让AI分角色迭代优化幻灯片设计，生成更专业的演示稿。
DesignLab: Designing Slides Through Iterative Detection and Correction
- 拆分评审与修正角色，形成持续改进的循环流程
- 相比现有方法，生成幻灯片质量显著提升，超越商用工具
- 适合非专业人士快速制作专业级演示文稿
非专业人士在制作高质量幻灯片时面临设计选择复杂的问题。尽管已有多种自动化工具可推荐版式和配色，但普遍缺乏自我优化能力，而这正是真实工作流中的关键环节。我们提出 DesignLab，将设计过程分解为‘设计评审员’（识别问题）和‘设计贡献者’（修正问题）两个角色。该机制支持迭代循环：评审员持续检测设计缺陷，贡献者相应修正，使草稿逐轮精炼，最终达到原方法无法企及的质量。通过微调大语言模型实现两角色，并引入可控扰动模拟中间版本，使评审员学会识别设计错误，贡献者学会修复方法。实验表明，DesignLab 在多项指标上优于现有生成方法，包括商用工具，其迭代特性能产出更精致、专业的幻灯片。
原文摘要 · Abstract (English)
Designing high-quality presentation slides can be challenging for non-experts due to the complexity involved in navigating various design choices. Numerous automated tools can suggest layouts and color schemes, yet often lack the ability to refine their own output, which is a key aspect in real-world workflows. We propose DesignLab, which separates the design process into two roles, the design reviewer, who identifies design-related issues, and the design contributor who corrects them. This decomposition enables an iterative loop where the reviewer continuously detects issues and the contributor corrects them, allowing a draft to be further polished with each iteration, reaching qualities that were unattainable. We fine-tune large language models for these roles and simulate intermediate drafts by introducing controlled perturbations, enabling the design reviewer learn design errors and the contributor learn how to fix them. Our experiments show that DesignLab outperforms existing design-generation methods, including a commercial tool, by embracing the iterative nature of designing which can result in polished, professional slides.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。