NanboLi/FACTS

[ICLR 2025] Implementation of "FACTS: A Factored State-Space Framework For World Modelling"

29
/ 100
Experimental

FACTS helps machine learning researchers efficiently build and experiment with state-space models, which are used for 'world modeling' in AI. It takes in structured input data, often time-series or sequential data, and outputs processed representations that capture underlying patterns and dynamics. This tool is designed for AI researchers and practitioners who are developing advanced predictive models and complex AI systems.

No commits in the last 6 months.

Use this if you are a machine learning researcher or developer working on advanced AI models and need a flexible, high-performance PyTorch implementation of factored state-space models for tasks like time series forecasting.

Not ideal if you are looking for a plug-and-play solution for a business problem without deep knowledge of machine learning model development and PyTorch.

AI-model-development world-modeling time-series-forecasting sequential-data-analysis deep-learning-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

29

Forks

1

Language

Python

License

MIT

Last pushed

Jun 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NanboLi/FACTS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.