Large vision-language models that appear to recognize visual illusions often answer fake-illusion questions from prior knowledge, not from actually seeing the images.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Large Vision-Language Models Distinguish between the Actual and Apparent Features of Illusions?
Large vision-language models that appear to recognize visual illusions often answer fake-illusion questions from prior knowledge, not from actually seeing the images.