Nvidia · NVIDIA Blog
How Cosmos 3 Helps Physical AI Think Before It Acts
Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.
◎ Multiple-sources
The real world is always in motion.
Key facts
- With the OpenMDW 1.1 license from Linux Foundation, developers can use Cosmos model materials across physical AI workflows under a single, model-centric license
- Developers can try Cosmos 3 on build.nvidia.com, download open models from Hugging Face, customize models and generate synthetic data with resources on GitHub, and deploy with NVIDIA NIM microservices
- Watch the GTC Taipei keynote from NVIDIA founder and CEO Jensen Huang and explore these physical AI sessions
- Agile Robots is building humanoids and other embodiments like Thor 3 or FR3 that handle industrial tasks autonomously, precisely and efficiently
Summary
In a warehouse, a robot may encounter object configurations it’s never seen before. Capturing and recreating those scenarios in the real world is slow, expensive and often impossible to repeat at scale. Cosmos 3 powers perception, prediction and action. Learn more about how Cosmos 3’s mixture-of-transformers architecture enables a reasoning block to first interpret what is happening in a scene, then harnesses a generation block to use that context to create physically grounded outputs, from synthetic video to robot-task data. Cosmos 3 is a generalist foundation model trained on diverse data that gives it a broad understanding of how scenes, motion and robotic actions relate.