SlideLab: Audience-Centered Scientific Slide Generation and Evaluation

SlideLab：以受众为中心的科学幻灯片生成与评估

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. 科学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研究工作，清晰地解释核心思想，并帮助听众跟上演示的节奏。

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. 我们提出了 SlideLab，这是一个无需训练的多智能体框架，用于从研究论文中生成科学演示文稿。SlideLab 首先规划演示叙事，然后利用负责内容规划、视觉生成、布局优化和基础验证的智能体，构建并迭代优化共享的幻灯片集。

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. 在一项盲测人类偏好研究中，在 77% 的论文案例中，SlideLab 的表现优于开源和商业系统，且其推理 Token 使用量比最强的开源基准模型减少了约 4 倍。

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. 我们还引入了 ConfArena，这是一个面向受众的评估框架，它模拟会议室环境并逐页评估演示文稿。ConfArena 的评估结果与人类系统排名相符，并能检测出演示中人为注入的问题，包括伪造的数据、质量下降的图表、丢失的幻灯片以及幻灯片顺序混乱等。