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

2026-02-25

AI Summary

This work addresses key challenges in automatic academic poster generation with multimodal large language models, including low input information density, high token consumption, and unreliable layout validation. To overcome these limitations, the authors propose EfficientPosterGen, an end-to-end framework that significantly reduces input redundancy through semantic contribution map–driven key information retrieval and an image rendering–based text token compression mechanism. Furthermore, the method introduces a model-free color gradient analysis technique for deterministic detection of layout violations, eliminating the need for auxiliary models. By substantially lowering token usage and enhancing generation efficiency without compromising content quality or layout compliance, EfficientPosterGen offers a scalable and effective solution for automated academic poster creation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• automated academic poster generation
• token efficiency
• layout verification
• information density
• multimodal large language models

Innovation

• Semantic-aware Retrieval
• Token Compression
• Multimodal Generation
• Layout Violation Detection
• Academic Poster Generation