AutoPresent: Designing Structured Visuals from Scratch

TL;DR

AutoPresent introduces a new benchmark and a Llama-based model for automated slide generation from natural language, demonstrating that programmatic methods and iterative refinement improve slide quality.

Contribution

The paper presents SlidesBench, the first slide generation benchmark, and AutoPresent, a novel Llama-based model for creating structured visuals from instructions.

Findings

Programmatic methods outperform image generation in slide quality.

AutoPresent achieves results comparable to GPT-4o.

Iterative self-refinement enhances slide design quality.

Abstract

Designing structured visuals such as presentation slides is essential for communicative needs, necessitating both content creation and visual planning skills. In this work, we tackle the challenge of automated slide generation, where models produce slide presentations from natural language (NL) instructions. We first introduce the SlidesBench benchmark, the first benchmark for slide generation with 7k training and 585 testing examples derived from 310 slide decks across 10 domains. SlidesBench supports evaluations that are (i)reference-based to measure similarity to a target slide, and (ii)reference-free to measure the design quality of generated slides alone. We benchmark end-to-end image generation and program generation methods with a variety of models, and find that programmatic methods produce higher-quality slides in user-interactable formats. Built on the success of program generation, we create AutoPresent, an 8B Llama-based model trained on 7k pairs of instructions paired with code for slide generation, and achieve results comparable to the closed-source model GPT-4o. We further explore iterative design refinement where the model is tasked to self-refine its own output, and we found that this process improves the slide's quality. We hope that our work will provide a basis for future work on generating structured visuals.