ASAL
A research paper by Akarsh Kumar and colleagues that proposes using foundation models to automate the search for emergent phenomena in artificial life simulators, exploring the intersection of evolutionary algorithms and artificial life.
Timeline (last 90 days)
ASAL (Automating the Search for Artificial Life with Foundation Models) is a paper by Akarsh Kumar that proposes using foundation models to automate the search for artificial life.
The core idea of ASAL is to parameterize a simulation space and then use a foundation model (a vision-language model) as a judge to search for artificial life.
In the ASAL experiment, the results of all 260,000 rules were input into CLIP and visualized in two-dimensional space; after coloring by openness, a large island of low openness and a small island concentrating the coolest simulations were found to exist.
All Facts (3)
ASAL (Automating the Search for Artificial Life with Foundation Models) is a paper by Akarsh Kumar that proposes using foundation models to automate the search for artificial life.
50%UnverifiedThe core idea of ASAL is to parameterize a simulation space and then use a foundation model (a vision-language model) as a judge to search for artificial life.
50%UnverifiedIn the ASAL experiment, the results of all 260,000 rules were input into CLIP and visualized in two-dimensional space; after coloring by openness, a large island of low openness and a small island concentrating the coolest simulations were found to exist.
50%