HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing 事件

HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing arXiv:2605.24687v1 Announce Type: new Abstract: Text-to-Image (T2I) models have made significant strides in visual realism and semantic consistency, yet they often perpetuate and amplify societal biases. Existing evaluation methods typically address only single-dimensional biases, lacking perspectives to uncover model biases at social-related deeper semantic levels. We introduce HoloFair, a comprehensive benchmark framework for m