内容：
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI, effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state of the art across a diverse suite of understanding and generation tasks, highlighting omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source text-to-image and image-to-video models by Artificial Analysis, and as the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation’s OpenMDW-1.1 License at github.com/nvidia/cosmos and huggingface.co/collections/nvidia/cosmos3. The project website is available at research.nvidia.com/labs/cosmos-lab/cosmos3.
