Nvidia · GitHub · U.S. · AI Agent · NVIDIA Blog
Into the Omniverse: How Open World Models Push the Frontier of Physical AI
Compiled by KHAO Editorial — aggregated from 1 source + 1 reference discovered via search. See llms.txt for citation guidance.
★ Tier-1 Source
Editor’s note: This post is part of Into the Omniverse, a series focused on how developers, 3D practitioners and enterprises can transform their workflows using the latest advancements in OpenUSD and NVIDIA Omniverse.
Key facts
- In July, NVIDIA joined more than 200 companies and organizations in signing “ Open Weights and American AI Leadership,” an open letter arguing that AI leadership will be measured not by any single
- The family includes Cosmos 3 Super (64B) for high-fidelity world modeling, Cosmos 3 Nano (16B) for efficient reasoning and post-training, and Cosmos 3 Edge (4B) for on-device vision reasoning
- NVIDIA Cosmos world foundation models are available under the Linux Foundation’s OpenMDW 1.1 license, enabling teams to post-train models on their own data and hardware
- Explore the open Cosmos 3 model collection and datasets on Hugging Face and GitHub
Summary
In July, NVIDIA joined more than 200 companies and organizations in signing “ Open Weights and American AI Leadership,” an open letter arguing that AI leadership will be measured not by any single frontier model but by whether an open ecosystem reaches every sector. Open models, which anyone can download, inspect, modify and run on their own infrastructure, are what make that possible. Physical AI has to understand and predict consequences, not appearances. To make this possible, w orld models learn how physical environments behave, what may happen next and which following actions make sense.