decisionintelligence/Aurora

[ICLR 2026] Aurora: Towards Universal Generative Multimodal Time Series Forecasting

30
/ 100
Emerging

Aurora helps data analysts and domain experts predict future trends by leveraging both numerical time series data and related textual information. It takes in historical numerical sequences (like stock prices or sensor readings) and optional descriptive text, then outputs multiple probable future forecasts. This tool is for anyone needing to understand the likelihood of various future scenarios.

Use this if you need to generate multiple, probable future forecasts for time-series data, especially when textual context (like news articles or event descriptions) can inform your predictions.

Not ideal if your forecasting needs are simple and only require a single, deterministic prediction without considering multiple future possibilities or multimodal input.

predictive-analytics market-forecasting demand-planning risk-assessment operations-optimization
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 3 / 25
Community 10 / 25

How are scores calculated?

Stars

26

Forks

3

Language

Python

License

Last pushed

Feb 08, 2026

Commits (30d)

0

Get this data via API

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

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