NVlabs/Long-RL

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

39
/ 100
Emerging

This project helps researchers and machine learning engineers create more capable AI models that can understand and reason about very long videos, even those lasting an hour or more. It takes in lengthy video footage and questions about its content, then produces accurate, detailed answers. The primary users are AI model developers focused on advanced video analysis, robotics, or complex event understanding.

700 stars. No commits in the last 6 months.

Use this if you need to train AI models that can process and reason over extremely long video sequences for tasks like surveillance, sports analysis, or educational content understanding.

Not ideal if you are looking for an off-the-shelf application for end-users, or if your video analysis tasks only involve short clips.

video-reasoning long-form-content-analysis AI-model-training multi-modal-learning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 12 / 25

How are scores calculated?

Stars

700

Forks

26

Language

Python

License

Apache-2.0

Last pushed

Sep 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/NVlabs/Long-RL"

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