← Model index
Physical AI / embodied world models

NVIDIA Cosmos

NVIDIA Cosmos is a family of world foundation models for physical AI. Cosmos focuses on multimodal reasoning, world simulation, synthetic data, action prediction, robotics, and autonomous systems rather than consumer 3D world creation.

ResearchOpen weights / codeUpdated 2026-06-09

Overview

StatusResearch
AccessOpen weights / code
Released2025–2026
Inputstext, image, video, sound, actions
Outputsvideo, synthetic data, action trajectories, world states
Best forrobotics, autonomous systems, synthetic data generation, physical AI reasoning, simulation workflows

Why it matters

Cosmos is essential for the scientific and industrial side of world models. It connects the category to robotics, autonomous vehicles, simulation, and physical AI training data.

Roamscape use

Tracked as physical-AI world model infrastructure; useful for research pages and ecosystem mapping.

Strengths

  • physical AI orientation
  • robotics ecosystem integration
  • multimodal reasoning and generation
  • open model direction

Limitations

  • not a consumer world generator
  • requires technical infrastructure
  • best suited to physical AI teams and developers

Sources

Related models