Problem
Research questions and friction points this paper is trying to address.
scientific slide generation
audience-centered presentation
slide evaluation
research paper to slides
SlideLab: Audience-Centered Scientific Slide Generation and Evaluation
🤖 AI Summary
This study addresses the narrative fragmentation and inefficient communication of core messages in scientific presentations by proposing a training-free multi-agent framework. Through iterative collaboration encompassing content planning, visual generation, layout optimization, and fact-checking, the framework constructs audience-centric scientific slides. Furthermore, it introduces ConfArena, a novel evaluation framework that simulates conference scenarios to perform page-level detection of defects such as data fabrication and image degradation, achieving automated assessment highly aligned with human preferences. Blind evaluations demonstrate that the proposed method outperforms mainstream open-source and commercial systems with a 77% preference rate, reduces inference token consumption by approximately fourfold, and accurately identifies diverse presentation defects.
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-agent framework
Training-free
Slide generation
Audience-centered evaluation
ConfArena
🔎 Similar Papers
No similar papers found.
