Evaluation-Verification Reward for Consistent Multi-Reference Image Editing

arXiv:2607.29025v1 Announce Type: new Abstract: While recent image editing models have made rapid progress, multi-reference editing remains challenging, particularly in maintaining visual consistency across references and ensuring overall visual harmony. Reinforcement learning has proven highly effective for text-to-image generation and single-image editing, but its extension to multi-reference editing is hindered by the absence of suitable reward models that capture multi-image relational const...