Year: 2026
Type: conference-paper
Abstract: Visual text compression is an emerging paradigm for rendering text as images for processing by vision-language models (VLMs), enabling higher information density per context token.However, the robustness of VLMs under dense, text-based visual inputs remains unevaluated.We introduce FICO, a benchmark designed to assess VLM robustness across seven controlled variants of visual fidelity and information density.FICO spans documents of 8k to 64k tokens and includes three tasks of increasing semantic granularity: optical character recognition (OCR), needle-ina-haystack (NIAH) retrieval, and visual question answering (VQA).Evaluating 13 generalpurpose VLMs and 3 OCR-specialized models reveals three consistent trends: performance drops sharply under increased density or reduced resolution; cross-task transfer between OCR, NIAH, and VQA is limited; and VQA is comparatively robust, suggesting that low-level details are lost before semantics.By exposing failure modes that remain invisible under conventional VLM evaluations, FICO establishes a rigorous testbed for visual text compression.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166890138