CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs

Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu +7

Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sidestepping the scarcity of annotated 3D data. However, it produce…