PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs

Hugging Face Daily Papers Papers
multi-agent paper-to-poster academic-papers design-diversity print-ready vision-language-model

Summary

PosterMELD is a template-conditioned multi-agent pipeline that converts academic papers into editable, print-ready posters, achieving 81.3% Print-Ready Rate with low cost, and is released with code and resources.

Scientific poster construction compresses a long multimodal paper into a readable, editable canvas. Existing systems hide request-level failures by scoring only completed outputs; direct image generation is not element-editable, while coding-agent workflows are costly. PosterMELD is a template-conditioned multi-agent pipeline: capacity-aware slots guide writing before rendering, and deterministic gates plus vision-language model (VLM) review route failures to bounded repair. Each accepted request exports editable PowerPoint (PPTX) and Portable Network Graphics (PNG) artifacts; explicit design controls yield same-paper variants. Across 621 papers, Print-Ready Rate (PRR) counts requests passing geometric, readability, asset-integrity, and obvious-factual-error checks, with native editability reported separately. A frozen VLM assigns conditional Craftsmanship-Harmony-Expressiveness (CHE) scores to print-ready outputs. PosterMELD attains 81.3% PRR, 3.4 times P2P's rate and 5.2 times PosterGen's, and the highest conditional CHE among generated methods with multiple print-ready outputs. Native editability and explicit design controls are retained at a mean cost of USD 0.38 per request, 3.5% of Codex+Skill's. Code and resources are available at https://github.com/Shannon4Science/PosterMELD.
Original Article
View Cached Full Text

Cached at: 08/05/26, 09:44 AM

Paper page - PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs

Source: https://huggingface.co/papers/2608.02218 Published on Aug 3

·

Submitted byhttps://huggingface.co/T-Jack

Jieon Aug 5

Abstract

Scientificposterconstructioncompressesalongmultimodalpaperintoareadable,editablecanvas.Existingsystemshiderequest-levelfailuresbyscoringonlycompletedoutputs;directimagegenerationisnotelement-editable,whilecoding-agentworkflowsarecostly.PosterMELDisatemplate-conditionedmulti-agentpipeline:capacity-awareslotsguidewritingbeforerendering,anddeterministicgatesplusvision-languagemodel(VLM)reviewroutefailurestoboundedrepair.EachacceptedrequestexportseditablePowerPoint(PPTX)andPortableNetworkGraphics(PNG)artifacts;explicitdesigncontrolsyieldsame-papervariants.Across621papers,Print-ReadyRate(PRR)countsrequestspassinggeometric,readability,asset-integrity,andobvious-factual-errorchecks,withnativeeditabilityreportedseparately.AfrozenVLMassignsconditionalCraftsmanship-Harmony-Expressiveness(CHE)scorestoprint-readyoutputs.PosterMELDattains81.3%PRR,3.4timesP2P’srateand5.2timesPosterGen’s,andthehighestconditionalCHEamonggeneratedmethodswithmultipleprint-readyoutputs.NativeeditabilityandexplicitdesigncontrolsareretainedatameancostofUSD0.38perrequest,3.5%ofCodex+Skill’s.Codeandresourcesareavailableathttps://github.com/Shannon4Science/PosterMELD.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2608\.02218

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.02218 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.02218 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.02218 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text

arXiv cs.CL

This paper introduces MELD, a detector for AI-generated text that uses multi-task learning with auxiliary heads for generator family, attack type, and source domain to improve robustness. MELD achieves strong performance on the RAID benchmark and maintains low false-positive rates under adversarial attacks.

Prompt-to-Paper: Agentic AI System for Bioinformatics

arXiv cs.AI

Prompt-to-Paper is a multi-stage multi-agent AI framework for automated bioinformatics manuscript generation that uses deterministic retrieval-augmented generation, an autonomous coding agent for real experiments, and an eight-dimensional quality scorer to produce submission-formatted PDFs at low cost, with validated quality improvements.