Yixin Wan

Examining gender bias in T2I models through the Paired Stereotype Test.

Examining biases in image generation and their societal impacts.

This study analyzes language biases affecting gender and race in various texts.

Enhancing user engagement in large vision-language models through proactive communication.

This study explores the trade-off between diversity and factual accuracy in AI-generated images.

A fresh approach enhances image accuracy from text descriptions using attention techniques.