# Paper2Poster/Paper2Poster

[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

Repository: https://github.com/Paper2Poster/Paper2Poster
Canonical: https://ross.abutalabs.com/products/paper2poster
Homepage: https://paper2poster.github.io/
Language: Python
License: MIT
License Family: permissive
Topics: agent, multi-agent-systems, paper, poster, pptx, task-automation
Last push: 2026-06-08T14:53:00+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 86, release rhythm 35, longevity 33
- inputs: {"age_days": 474, "days_push": 86, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3923, forks 284 (observed 2026-08-28T04:08:29.799501+00:00)

## What it is
Paper2Poster is an open-source multi-agent system (PosterAgent) that converts scientific paper PDFs into editable PowerPoint posters using a parser, planner, and painter-commentor loop with VLM feedback. It also ships a NeurIPS 2025 benchmark dataset for evaluating paper-to-poster generation.

## Use cases
- generate an academic poster from a paper pdf
- convert research paper to pptx poster automatically
- evaluate ai-generated posters against human posters
- automate conference poster design with multi-agent llm pipeline
- customize poster themes and layouts from a paper
- create posters with figures and tables extracted from a pdf

## When to choose
- you need editable pptx output rather than a static image
- you want layout-aware posters preserving reading order and multimodal assets
- you need a benchmark for paper-to-poster evaluation
- you want an open-source, self-hosted alternative to image-model poster generation

## When to avoid
- you need general-purpose slide deck generation, not academic posters
- you cannot access an LLM/VLM API or local models
- you need pixel-perfect manual design control from the start
- your source material is not a structured scientific paper

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, pdf, llm-inference, data-generation
- domain: artificial-intelligence, education
- platform: python, cross-platform
- tags: poster-generation, multi-agent, pptx, academic-posters, vlm, paper-to-poster, benchmark, ai-agents, natural-language-processing, automation, docker

## Member repositories
- Paper2Poster/Paper2Poster (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:29.799501+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:45.332147+00:00, confidence not recorded.
  - readme: https://github.com/Paper2Poster/Paper2Poster (fetched 2026-08-28T04:08:29.799501+00:00, sha cf9d43250ed8)
  - homepage: https://paper2poster.github.io/ (fetched 2026-08-29T09:18:45.018071+00:00, sha 26337574e524)
- Data as of 2026-08-30T08:39:29.467469+00:00.