# CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs > Source: > Published: 2026-09-09 06:30:24+00:00 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 fam