CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs
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 produces thousands of redundant visual tokens whose cost grows with every view. Existing visual token pruners fall into two families, each limited...
Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu et al.
· 0 citations