A combination of illusion-specific image transformations, anti-illusion prompts, and majority voting lets VLMs reach 90.48% accuracy on a 630-image illusion benchmark without any model training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models
A combination of illusion-specific image transformations, anti-illusion prompts, and majority voting lets VLMs reach 90.48% accuracy on a 630-image illusion benchmark without any model training.