Preprint
Sep 2026
QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning
QCPruner fuses two cross-modal cues into utility and applies it to both visual targets and candidate representatives within visual-affinity-based coverage, which achieves the highest average relative performance among evaluated complete-system pruning methods at every reported token budget.
Sheng-Li He, Yong-Chao Liang, Rou-Meng He et al.
· 2 citations