EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection

TL;DR

EfficientPosterGen is an innovative framework that enhances automated academic poster creation by improving token efficiency, layout reliability, and content preservation through semantic-aware retrieval, visual context compression, and deterministic violation detection.

Contribution

It introduces three novel techniques—SKIR, VCC, and ALVD—that collectively address key limitations in existing multimodal poster generation methods.

Findings

Significantly reduces token consumption in poster generation.

Improves layout verification accuracy without auxiliary models.

Maintains high-quality poster outputs with better information density.

Abstract

Automated academic poster generation aims to distill lengthy research papers into concise, visually coherent presentations. Existing Multimodal Large Language Models (MLLMs) based approaches, however, suffer from three critical limitations: low information density in full-paper inputs, excessive token consumption, and unreliable layout verification. We present EfficientPosterGen, an end-to-end framework that addresses these challenges through semantic-aware retrieval and token-efficient multimodal generation. EfficientPosterGen introduces three core innovations: (1) Semantic-aware Key Information Retrieval (SKIR), which constructs a semantic contribution graph to model inter-segment relationships and selectively preserves important content; (2) Visual-based Context Compression (VCC), which renders selected text segments into images to shift textual information into the visual modality, significantly reducing token usage while generating poster-ready bullet points; and (3) Agentless Layout Violation Detection (ALVD), a deterministic color-gradient-based algorithm that reliably detects content overflow and spatial sparsity without auxiliary MLLMs. Extensive experiments demonstrate that EfficientPosterGen achieves substantial improvements in token efficiency and layout reliability while maintaining high poster quality, offering a scalable solution for automated academic poster generation. Our code is available at https://github.com/vinsontang1/EfficientPosterGen-Code.