Reproduce “Visual Orientalism in the AI Era: From West-East Binaries to English-Language Centrism” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhilong Zhao, Yindi Liu
The authors examine how image generators represent political sovereignty and cultural tradition. They generated 396 images for 12 countries and 11 concepts using GPT-Image-1, Midjourney, and NanoBanana, coding symbols. In an exploratory comparison, the USA and UK averaged 1.48 political-symbol instances per image, versus 0.22 for ten countries; this sample does not establish the cause or a rule for English-speaking countries.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.