Follow-Your-Preference++: Rethinking Preference Alignment for Image Inpainting 事件

Follow-Your-Preference++: Rethinking Preference Alignment for Image Inpainting arXiv:2606.03216v1 Announce Type: new Abstract: We study preference alignment for image inpainting. Rather than proposing yet another method, we revisit the problem from first principles and reassess its core challenges. We adopt the widely used direct preference optimization framework and construct preference training data with publicly available reward models. Our empirical study spans nine reward models, two bench