming current methods by over 10 percentage points through innovative graph-attentive techniques.

SurfSVR transforms 2D surface information into robust 3D structures, eliminating common artifacts and achieving unprecedented reconstruction quality.