Yushu Li

Exploiting Vision Language Model for Training-Free 3D Point Cloud Understanding via Improved Graph Score Propagation.

GSP++ is presented, a graph-based inference framework that exploits the manifold structure of test-time point clouds to refine VLM scores without additional training, and introduces a self-training strategy that selects high-confidence positive and negative samples and assigns them calibrated pseudo scores to further stabilize propagation.