Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing

13 March 2025

Papers citing "Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing"

1 / 1 papers shown

Title
Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark Enxin Song Wenhao Chai Weili Xu Jianwen Xie Yuxuan Liu Gaoang Wang 51 0 0 20 Apr 2025