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

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.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-02-25

• Fields of study

  Computer Science

• Identifiers
  arXiv 2603.00155
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• ComUICoder: Component-based Reusable UI Code Generation for Complex Websites via Semantic Segmentation and Element-wise Feedback

  2026cited by this paper
• PosterVerse: A Full-Workflow Framework for Commercial-Grade Poster Generation with HTML-Based Scalable Typography

  2026cited by this paper
• AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache

  2025cited by this paper
• TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework

  2025cited by this paper
• Glyph: Scaling Context Windows via Visual-Text Compression

  2025cited by this paper
• Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers

  2025cited by this paper
• Text or Pixels? Evaluating Efficiency and Understanding of LLMs with Visual Text Inputs

  2025cited by this paper
• SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design

  2025cited by this paper
• P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark

  2025cited by this paper
• DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation

  2025cited by this paper
• POSTA: A Go-to Framework for Customized Artistic Poster Generation

  2025cited by this paper
• Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety

  2025cited by this paper
• Envisioning Future Interactive Web Development: Editing Webpage with Natural Language

  2025cited by this paper
• HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks

  2024cited by this paper
• Perplexed: Understanding When Large Language Models are Confused

  2024cited by this paper
• MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems

  2024cited by this paper
• SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities

  2024cited by this paper
• The Llama 3 Herd of Models

  2024cited by this paper
• LLaVA-OneVision: Easy Visual Task Transfer

  2024cited by this paper
• MinerU: An Open-Source Solution for Precise Document Content Extraction

  2024cited by this paper
• DynEx: Dynamic Code Synthesis with Structured Design Exploration for Accelerated Exploratory Programming

  2024cited by this paper
• Prompt2Poster: Automatically Artistic Chinese Poster Creation from Prompt Only

  2024cited by this paper
• Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models

  2024cited by this paper
• Empowering LLMs to Understand and Generate Complex Vector Graphics

  2024cited by this paper
• Lost in the Middle: How Language Models Use Long Contexts

  2023cited by this paper
• StarVector: Generating Scalable Vector Graphics Code from Images and Text

  2023cited by this paper
• AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation

  2023cited by this paper
• Llama 2: Open Foundation and Fine-Tuned Chat Models

  2023cited by this paper
• FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

  2022cited by this paper
• PosterBot: A System for Generating Posters of Scientific Papers with Neural Models

  2022cited by this paper
• Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Models

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• Normalization: A Preprocessing Stage

  2015cited by this paper
• PageRank beyond the Web

  2014cited by this paper
• Learning String-Edit Distance

  1996cited by this paper
• On finding lowest common ancestors in trees

  1973cited by this paper

• No citing papers are available for this paper.