Runway launches open-source robot model Praxis-1
The story so far
Runway, a U.S. video AI company, has launched the robot model Praxis-1, which applies knowledge learned from video pre-training to real robot control, with a speed increase of 15.6 times and a cost reduction to 1/51. The model is based on the 27 billion parameter Runway Video Foundation model and achieved a success rate of approximately 46.2% in the RoboLab-120 benchmark test. Runway has opened the model weights under the Apache 2.0 license, allowing developers to run and fine-tune it on their own hardware. The model weights and related code are publicly available on Hugging Face and GitHub.
AI-written from the reports · Updated 8 hours ago
Coverage timeline
Follow the coverage to see every side of the story.
- The DecoderRunway open-sources robot control model Praxis-1
Runway has released the open-source robot control model Praxis-1, which learns to control robots through video and has shown excellent performance in its own tests, scoring 46.2% on the Nvidia RoboLab-120 evaluation, leading similar models. The model requires additional training to adapt to new robot systems, the standard version requires an 80GB memory GPU, and it has been made available on Hugging Face.
- ITHome · AIRunway launches robot model Praxis-1, 15.6 times faster and cost reduced to 1/51
Runway has launched the robot model Praxis-1, based on the Runway video foundation model with 27 billion parameters. In the RoboLab-120 benchmark test, it achieved a success rate of approximately 46.2%, with a speed increase of 15.6 times and a cost reduction to 1/51. This model is licensed under Apache 2.0 and both weights and code are open-sourced.
Heat over time
- Now
- 8
- Peak
- 1014 Nov, 18:00
- 24h change
- +113%
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.