Scalable Minimal-Change Learning for Controllable Image Editing

Abstract:Image editing should change only the attributes specified by an instruction while preserving everything else, yet current methods often make unintended changes. We treat this minimal-change principle as an optimization objective for instruction-based editing. Latent L1 regularization is a poor proxy for output locality in modern nonlinear generators and often requires supervision unavailable at scale. We instead optimize edit outcomes with reinforcement learning. An agentic vision-language reward model audits each source image, instruction, and edited image for two failure types: unimplemented requested changes and unintended changes. A group-level rubric merges and verifies these issues to provide consistent rewards across candidate edits without per-instruction human annotations. On FLUX.1 Kontext-dev, ARRO raises average EditScore from 5.21 to 5.88 across MinEval, MagicBrush, AnyBench, and Emu-Edit. On 600 evaluation examples, it reduces off-target pixel change by 8.4% relative to the base editor. Reward and SFT controls, blinded human evaluations, and transfer to OmniGen2 provide complementary evidence. Code: this https URL

29 pages, 2 figures. Accepted at NeurIPS 2026. Revised version with additional off-target, reward and SFT control, human evaluation, and OmniGen2 transfer results; clarified related work and experimental scope

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

arXiv:2610.06021 [cs.CV]

(or arXiv:2610.06021v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2610.06021 arXiv-issued DOI via DataCite (pending registration)