ulab-uiuc/Time-R1

Time-R1: Framework and resources for endowing LLMs with comprehensive temporal reasoning (understanding, prediction, creative generation) using a novel three-stage RL curriculum. Includes the Time-Bench dataset and pre-trained models.

30
/ 100
Emerging

This project helps large language models (LLMs) better understand, predict, and creatively generate information related to time. It takes historical text data, like news articles, as input and produces an LLM capable of robust temporal reasoning. Anyone who uses or develops applications with LLMs for tasks involving event sequencing, future prediction, or scenario planning would benefit.

No commits in the last 6 months.

Use this if you need an LLM to accurately interpret past events, forecast future occurrences, or generate plausible timelines and scenarios.

Not ideal if your primary need is for non-temporal text generation or analysis, or if you are looking for a ready-to-use application rather than a framework for enhancing LLMs.

predictive-analytics scenario-planning event-forecasting natural-language-understanding generative-ai
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 5 / 25

How are scores calculated?

Stars

66

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Jun 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ulab-uiuc/Time-R1"

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