Nvidia Physical AI #2749

Vaibhavs10 · 2025-03-18T19:36:40Z

Congratulations! You've made it this far! Once merged, the article will appear at https://huggingface.co/blog. Official articles
require additional reviews. Alternatively, you can write a community article following the process here.

Preparing the Article

You're not quite done yet, though. Please make sure to follow this process (as documented here):

Add an entry to _blog.yml.
Add a thumbnail. There are no requirements here, but there is a template if it's helpful.
Check you use a short title and blog path.
Upload any additional assets (such as images) to the Documentation Images repo. This is to reduce bloat in the GitHub base repo when cloning and pulling. Try to have small images to avoid a slow or expensive user experience.
Add metadata (such as authors) to your md file. You can also specify guest or org for the authors.
Ensure the publication date is correct.
Preview the content. A quick way is to paste the markdown content in https://huggingface.co/new-blog. Do not click publish, this is just a way to do an early check.

Here is an example of a complete PR: #2382

Getting a Review

Please make sure to get a review from someone on your team or a co-author.
Once this is done and once all the steps above are completed, you should be able to merge.
There is no need for additional reviews if you and your co-authors are happy and meet all of the above.

Feel free to add @pcuenca as a reviewer if you want a final check. Keep in mind he'll be biased toward light reviews
(e.g., check for proper metadata) rather than content reviews unless explicitly asked.

_blog.yml

nvidia-physical-ai.md

pcuenca · 2025-03-18T19:54:18Z

nvidia-physical-ai.md

+
+At its annual GTC conference, NVIDIA has unveiled a trio of groundbreaking open-source releases aimed at accelerating physical AI development. Release of a new suite of world foundation models(WFMs) with multicontrols called **Cosmos Transfer**, a highly curated **Physical AI Dataset**, and the first open model for general humanoid reasoning called **NVIDIA Isaac GR00T N1** - represent a significant leap forward in physical AI technology, offering developers powerful tools and resources to advance robotics systems, and enhance autonomous vehicle technology.
+
+# New World Foundation Model - Cosmos Transfer


Suggested change

# New World Foundation Model - Cosmos Transfer

## New World Foundation Model - Cosmos Transfer

pcuenca · 2025-03-18T19:54:29Z

nvidia-physical-ai.md

+
+Available in 7 billion parameter size, the model utilizes multicontrols to guide the generation of high-fidelity world scenes from structural inputs, ensuring precise spatial alignment and scene composition.
+
+## How it works


Suggested change

## How it works

### How it works

pcuenca · 2025-03-18T19:54:41Z

nvidia-physical-ai.md

+
+Cosmos Transfer [samples](https://huggingface.co/nvidia/Cosmos-Transfer1-7B-Sample-AV) built using post-training base model are also available for autonomous vehicles. 
+
+# Open Physical AI Dataset


Suggested change

# Open Physical AI Dataset

## Open Physical AI Dataset

pcuenca · 2025-03-18T19:54:51Z

nvidia-physical-ai.md

+
+The dataset is designed for post-training foundation models like Cosmos Predict world foundation models, providing developers with high-quality, diverse data to enhance their AI models.
+
+# Purpose Built Model for Humanoids - NVIDIA Isaac GR00T N1


Suggested change

# Purpose Built Model for Humanoids - NVIDIA Isaac GR00T N1

## Purpose Built Model for Humanoids - NVIDIA Isaac GR00T N1

pcuenca · 2025-03-18T19:55:00Z

nvidia-physical-ai.md

+- **Vision-Language Model (System 2)**: This methodical thinking system is based on [NVIDIA-Eagle](https://huggingface.co/NVEagle) with [SmolLM-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B). It interprets the environment through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions.
+- **Diffusion Transformer (System 1)**: This action model generates continuous actions to control the robot's movements, translating the action plan made by System 2 into precise, continuous robot movements.
+
+# Path Forward


Suggested change

# Path Forward

## Path Forward

pcuenca · 2025-03-18T19:57:11Z

nvidia-physical-ai.md

+
+Check out GitHub for [Cosmos Predict](https://github.com/nvidia-cosmos/cosmos-predict1) and [Cosmos Transfer](https://github.com/nvidia-cosmos/cosmos-transfer1) inference scripts. Explore the Cosmos Transfer [research paper](https://research.nvidia.com/publication/2025-03_cosmos-transfer-1-world-world-transfer-adaptive-multi-control-physical-ai) for more details.
+
+The NVIDIA Isaac GR00T-N1-2B model is available on [Hugging Face](https://huggingface.co/nvidia/Isaac-GR00T-N1-2B). Sample datasets and PyTorch scripts for post-training using custom user datasets, which is compatible with the Hugging Face LeRobot format are available on [GitHub](http://github.com/NVIDIA/Isaac-GR00T). For more information about the Isaac GR00T N1 model, see the [research paper](https://research.nvidia.com/publication/2025-03_nvidia-isaac-gr00t-n1-open-foundation-model-humanoid-robots).


Suggested change

The NVIDIA Isaac GR00T-N1-2B model is available on [Hugging Face](https://huggingface.co/nvidia/Isaac-GR00T-N1-2B). Sample datasets and PyTorch scripts for post-training using custom user datasets, which is compatible with the Hugging Face LeRobot format are available on [GitHub](http://github.com/NVIDIA/Isaac-GR00T). For more information about the Isaac GR00T N1 model, see the [research paper](https://research.nvidia.com/publication/2025-03_nvidia-isaac-gr00t-n1-open-foundation-model-humanoid-robots).

The NVIDIA Isaac GR00T-N1-2B model is available on [Hugging Face](https://huggingface.co/nvidia/GR00T-N1-2B). Sample datasets and PyTorch scripts for post-training using custom user datasets, which is compatible with the Hugging Face LeRobot format are available on [GitHub](http://github.com/NVIDIA/Isaac-GR00T). For more information about the Isaac GR00T N1 model, see the [research paper](https://research.nvidia.com/publication/2025-03_nvidia-isaac-gr00t-n1-open-foundation-model-humanoid-robots).

pcuenca · 2025-03-18T19:57:56Z

nvidia-physical-ai.md

+
+# Purpose Built Model for Humanoids - NVIDIA Isaac GR00T N1
+
+Another exciting announcement is the release of [NVIDIA Isaac GR00T N1](https://developer.nvidia.com/blog/accelerate-generalist-humanoid-robot-development-with-nvidia-isaac-gr00t-n1/), the world's first open foundation model for generalized humanoid robot reasoning and skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. The NVIDIA Isaac GR00T-N1-2B model is available on [Hugging Face](https://huggingface.co/nvidia/Isaac-GR00T-N1-2B).


Suggested change

Another exciting announcement is the release of [NVIDIA Isaac GR00T N1](https://developer.nvidia.com/blog/accelerate-generalist-humanoid-robot-development-with-nvidia-isaac-gr00t-n1/), the world's first open foundation model for generalized humanoid robot reasoning and skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. The NVIDIA Isaac GR00T-N1-2B model is available on [Hugging Face](https://huggingface.co/nvidia/Isaac-GR00T-N1-2B).

Another exciting announcement is the release of [NVIDIA Isaac GR00T N1](https://developer.nvidia.com/blog/accelerate-generalist-humanoid-robot-development-with-nvidia-isaac-gr00t-n1/), the world's first open foundation model for generalized humanoid robot reasoning and skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. The NVIDIA Isaac GR00T-N1-2B model is available on [Hugging Face](https://huggingface.co/nvidia/GR00T-N1-2B).

nvidia-physical-ai.md

pcuenca · 2025-03-18T20:01:41Z

nvidia-physical-ai.md

+- user: asawareeb
+  guest: true
+  org: nvidia


This user does not belong to the nvidia org in the Hub.

_blog.yml

nvidia-physical-ai.md

Vaibhavs10 added 2 commits March 18, 2025 20:36

add nvidia physical AI blogpost

2bbbc6e

up

1015776

pcuenca approved these changes Mar 18, 2025

View reviewed changes

_blog.yml Show resolved Hide resolved

nvidia-physical-ai.md Outdated Show resolved Hide resolved

pcuenca reviewed Mar 18, 2025

View reviewed changes

nvidia-physical-ai.md Outdated Show resolved Hide resolved

pcuenca reviewed Mar 18, 2025

View reviewed changes

Apply suggestions from code review

147e652

pcuenca reviewed Mar 18, 2025

View reviewed changes

_blog.yml Show resolved Hide resolved

Update _blog.yml

fd16c8d

pcuenca reviewed Mar 18, 2025

View reviewed changes

_blog.yml Show resolved Hide resolved

Update _blog.yml

c6fb86c

Vaibhavs10 commented Mar 18, 2025

View reviewed changes

nvidia-physical-ai.md Outdated Show resolved Hide resolved

nvidia-physical-ai.md Show resolved Hide resolved

Update nvidia-physical-ai.md

711a51a

jeffboudier merged commit 9a4d8d8 into main Mar 18, 2025
1 check passed

jeffboudier deleted the vb/add-nvidia-physical-ai branch March 18, 2025 22:06

pcuenca changed the title ~~fix typo~~ Nvidia Physical AI Mar 19, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Nvidia Physical AI #2749

Nvidia Physical AI #2749

Vaibhavs10 commented Mar 18, 2025

pcuenca Mar 18, 2025

pcuenca Mar 18, 2025

pcuenca Mar 18, 2025

pcuenca Mar 18, 2025

pcuenca Mar 18, 2025

pcuenca Mar 18, 2025

pcuenca Mar 18, 2025

pcuenca Mar 18, 2025


		At its annual GTC conference, NVIDIA has unveiled a trio of groundbreaking open-source releases aimed at accelerating physical AI development. Release of a new suite of world foundation models(WFMs) with multicontrols called Cosmos Transfer, a highly curated Physical AI Dataset, and the first open model for general humanoid reasoning called NVIDIA Isaac GR00T N1 - represent a significant leap forward in physical AI technology, offering developers powerful tools and resources to advance robotics systems, and enhance autonomous vehicle technology.

		# New World Foundation Model - Cosmos Transfer

	# New World Foundation Model - Cosmos Transfer
	## New World Foundation Model - Cosmos Transfer


		Available in 7 billion parameter size, the model utilizes multicontrols to guide the generation of high-fidelity world scenes from structural inputs, ensuring precise spatial alignment and scene composition.

		## How it works


		Cosmos Transfer [samples](https://huggingface.co/nvidia/Cosmos-Transfer1-7B-Sample-AV) built using post-training base model are also available for autonomous vehicles.

		# Open Physical AI Dataset


		The dataset is designed for post-training foundation models like Cosmos Predict world foundation models, providing developers with high-quality, diverse data to enhance their AI models.

		# Purpose Built Model for Humanoids - NVIDIA Isaac GR00T N1

	# Purpose Built Model for Humanoids - NVIDIA Isaac GR00T N1
	## Purpose Built Model for Humanoids - NVIDIA Isaac GR00T N1


		Check out GitHub for [Cosmos Predict](https://github.com/nvidia-cosmos/cosmos-predict1) and [Cosmos Transfer](https://github.com/nvidia-cosmos/cosmos-transfer1) inference scripts. Explore the Cosmos Transfer [research paper](https://research.nvidia.com/publication/2025-03_cosmos-transfer-1-world-world-transfer-adaptive-multi-control-physical-ai) for more details.

		The NVIDIA Isaac GR00T-N1-2B model is available on [Hugging Face](https://huggingface.co/nvidia/Isaac-GR00T-N1-2B). Sample datasets and PyTorch scripts for post-training using custom user datasets, which is compatible with the Hugging Face LeRobot format are available on [GitHub](http://github.com/NVIDIA/Isaac-GR00T). For more information about the Isaac GR00T N1 model, see the [research paper](https://research.nvidia.com/publication/2025-03_nvidia-isaac-gr00t-n1-open-foundation-model-humanoid-robots).


		# Purpose Built Model for Humanoids - NVIDIA Isaac GR00T N1

		Another exciting announcement is the release of [NVIDIA Isaac GR00T N1](https://developer.nvidia.com/blog/accelerate-generalist-humanoid-robot-development-with-nvidia-isaac-gr00t-n1/), the world's first open foundation model for generalized humanoid robot reasoning and skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. The NVIDIA Isaac GR00T-N1-2B model is available on [Hugging Face](https://huggingface.co/nvidia/Isaac-GR00T-N1-2B).

Nvidia Physical AI #2749

Nvidia Physical AI #2749

Conversation

Vaibhavs10 commented Mar 18, 2025

Preparing the Article

Getting a Review

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment