{"ID":2886912,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02374","arxiv_id":"2508.02374","title":"Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation","abstract":"Layout generation plays a crucial role in enhancing both user experience and design efficiency. However, current approaches suffer from task-specific generation capabilities and perceptually misaligned evaluation metrics, leading to limited applicability and ineffective measurement. In this paper, we propose \\textit{Uni-Layout}, a novel framework that achieves unified generation, human-mimicking evaluation and alignment between the two. For universal generation, we incorporate various layout tasks into a single taxonomy and develop a unified generator that handles background or element contents constrained tasks via natural language prompts. To introduce human feedback for the effective evaluation of layouts, we build \\textit{Layout-HF100k}, the first large-scale human feedback dataset with 100,000 expertly annotated layouts. Based on \\textit{Layout-HF100k}, we introduce a human-mimicking evaluator that integrates visual and geometric information, employing a Chain-of-Thought mechanism to conduct qualitative assessments alongside a confidence estimation module to yield quantitative measurements. For better alignment between the generator and the evaluator, we integrate them into a cohesive system by adopting Dynamic-Margin Preference Optimization (DMPO), which dynamically adjusts margins based on preference strength to better align with human judgments. Extensive experiments show that \\textit{Uni-Layout} significantly outperforms both task-specific and general-purpose methods. Our code is publicly available at https://github.com/JD-GenX/Uni-Layout.","short_abstract":"Layout generation plays a crucial role in enhancing both user experience and design efficiency. However, current approaches suffer from task-specific generation capabilities and perceptually misaligned evaluation metrics, leading to limited applicability and ineffective measurement. In this paper, we propose \\textit{Un...","url_abs":"https://arxiv.org/abs/2508.02374","url_pdf":"https://arxiv.org/pdf/2508.02374v1","authors":"[\"Shuo Lu\",\"Yanyin Chen\",\"Wei Feng\",\"Jiahao Fan\",\"Fengheng Li\",\"Zheng Zhang\",\"Jingjing Lv\",\"Junjie Shen\",\"Ching Law\",\"Jian Liang\"]","published":"2025-08-04T13:02:23Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.IR\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":611378,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2886912,"paper_url":"https://arxiv.org/abs/2508.02374","paper_title":"Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation","repo_url":"https://github.com/JD-GenX/Uni-Layout","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}