一作ACL 2026Findings· Findings of ACL
M o P rune: Scene-Guided Motion-Aware Token Pruning for Efficient Video Large Language Models
Wenhao Hong · Ziyang Wang · Yixin Zhang · Zilei Wang
摘要
Video Large Language Models (VideoLLMs) struggle with the heavy computational cost of long or high-resolution videos due to massive visual token counts and the quadratic complexity of attention. Prior pruning approaches mainly rely on token importance or similarity, while largely overlooking vide...