What it does
Core capabilities at a glance
- ACL
- Cvpr
- Eccv
- Emnlp
- Figures
- Iccv
- Iclr
- Icml
Deep dive
The full breakdown - performance, comparisons, and setup
figures4papersLink to this section
figures4papers is a local-AI tool - My Python scripts to make high-quality figures for publications in top AI conferences and journals.
OverviewLink to this section
I am Chen Liu (刘晨), a Computer Science PhD Candidate at Yale University.
This is a centralized repository of my own Python scripts for high-quality figures.
These figures are published at top venues, including Nature Machine Intelligence, ICML, NeurIPS, ECCV, etc. 🎉
These figures were made partially in Python. I included them to acknowledge the time and efforts I spent on them.
I want to show appreciation to my friend Shan Chen who suggested doing this.
The scientific figure making skill lives in 'scientific-figure-making/'. Demo figures live in 'assets/'. Project-specific scripts and outputs live in 'figure_*/'.
You can use this skill without installing anything: open this repo in your AI coding agent (e.g. Cursor, Claude Code, etc.) and reference the skill by path in your prompts. The agent reads 'scientific-figure-making/SKILL.md' and the 'references/' files from the repo—no symlinks or plugins required.
- Open this repository in your AI coding agent (e.g. Cursor). 2. Ask the AI to create or update a plotting script in your target folder (for example 'figure_PROJECT_NAME/'). 3. In your prompt, explicitly ask it to follow 'scientific-figure-making/SKILL.md' and 'scientific-figure-making/references/design-theory.md'. 4. Run the generated script and check the exported figure.
figures4papers is open-source, written primarily in Python, with 9,612 GitHub stars under the Other license. It was last updated on 2026-10-19.
How it fits a local-AI stackLink to this section
figures4papers runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related local-AI tools in the directory:
SourcesLink to this section
- Source code & docs: ChenLiu-1996/figures4papers
- Official website: https://chenliu-1996.github.io/
Stats from GitHub, 2026-11-05.
Frequently asked
Quick answers to common questions
What is figures4papers?
figures4papers is a other tool for local AI workloads. My Python scripts to make high-quality figures for publications in top AI conferences and journals.
Is figures4papers free and open source?
Yes, figures4papers has 9,612 GitHub stars and is licensed under Other. You can self-host it for free on .
What hardware do I need for figures4papers?
The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. figures4papers has 9,612 GitHub stars and an active community.
Does figures4papers support GPU acceleration?
figures4papers's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.
What are the best alternatives to figures4papers?
Popular alternatives include other other tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.
How much does figures4papers cost?
figures4papers is free-open-source. It is completely free and open source to self-host.
Pairs well with
Complementary tools, models, and hardware