CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models 文章

ArXiv CS.CV2026-08-04PAPERen作者: Yu Chen, Xiaohong Li, Xiaole Wang, Jianjin Zhang, Jun Sun, Yafeng Deng
大语言模型
查看原文 →
关系图谱

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models · 相关人物

暂无数据