figures4papers

<div align="center">

<h1><code>Figures for Papers</code></h1>

[![LinkedIn](https://img.shields.io/badge/LinkedIn-Chen-blue)](https://www.linkedin.com/in/chenliu1996/)
[![Twitter Follow](https://img.shields.io/twitter/follow/Chen.svg?style=social)](https://x.com/ChenLiu_1996)
[![Google Scholar](https://img.shields.io/badge/Google_Scholar-Chen-4a86cf?logo=google-scholar&logoColor=white)](https://scholar.google.com/citations?user=3rDjnykAAAAJ&sortby=pubdate)

</div>

I am [Chen Liu](https://chenliu-1996.github.io/) (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. &#127881; 

Please feel free to cite any of these papers if you find them relevant or helpful. &#127891; 

<br>

### Bar plots for quantitative comparison
<img src="figure_ImmunoStruct/figures/bars_comparison_IEDB.png" width="800">

### Bar plots for composition breakdown
<img src="figure_Brainteaser/figures/brute_force.png" width="800">


### 3D spheres
<img src="figure_Dispersion/figures/illustration.png" width="800">

<div align="center">

<h3 align="left">Radar plots &emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; Line plots</h3>

<p align="left">
<img align="left" src="figure_VIGIL/figures/comparison_radar.png" width="400" alt="Radar comparison">
<img align="left" src="figure_VIGIL/figures/comparison_posttraining.png" width="350" alt="Post-training comparison">
<br clear="all">
</p>

</div>

### Concept plots
<img src="figure_VIGIL/figures/concept.png" width="800">

### Trend plots
<img src="figure_ophthal_review/figures/trend_by_month.png" width="800">

### 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.

<img src="assets/ImmunoStruct_schematic.png" width="400"><img src="assets/ImmunoStruct_contrastive.png" width="400">
<br><img src="assets/ImmunoStruct_results_IEDB.png" width="400"><img src="assets/ImmunoStruct_results_CEDAR.png" width="400">
<br><img src="assets/VIGIL_teaser.png" width="400"><img src="assets/RNAGenScape_schematic.png" width="400">
<br><img src="assets/RNAGenScape_teaser.png" width="400"><img src="assets/Dispersion_motivation.png" width="400">
<br><img src="assets/Dispersion_observation.png" width="400"><img src="assets/Dispersion_observation_distillation.png" width="400">

<br>

## LLM skill integration
I want to show appreciation to my friend [Shan Chen](https://shanchen.dev/) 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