GLEaN distills text-to-image model biases into single median-pixel portrait composites that communicate associations like skin tone and emotion as effectively as data tables but faster.
Abuzuraiq and Philippe Pasquier
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension
GLEaN distills text-to-image model biases into single median-pixel portrait composites that communicate associations like skin tone and emotion as effectively as data tables but faster.