Praxis 1 Video Pretraining To Robot Control

An open-weight model pretrained on video reports 46.2% on RoboLab-120, ahead of listed VLA baselines such as pi0.5. That points to video pretraining as a data source for robot policies.

• open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
• pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
• fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.

• articleClosing The Gap
• articlePraxis 1 Is Now Available
• articleReal Time Video At Batch Size One
• articleRunway Dev Plugins For Coding Agents

• articleIntroducing Praxis 1Runway editorial sitemap
• articlePraxis 1 Is Now AvailableRunway editorial sitemap
• articleAccelerating Robot Policy EvaluationRunway

Checking sign-in…

Loading comments…