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

Researchers introduce EfficientPosterGen, an AI framework that automatically converts research papers into academic posters using semantic-aware retrieval and token compression techniques. The system addresses key limitations of existing multimodal language models by reducing token consumption while maintaining high-quality poster generation through innovative visual-based context compression and deterministic layout violation detection.

• →EfficientPosterGen uses semantic contribution graphs to identify and preserve the most important content from research papers.
• →The system converts text segments into images to reduce token usage while generating poster-ready bullet points.
• →A new deterministic algorithm detects layout violations without requiring additional AI models.
• →The framework demonstrates substantial improvements in token efficiency and layout reliability compared to existing approaches.
• →Open-source code is available, making the technology accessible for academic poster automation.