Video models are becoming robot brains. runway released praxis-1 on oct 1, an open-weight 'world…
video models are becoming robot brains. runway released praxis-1 on oct 1, an open-weight 'world action model' that turns video-pretrained knowledge into control for physical robots, per the announcement.
the same weights that learned to generate footage now decide how a machine moves.
Context
Runway's research page describes Praxis-1 as its first open-weight world action model, an open-weight model that turns Runway's video pretraining into control for real robots, and says it is being tested with early partners across a variety of embodiments and will be released publicly in the coming months. The page says simulating robot policies inside Runway's world model predicts real-world results with 0.95 correlation.
The Robot Report, dated October 2, 2026, says Runway introduced the model that week.
The note says Runway released Praxis-1 on October 1. Runway's page is dated September 2026 and says public release comes in the coming months, so the pages read describe an announcement with partner testing, not a release of weights. The October 1 date is unsupported here, not refuted, and trade press dated October 1 and 2 covers the announcement.
'The same weights that learned to generate footage now decide how a machine moves' is the author's line. Runway says Praxis-1 builds on the same video pretraining behind its world models, which is a description of training lineage, not of one set of weights.
The 0.95 correlation is about predicting real-world results of robot policies by simulating them in the world model, as Runway states it, not about Praxis-1's success rate on tasks.
Related work
- Introducing Praxis-1 (Runway Research, September 2026) ↗Source for the open-weight world action model, partner testing and the coming-months release.
- Runway introduces Praxis-1 world action model for robotics (The Robot Report, October 2, 2026) ↗Trade coverage of the announcement dated October 2, 2026.
Watch next
- Check whether the weights have been published and under what license. Look for Praxis-1 task success rates from partners.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 9 October 2026 at 08:18 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →