[
    {
        "id": "osp-15932",
        "type": "article-journal",
        "title": "Scalable Minimal-Change Learning for Controllable Image Editing",
        "author": [
            {
                "family": "Chen",
                "given": "Shuo"
            },
            {
                "family": "Huang",
                "given": "Fengming"
            },
            {
                "family": "Yao",
                "given": "Yu"
            },
            {
                "family": "Gong",
                "given": "Mingming"
            },
            {
                "family": "Liu",
                "given": "Tongliang"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/scalable-minimal-change-learning-for-controllable-image-editing",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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: https://github.com/Showwwwwwwww/ARRO"
    }
]