CES 2025: NVIDIA Adds Generative Physical AI to Omniverse

At CES this week, NVIDIA revealed generative AI models and blueprints that expand NVIDIA Omniverse, the company's immersive simulation environment. The additional models are expected to advance physical AI applications such as robotics, autonomous vehicles, and vision AI. 

“Physical AI will revolutionize the $50 trillion manufacturing and logistics industries. Everything that moves — from cars and trucks to factories and warehouses — will be robotic and embodied by AI,” said Jensen Huang, founder and CEO at NVIDIA. “NVIDIA’s Omniverse digital twin operating system and Cosmos physical AI serve as the foundational libraries for digitalizing the world’s physical industries.”

Generative AI Models for Omniverse

According to NVIDIA, the new generative AI models will speed up world building, labeling the world with physical attributes, and making it photorealistic. 

"NVIDIA Omniverse, paired with new NVIDIA Cosmos world foundation models, creates a synthetic data-multiplication engine — letting developers easily generate massive amounts of controllable, photoreal synthetic data. Developers can compose 3D scenarios in Omniverse and render images or videos as outputs. These can then be used with text prompts to condition Cosmos models to generate countless synthetic virtual environments for physical AI training," explained NVIDIA.

During his CES keynote, Huang announced four new bluprints aimed at the growing market for digital twins:

• Mega, powered by Omniverse Sensor RTX APIs, for developing and testing robot fleets at scale;
• Autonomous vehicle simulation, powered by Omniverse Sensor RTX APIs, for autonomous car developers to replay driving data, generate new ground-truth data, and perform closed-loop testing;
• Omniverse spatial streaming to Apple Vision Pro for immersive digital visualization; 
• Real-time digital twins for Computer Aided Engineering (CAE), a reference workflow built on NVIDIA CUDA-X acceleration, physics AI, and Omniverse libraries. 

According to NVIDIA's announcement, Accenture, Altair, Ansys, Cadence, Foretellix, Microsoft, and Neural Concept are the early integrators of Omniverse. Siemens, a leader in industrial automation, also announced at the CES the availability of Teamcenter Digital Reality Viewer — the first Siemens Xcelerator application powered by NVIDIA Omniverse libraries.

Cosmos World Foundation Model Platform

To speed up the development of generative physical AI, NVIDIA is launching Cosmos World, a platform with state-of-the-art generative world foundation models, advanced tokenizers, guardrails, and an accelerated video processing pipeline, the company revealed.

Foundation models are neural networks trained on immense amounts of raw data and they serve as the building blocks for generative AI.

VIDIA explained, "Cosmos WFMs are purpose-built for physical AI research and development, and can generate physics-based videos from a combination of inputs, like text, image and video, as well as robot sensor or motion data. The models are built for physically based interactions, object permanence, and high-quality generation of simulated industrial environments — like warehouses or factories — and of driving environments, including various road conditions." 

Foundation Models for RTX-Powered AI PCs

Also at CES, NVIDIA announced the foundation models designed to run locally on NVIDIA RTX-powered AI PCs. The new addition is expected to supercharge digital humans, content creation, productivity, and development. These models come as NIMs (NVIDIA inferencing microservices) and are accelerated by the new GeForce RTX 50 Series GPUs. 

“AI is advancing at light speed, from perception AI to generative AI and now agentic AI,” said Huang. “NIM microservices and AI Blueprints give PC developers and enthusiasts the building blocks to explore the magic of AI.”