Software / Open source

cosmos reason1 · nvidia-cosmos

Models for physical common-sense reasoning and embodied decision-making.

Overview

Models for physical common-sense reasoning and embodied decision-making.

Publisher summary: “Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.”

Use its repository to inspect the implementation, documentation and supported workflows. This directory record identifies the maintainer, code license and related resources; it does not claim that the project has been installed or tested on your robot.

Project information

Maintainer: nvidia-cosmos
Primary language: Python
Repository code license: Apache-2.0
Model-weight license: Not recorded
Dataset license: Not recorded
Hardware design license: Not recorded
Maintenance: Not archived in the last recorded metadata
Last observed repository push: 2026-06-07

Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.

Documentation sections

[Paper](https://arxiv.org/abs/2503.15558) | [Website](https://research.nvidia.com/labs/dir/cosmos-reason1/) | [HuggingFace](https://huggingface.co/collections/nvidia/cosmos-reason1-67c9e926206426008f1da1b7) | [Cosmos Cookbook](https://github.com/nvidia-cosmos/cosmos-cookbook)
News
Model
Setup
Inference
Tutorials

Browse this resource’s categories

Software / Robot learning frameworks ↗

Explore related collections

Browse Software →

Repository

Research

NVIDIA Cosmos

World-model resources for physical AI and synthetic-data workflows.

World models

Models Explore →