Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Automating the Search for Artificial Life with Foundation Models!
| Date | Stars |
|---|---|
| 2026-07-31 | 476 |
| 2026-08-03 | 476 |
| 2026-08-06 | 476 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h1 align="center">
<a href="https://sakana.ai/asal">
<img width="600" alt="Discovered ALife Simulations" src="https://pub.sakana.ai/asal_blog_assets/cover_video_square-min.png"></a><br>
</h1>
<h1 align="center">
Automating the Search for Artificial Life with Foundation Models
</h1>
<p align="center">
📝 <a href="https://sakana.ai/asal">Blog</a> |
🌐 <a href="https://asal.sakana.ai/">Paper</a> |
📄 <a href="https://arxiv.org/abs/2412.17799">PDF</a>
</p>
<p align="center">
<a href="https://colab.research.google.com/github/SakanaAI/asal/blob/main/asal.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
</p>
[Akarsh Kumar](https://x.com/akarshkumar0101) $^{1}$ $^2$, [Chris Lu](https://x.com/_chris_lu_) $^{3}$, [Louis Kirsch](https://x.com/LouisKirschAI) $^{4}$, [Yujin Tang](https://x.com/yujin_tang) $^2$, [Kenneth O. Stanley](https://x.com/kenneth0stanley) $^5$, [Phillip Isola](https://x.com/phillip_isola) $^1$, [David Ha](https://x.com/hardmaru) $^2$
<br>
$^1$ MIT, $^2$ Sakana AI, $^3$ OpenAI, $^4$ The Swiss AI Lab IDSIA, $^5$ Independent
## Abstract
With the recent Nobel Prize awarded for radical advances in protein discovery, foundation models (FMs) for exploring large combinatorial spaces promise to revolutionize many scientific fields. Artificial Life (ALife) has not yet integrated FMs, thus presenting a major opportunity for the field to alleviate the historical burden of relying chiefly on manual design and trial-and-error to discover the configurations of lifelike simulations. This paper presents, for the first time, a successful realization of this opportunity using vision-language FMs. The proposed approach, called *Automated Search for Artificial Life* (ASAL), (1) finds simulations that produce target phenomena, (2) discovers simulations that generate temporally open-ended novelty, and (3) illuminates an entire space of interestingly diverse simulations. Because of the generality of FMs, ASAL works effectively across a diverse range of ALife substrates including Boids, Particle Life, Game of Life, Lenia, and Neural Cellular Automata. A major result highlighting the potential of this technique is the discovery of previously unseen Lenia and Boids lifeforms, as well as cellular automata that are open-ended like Conway’s Game of Life. Additionally, the use of FMs allows for the quantification of previously qualitative phenomena in a human-aligned way. This new paradigm promises to accelerate ALife research beyond what is possible through human ingenuity alone.
<div style="display: flex; justify-content: space-between;">
<img src="https://pub.sakana.ai/asal_blog_assets/teaser.png" alt="Image 1" style="width: 48%;">
<img src="https://pub.sakana.ai/asal_blog_assets/methods_figure.png" alt="Image 2" style="width: 48%;">
</div>
## Repo Description
This repo contains a minimalistic implementation of ASAL to get you started ASAP.
Everything is implemented in the [Jax framework](https://github.com/jax-ml/jax), making everything end-to-end jittable and very fast.
If you are looking for a PyTorch implementation, check [this](https://github.com/fredericowieser/ASAL-PyTorch) out.
The important code is here:
- [foundation_models/__init__.py](foundation_models/__init__.py) has the code to create a foundation model.
- [substrates/__init__.py](substrates/__init__.py) has the code to create a substrate.
- [rollout.py](rollout.py) has the code to rollout a simulation efficiently.
- [asal_metrics.py](asal_metrics.py) has the code to compute the metrics from ASAL.
Here is some minimal code to sample some random simulation parameters and run the simulation and evaluate how open-ended it is:
```python
import jax
from functools import partial
import substrates
import foundation_models
from rollout import rollout_simulation
import asal_metrics
fm = foundation_models.create_foundation_model('clip')
substrate = substrates.create_substrate('lenia')
rollout_Excerpt of 8,160 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:59d63ded77ffd993, llm:Repository description: "Automating the Search for Artificial Life with Foundation Models!" (no topics provided).