🎓Paper2Poster: Multimodal Poster Automation from Scientific Papers

从学术论文自动生成学术海报

We address How to create a poster from a paper and How to evaluate poster.

📚 Awesome Paper2Poster

New to this area? Check out Awesome Paper2Poster — a curated list of paper-to-poster methods, benchmarks, agent skills, and related paper-to-slides / video / webpage work.

🤩 Paper2Poster for Paper2Poster

🔥 Update

• [2026.10.23] We release Awesome Paper2Poster, a curated list of paper-to-poster methods, benchmarks and agent skills.
• [2026.6.6] We introduce lightweight Paper2Poster SKILL.
• [2025.10.7] Check out follow-up Paper2Video.
• [2025.11.3] Added Gradio demo support.
• [2025.10.18] Added Docker support.
• [2025.10.13] Added automatic logo support for conferences and institutions, YAML-based style customization, a new default theme.
• [2025.9.18] Paper2Poster has been accepted to NeurIPS 2025 Dataset and Benchmark Track.
• [2025.9.3] We now support generate per section content in parallel for faster generation, by simply specifying --max_workers.
• [2025.5.27] We release the arXiv, code and dataset

PosterAgent is a top-down, visual-in-the-loop multi-agent system from paper.pdf to editable poster.pptx.

📋 Table of Contents

• 🌟 Awesome Paper2Poster
• 🧰 Agent SKILL
• 🛠️ Installation
• 🐳 Docker Deployment
• 🚀 Quick Start
• 🔮 Evaluation

---

🧰 Agent SKILL

We provide a lightweight skill (without the need of dependency) in skills/ for AI agents such as Codex or Claude to help prepare poster-ready content from a paper.

For example, in Codex, you can invoke:

Use $paper2poster-poster to turn this paper into a poster package.

See skills/README.md for more examples.

🛠️ Installation

Our Paper2Poster supports both local deployment (via vLLM) or API-based access (e.g., GPT-4o).

Python Environment

pip install -r requirements.txt

Install Libreoffice

sudo apt install libreoffice

or, if you do not have sudo access, download soffice executable directly: https://www.libreoffice.org/download/download-libreoffice/, and add the executable directory to your $PATH.

Install poppler

conda install -c conda-forge poppler

API Key

Create a .env file in the project root and add your OpenAI API key:

OPENAI_API_KEY=<your_openai_api_key>

Optional: Google Search API (for logo search)

To use Google Custom Search for more reliable logo search, add these to your .env file:

GOOGLE_SEARCH_API_KEY=<your_google_search_api_key>
GOOGLE_SEARCH_ENGINE_ID=<your_search_engine_id>

---

🐳 Docker Deployment

For easier deployment, you can use Docker to run Paper2Poster without manual dependency installation.

Build the Docker image:

docker build -t paper2poster .

Troubleshooting:

• If you get a "permission denied" error when running Docker commands, use sudo before Docker commands (e.g., sudo docker build -t paper2poster .)

Example:

# Create output directory if it doesn't exist
mkdir -p <4o_4o>_generated_posters

docker run --rm \
-e OPENAI_API_KEY=<your_openai_api_key> \
-v "$(pwd)/Paper2Poster-data:/Paper2Poster-data" \
-v "$(pwd)/<4o_4o>_generated_posters:/app/<4o_4o>_generated_posters" \
paper2poster \
python -m PosterAgent.new_pipeline \
--poster_path="/Paper2Poster-data/<paper_name>/paper.pdf" \
--model_name_t=4o \
--model_name_v=4o \
--poster_width_inches=48 \
--poster_height_inches=36

The generated poster will be saved in <4o_4o>_generated_posters/Paper2Poster-data/paper_name/poster.pptx on your host machine.

---

🚀 Quick Start

Create a folder named {paper_name} under {dataset_dir}, and place your paper inside it as a PDF file named paper.pdf.

📁 {dataset_dir}/
└── 📁 {paper_name}/
    └── 📄 paper.pdf

To use open-source models, you need to first deploy them using vLLM, ensuring the port is correctly specified in the get_agent_config() function in utils/wei_utils.py.

• [High Performance] Generate a poster with GPT-4o:

python -m PosterAgent.new_pipeline \
    --poster_path="${dataset_dir}/${paper_name}/paper.pdf" \
    --model_name_t="4o" \  # LLM
    --model_name_v="4o" \  # VLM
    --poster_width_inches=48 \
    --poster_height_inches=36

• [Economic] Generate a poster with Qwen-2.5-7B-Instruct and GPT-4o:

python -m PosterAgent.new_pipeline \
    --poster_path="${dataset_dir}/${paper_name}/paper.pdf" \
    --model_name_t="vllm_qwen" \  # LLM
    --model_name_v="4o" \         # VLM
    --poster_width_inches=48 \
    --poster_height_inches=36 \
    --no_blank_detection          # An option to disable blank detection

• [Local] Generate a poster with Qwen-2.5-7B-Instruct:

python -m PosterAgent.new_pipeline \
    --poster_path="${dataset_dir}/${paper_name}/paper.pdf" \
    --model_name_t="vllm_qwen" \           # LLM
    --model_name_v="vllm_qwen_vl" \        # VLM
    --poster_width_inches=48 \
    --poster_height_inches=36

PosterAgent supports flexible combination of LLM / VLM, feel free to try other options, or customize your own settings in get_agent_config() in utils/wei_utils.py.

This is the beginning of the README. Read the rest at the original. Read the full README ↗