CARES: Context-Aware Resolution Selector for VLMs 事件

CARES: Context-Aware Resolution Selector for VLMs arXiv:2510.19496v3 Announce Type: replace Abstract: Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks. This inflates visual tokens ofter to 97-99% of total tokens, resulting in high compute and latency, even when low-resolution images would suffice. We introduce \emph{CARES}-a \textbf{C}ontext-\textbf{A}ware \textbf{R}esolution \textbf{S}elector, a lightweight preprocessing