clement-bonnet/lpn
Latent Program Network (from the "Searching Latent Program Spaces" paper)
This project offers an advanced architecture for program synthesis, a method for automatically generating computer programs. It takes in problem specifications or examples and outputs executable code, even adapting to new challenges at the time of execution. Researchers in artificial intelligence and machine learning would find this useful for exploring novel program generation techniques.
108 stars.
Use this if you are an AI researcher or machine learning engineer working on automated program generation and want to explore a latent space search approach.
Not ideal if you are looking for a ready-to-use application to generate code for specific practical tasks outside of research into program synthesis itself.
Stars
108
Forks
13
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Nov 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/clement-bonnet/lpn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
kk7nc/RMDL
RMDL: Random Multimodel Deep Learning for Classification
OML-Team/open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
miguelvr/dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
PaddlePaddle/models
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models...