{"ID":5937867,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T02:28:54.689456049Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04612","arxiv_id":"2607.04612","title":"StructuredEdit: Constraint-Aware Graphic Design Editing via Differentiable Parameter Propagation","abstract":"Graphic design editing requires precise manipulation of typography, layout, and visual hierarchy under strict design constraints. Following the introduction of large language models, organizations have increasingly promoted vision-language models to enhance productivity. However, current models operate on pixels and achieve only 52% constraint satisfaction on structured design edits, thereby limiting their reliability for professional workflows. We present StructuredEdit, a pipeline that reframes design editing as parameter manipulation rather than pixel generation. Our core technical contribution is Differentiable Parameter Propagation (DPP), a training method that embeds hard design constraints into vision-language model fine-tuning by backpropagating pixel-level constraint violations through a lightweight differentiable rasterizer. A hybrid candidate-and-filter pipeline produces 125k validated edit triplets. The resulting system reaches 89% constraint satisfaction versus 52% for GPT-4V, 0.82 matched-element Intersection over Union, and 76% top-1 font accuracy over the 100 most-frequent design typefaces. In a user study (N=35), editing time drops 33% and correction iterations drop 44% relative to a GPT-4V baseline.","short_abstract":"Graphic design editing requires precise manipulation of typography, layout, and visual hierarchy under strict design constraints. Following the introduction of large language models, organizations have increasingly promoted vision-language models to enhance productivity. However, current models operate on pixels and ac...","url_abs":"https://arxiv.org/abs/2607.04612","url_pdf":"https://arxiv.org/pdf/2607.04612v1","authors":"[\"Veeramanohar Avudaiappan\",\"Ritwik Murali\"]","published":"2026-07-06T02:37:22Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.CV\"]","methods":"[\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}