ChenLiu-1996/figures4papers

Public

My Python scripts to make high-quality figures for publications in top AI conferences and journals.

  • Stars9.3k+466 tuần này
  • Forks644
  • Watchers21
  • Issues1
  • Ngày tạo29/04/2025
  • Cập nhật gần nhất20/10/2026
  • Ngôn ngữPython
  • Giấy phép—
README.md31.1 KBRaw

Figures for Papers

LinkedIn Twitter Follow Google Scholar

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. 🎉

Please feel free to cite any of these papers if you find them relevant or helpful. 🎓
在符合学术规范的前提下,欢迎大家狠狠引用。 🎓


Bar plots for quantitative comparison

Bar plots for composition breakdown

3D spheres

Radar plots                   Line plots

Radar comparison Post-training comparison

Concept plots

Trend plots

Miscellaneous: figures not made end-to-end in Python

These figures were made partially in Python. I included them to acknowledge the time and efforts I spent on them.






LLM skill integration

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_*/.

Skill folder hierarchy

scientific-figure-making/
├── SKILL.md                              # Quick reference: metadata, when to use, patterns, links
└── references/
    ├── api.md                            # API/conventions to implement (palette, helpers, export)
    ├── common-patterns.md                # Reusable figure patterns
    ├── demos.md                          # Real-world figure_* projects (with URLs)
    ├── design-theory.md                  # Style rationale and design principles
    └── tutorials.md                      # Step-by-step guides

Using this skill in an AI coding agent

No installation (path-based)

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.

Simple AI workflow

  1. Open this repository in your AI coding agent (e.g. Cursor).

Nội dung README thuộc về ChenLiu-1996 và cộng đồng đóng góp, giấy phép Không có giấy phép. Nguồn: github.com/ChenLiu-1996/figures4papers