SlideTailor: Personalized Presentation Slide Generation for Scientific Papers

TL;DR

SlideTailor is a novel system that personalizes scientific presentation slides based on minimal user input, effectively aligning content and style through a behavior-inspired framework and a new benchmark dataset.

Contribution

We introduce a new task for personalized slide generation conditioned on implicit user preferences, along with a novel framework and a benchmark dataset for evaluation.

Findings

Effective personalization of slides using minimal inputs

Improved slide quality and alignment with user preferences

Versatile application to video presentations and oral narration

Abstract

Automatic presentation slide generation can greatly streamline content creation. However, since preferences of each user may vary, existing under-specified formulations often lead to suboptimal results that fail to align with individual user needs. We introduce a novel task that conditions paper-to-slides generation on user-specified preferences. We propose a human behavior-inspired agentic framework, SlideTailor, that progressively generates editable slides in a user-aligned manner. Instead of requiring users to write their preferences in detailed textual form, our system only asks for a paper-slides example pair and a visual template - natural and easy-to-provide artifacts that implicitly encode rich user preferences across content and visual style. Despite the implicit and unlabeled nature of these inputs, our framework effectively distills and generalizes the preferences to guide customized slide generation. We also introduce a novel chain-of-speech mechanism to align slide content with planned oral narration. Such a design significantly enhances the quality of generated slides and enables downstream applications like video presentations. To support this new task, we construct a benchmark dataset that captures diverse user preferences, with carefully designed interpretable metrics for robust evaluation. Extensive experiments demonstrate the effectiveness of our framework.