Visual Persuasion: What Influences Decisions of Vision-Language Models? 事件

Visual Persuasion: What Influences Decisions of Vision-Language Models? arXiv:2602.15278v2 Announce Type: replace Abstract: The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet, we know little about the structure of their visual preferences. We introduce a framework for studying this by placing VLMs in controll