CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs
It is shown that spatial coverage is associated with 3D reasoning performance and CoVeR, a deterministic, training-free selector that uses only token coordinates, with no learned signals is introduced, which outperforms prior SOTAs on all three 3D reasoning benchmarks and generalizes as a plug-and-play module tested ac...
Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu et al.
· 0 citations