@inproceedings{kimhi-etal-2026-cares,
    title = "{CARES}: Context-Aware Resolution Selector for {VLM}s",
    author = "Kimhi, Moshe  and
      Shabtay, Nimrod  and
      Giryes, Raja  and
      Baskin, Chaim  and
      Schwartz, Eli",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.102/",
    pages = "2243--2256",
    ISBN = "979-8-89176-390-6",
    abstract = "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 \textit{CARES}{---}a \textbf{C}ontext-\textbf{A}ware \textbf{R}esolution \textbf{S}elector, a lightweight preprocessing module that, given an image{--}query pair, predicts the \textit{minimal} sufficient input resolution. CARES uses a compact VLM (350M) to extract features and predict when a target pretrained VLM{'}s response converges to its peak ability to answer correctly. Though trained as a discrete classifier over a set of optional resolutions, CARES interpolates continuous resolutions at inference for fine-grained control. Across five multimodal benchmarks spanning documents and natural images, as well as diverse target VLMs, CARES preserves task performance while reducing compute by up to 80{\%}."
}