NVIDIA/cosmos
Summary
NVIDIA Cosmos is an open platform featuring world models, datasets, and tools designed to help developers build Physical AI applications for robots, autonomous vehicles, and smart infrastructure.
Similar Articles
Nvidia Cosmos 3
NVIDIA has open-sourced Cosmos 3, a frontier foundation model for physical AI that unifies reasoning, world generation, and action generation within a single Mixture-of-Transformers architecture, releasing model checkpoints, datasets, and training scripts for robotics, autonomous vehicles, and warehouse monitoring.
nvidia/Cosmos3-Nano
NVIDIA releases Cosmos3-Nano, an omnimodal world model for Physical AI that generates video, image, audio, and action commands from text, image, video, and action inputs, targeting robotics, autonomous driving, and smart space applications.
nvidia/Cosmos3-Super
NVIDIA released Cosmos3, a collection of omnimodal world foundation models for Physical AI, capable of generating video, image, audio, and action commands from various inputs, with versions for different tasks like policy learning and image-to-video generation.
NVIDIA Launches Cosmos 3, the Open Frontier Foundation Model for Physical AI (5 minute read)
NVIDIA launches Cosmos 3, an open foundation model for physical AI with a mixture-of-transformers architecture, enabling reasoning, world simulation, and action generation for robotics and autonomous vehicles.
Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action
NVIDIA Cosmos 3 is an open omni-model for physical AI that unifies world generation, reasoning, and action generation into a single model, available on Hugging Face with various resources.