GenExam is the first benchmark for multidisciplinary text-to-image exams, with 1,000 samples, a four-level taxonomy, ground-truth images, and fine-grained scoring to test integrated understanding, reasoning, and generation in AI models.
checking the overall structure of the image) should be small, such as 0.1 or 0.2
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
-
GenExam: A Multidisciplinary Text-to-Image Exam
GenExam is the first benchmark for multidisciplinary text-to-image exams, with 1,000 samples, a four-level taxonomy, ground-truth images, and fine-grained scoring to test integrated understanding, reasoning, and generation in AI models.