Vision language models prompted with a low vision participant's vision profile and one example response reach only 70% agreement with that participant's held-out image answers.
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
-
Not There Yet: Evaluating Vision Language Models in Simulating the Visual Perception of People with Low Vision
Vision language models prompted with a low vision participant's vision profile and one example response reach only 70% agreement with that participant's held-out image answers.