Reveal-to-Revise: Explainable Bias-Aware Generative Modeling with Multimodal Attention

arXiv:2510.12957v3 Announce Type: replace-cross Abstract: We present an explainable, bias-aware generative framework that unifies cross-modal attention fusion, Grad-CAM++ attribution, and a Reveal-to-Revise feedback loop within a single training paradigm. The architecture couples a conditional attention WGAN GP with bias regularization and iterative local explanation feedback and is evaluated on Multimodal MNIST and Fashion MNIST for image generation and subgroup auditing, as well as a toxic/non