Runway: video pretraining lifts Praxis-1 to 80.0% on SimplerEnv vs RT-1's 52.4%
runwayml · x · 2026-11-11
Runway argues the most scalable source of robotics data is general video: a model trained to predict everyday footage learns object dynamics, hand motion and task progression, giving it a head start on new embodiments.
Fine-tuned on Google's RT-1 — a robot it never saw in training — Praxis-1 reaches 80.0% on SimplerEnv, versus 52.4% for the original RT-1 policy.
Related event: Runway Open-Sources Praxis-1 World Action Model, Tops RoboLab-120(10 posts)→
More from Embodied
- Open-source dual-arm robot solves tangram puzzles with 90 demos, ~60% success — DanGrover · 2026-11-12
- 3,500 Laser-Armed AI Submarine Robots Patrol Norwegian Salmon Farms — philfung · 2026-11-12
- Model Autonomously Designs a Surgical-Robot-Style Robotic Arm CAD After 75 Minutes — _Stocko_ · 2026-11-12
- Dev releases local world model turning any image into interactive video, runs on RTX 3060 — lucidml_lover · 2026-11-12
- RoboRisk benchmark shows foundation models pose high harm rates in robotics; LEASH harness cuts risk — UoLiverpool · 2026-11-12
- Embodied First Exam benchmarks coding agents on 47 robots across 1,156 tasks; best agent hits just 34% — MLL-Lab · 2026-11-12