Runway's Praxis-1 robot brain learns from ordinary videos, cutting demo data from thousands of hours to minutes
c_valenzuelab · x · 2026-10-03
Spotted at Runway's conference: the video-gen lab is applying its world model research to robotics' biggest bottleneck — training data. Praxis-1, a robot "brain," learns how the physical world works from ordinary videos of humans doing tasks, so robotics companies need only minutes of demos on their own robot instead of thousands of hours of teleoperated recordings. CEO Cristóbal Valenzuela adds that "the most consequential updates in the next 18 months are coming."
More from Embodied
- PSYONIC's prosthetic Ability Hand now used by 90+ robotics orgs, raising Series A — DhowCIO · 2026-11-19
- Simulator misspecification breeds overconfidence: sim-to-real study on SPEED+ — Nikolay Dolgov · 2026-11-19
- Doppel world model renders the robot body and beats action-only baselines across 8 embodiments — mangahomanga · 2026-11-19
- FloMo: a world action model using 3D motion as the bridge from video pre-training to robot control — CSProfKGD · 2026-11-19
- MIT's paperclip-weight flying robot is first microrobot with onboard sensing and compute — MIT News AI · 2026-11-19
- Ken Goldberg's 30-year arc: from Telegarden crowdsourced farming to Dex-Net and Ambi Robotics — jfiance · 2026-11-19