一作ACL 2026Poster· Natural Language Processing
CARES : Context-Aware Resolution Selector for VLM s
Moshe Kimhi · Nimrod Shabtay · Raja Giryes · Chaim Baskin · Eli Schwartz
摘要
Large vision–language models (VLMs) commonly process images at native or high resolution to remain effective across tasks. This inflates visual tokens to 97-99% of total tokens, resulting in high compute and latency, even when low-resolution images would suffice. We introduce CARES —a C ontext- A...