SlideLab：以受众为中心的科技幻灯片生成与评估
SlideLab: Audience-Centered Scientific Slide Generation and Evaluation
浏览论文内容
中文总结 AI 辅助
SlideLab是一个无需训练的多智能体框架，通过规划叙事和迭代优化生成科技演示，在盲人偏好研究中以更少推理令牌优于现有系统，并引入ConfArena逐张评估演示质量。
中文摘要 AI 辅助
科技演示不仅仅是研究论文的摘要。它们需要以连贯的顺序呈现工作，清晰地解释主要思想，并帮助受众跟上演示。我们提出了SlideLab，一个无需训练的多智能体框架，用于从研究论文生成科技演示。SlideLab首先规划演示叙事，然后使用内容规划、视觉生成、布局优化和接地验证的智能体构建并迭代优化共享幻灯片组。在一项盲人偏好研究中，SlideLab在77%的论文上优于开源和商业系统，同时使用的推理令牌大约比最强的开源基线少4倍。我们还引入了ConfArena，一个以受众为导向的评估框架，模拟会议室并逐张评估演示。ConfArena与人类系统排名一致，并检测注入的演示问题，包括伪造数字、降级图形、丢失幻灯片和打乱幻灯片顺序。
英文摘要
Scientific presentations are more than summaries of research papers. They need to present the work in a coherent sequence, explain the main ideas clearly, and help the audience follow the presentation. We present SlideLab, a training-free multi-agent framework for generating scientific presentations from research papers. SlideLab first plans the presentation narrative, then builds and iteratively refines a shared slide deck using agents for content planning, visual generation, layout refinement, and grounding verification. In a blind human preference study, SlideLab was preferred over both open-source and commercial systems on 77% of papers while using roughly 4 times fewer inference tokens than the strongest open-source baseline. We also introduce ConfArena, an audience-oriented evaluation framework that simulates a conference room and assesses presentations slide by slide. ConfArena matches human system rankings and detects injected presentation problems, including falsified numbers, degraded figures, dropped slides, and shuffled slide order.
发表机构
- INSAIT, Sofia University “St. Kliment Ohridski”（INSAIT，索非亚圣克莱门特奥赫里德大学）
机构由 AI 辅助整理，请以论文原文为准。
