arXiv cs.CV
· Papers
Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
arXiv:2604.11240v2 Announce Type: replace Abstract: Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discarding less informative visual tokens while preserving performance. However, existing methods typically rely on individua