ChatPaper.aiChatPaper

DesignLab:通過迭代檢測與修正來設計簡報

DesignLab: Designing Slides Through Iterative Detection and Correction

July 23, 2025
作者: Jooyeol Yun, Heng Wang, Yotaro Shimose, Jaegul Choo, Shingo Takamatsu
cs.AI

摘要

設計高品質的簡報投影片對於非專業人士而言可能具有挑戰性,這主要是由於在眾多設計選項中進行選擇的複雜性所致。雖然有許多自動化工具能夠建議版面配置和色彩方案,但它們往往缺乏對自身輸出進行細化的能力,而這正是實際工作流程中的關鍵環節。我們提出了DesignLab,它將設計過程分為兩個角色:設計審查者,負責識別設計相關問題;以及設計貢獻者,負責修正這些問題。這種分解方式形成了一個迭代循環,審查者持續發現問題,貢獻者則進行修正,使得草稿在每次迭代中都能得到進一步打磨,從而達到原本無法企及的品質。我們針對這些角色對大型語言模型進行了微調,並通過引入受控的擾動來模擬中間草稿,使設計審查者能夠學習設計錯誤,而貢獻者則學習如何修正這些錯誤。我們的實驗表明,DesignLab通過擁抱設計的迭代本質,能夠產生精緻、專業的投影片,其表現優於現有的設計生成方法,包括一款商業工具。
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.
PDF471July 24, 2025