CMU and Meta Release CoVeR, Training-Free Visual Token Pruning for 3D Reasoning

CMU and Meta introduced CoVeR, a training-free deterministic visual token pruning method for multi-view 3D reasoning. It discards about 92% of visual tokens while retaining 93.5% of performance, boosting multimodal model efficiency.

2026-09-09 ~ 2026-09-10 · 2 related posts

• CMU's CoVeR: Training-Free Token Pruning That Preserves Multi-View 3D Reasoning in VLMs — CarnegieMellonU · 2026-09-09
• CoVeR: Drop 92% of Visual Tokens, Keep 93.5% Performance in Multi-View 3D VLM Reasoning — Scobleizer · 2026-09-10