SOURCE-LINKED INTELLIGENCE

(How) Do MLLMs Report Bistable Images Like Humans?

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Bistable images such as the duck-rabbit are classic stimuli in which one image supports multiple mutually incompatible interpretations, typically reported one at a time in humans. We ask whether multimodal large language models (MLLMs) show similar report behavior and what internal computations support it. Using the LLaVA family, we study two tractable dimensions: modulability, whether reports can be biased by bottom-up visual cues and top-down linguistic priors, and exclusivity, whether responses commit to a single interpretation. We test both on the canonical duck-rabbit and on synthetic Vis

Read original source ↗ Open in workspace

recordType

paper

region

Global