The world model just learned to reason. nvidia's cosmos 3, out as an open physical ai foundation…
the world model just learned to reason. nvidia's cosmos 3, out as an open physical ai foundation model, adds native reasoning plus world and action generation on a mixture-of-transformers design.
the sim now plans before it moves.
Context
NVIDIA's Cosmos page calls Cosmos 3 the open physical AI foundation model, the first omni-model with native reasoning, world and action generation, built on Mixture-of-Transformers. NVIDIA's developer blog (Jun 1, 2026) says it unifies physical reasoning, world generation and action generation in one open model, combining a vision-language reasoner tower with a diffusion-based generator tower.
The Cosmos 3 paper on arXiv describes a family of omnimodal world models that process and generate language, image, video, audio and action sequences.
The native reasoning, world and action generation and the mixture-of-transformers design all match NVIDIA's pages. The developer blog is dated Jun 1, 2026, so Cosmos 3 is not new this week. That the simulator plans before it moves is the author's opinion, and the pages read describe a reasoner tower and a generator tower.
Related work
- NVIDIA docs: Cosmos 3 ↗Reasoner and generator runtime surfaces.
- arXiv: Cosmos 3 ↗Paper.
- NVIDIA Cosmos page ↗Product page.
Watch next
- Find any Cosmos 3 release news dated October 2026.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 11 October 2026 at 22:41 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 →