FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models

30 December 2024

Papers citing "FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"

1 / 1 papers shown

Title
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration Jintao Zhang Jia Wei Pengle Zhang Jun-Jie Zhu Jun Zhu Jianfei Chen VLM MQ 131 31 0 03 Oct 2024