P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark

Tao Sun, Enhao Pan, Zhengkai Yang, Kaixin Sui, Jiajun Shi, Xianfu Cheng, Tongliang Li, Ge Zhang, Wenhao Huang, Jian Yang, Zhoujun Li

Keywords: Poster Generate, LLM-as-a-Judge, Multi Agent

TL;DR: We present P2P, a LLM-based multi-agent framework that turns research papers into polished HTML posters, backed by a 30k-example instruction dataset and establish a fine-grained benchmark for rigorous evaluation.

Abstract:

Academic posters are vital for scholarly communication, yet their manual creation is time-consuming. However, automated academic poster generation faces significant challenges in preserving intricate scientific details and achieving effective visual-textual integration.
Existing approaches often struggle with semantic richness, structural nuances, and lack standardized benchmarks for evaluating generated academic posters comprehensively.
To address these limitations, we introduce P2P, the first flexible, LLM-based multi-agent framework that generates high-quality, HTML-rendered academic posters directly from research papers. P2P employs three specialized agents—for visual element processing, content generation, and final poster assembly—each integrated with dedicated checker modules to enable iterative refinement and ensure output quality.
To foster advancements and rigorous evaluation in this domain, we argue that generated posters must be assessed from two complementary perspectives: objective fidelity and subjective quality.
So we establish P2Peval, a comprehensive benchmark featuring 1738 checklist items and a dual evaluation methodology (Fine-Grained and Universal).
Our Fine-Grained Evaluation uses human-annotated checklists to objectively measure the faithful preservation of verifiable content from the source paper. Concurrently, our Universal Evaluation captures subjective, holistic quality by training a model to align with human aesthetic preferences across key design principles. We evaluate a total of 35 models.
To power these advancements, we also release P2Pinstruct, the first large-scale instruction dataset comprising over 30,000 high-quality examples tailored for the academic paper-to-poster generation task. Furthermore, our contributions aim to streamline research dissemination while offering a principled blueprint for evaluating complex, creative AI-generated artifacts.
The code is on the GitHub, https://github.com/multimodal-art-projection/P2P.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 11697