WASHINGTON, DC (GTC), Nov 4, 2025 – NVIDIA has announced America’s first AI-native wireless stack for 6G, developed in collaboration with Booz Allen, Cisco, MITRE, ODC, and T-Mobile. The new platform is designed to accelerate R&D of wireless networks.
As AI expands beyond smartphones to cameras, AR glasses, robots, and autonomous vehicles, wireless networks face demand to support billions of connections with greater speed and efficiency.
To enable technologies such as integrated sensing and communications (ISAC), which link physical and digital systems, wireless networks must integrate AI into their hardware, software, and architecture.
AI-native networks improve spectrum efficiency by managing the radio frequencies used for wireless communication. The AI-RAN architecture advances next-gen networks by integrating computing, connectivity, and sensing on a single software-defined platform.
“6G is being built from the ground up with AI at its core – unlocking extreme spectral efficiency, massive connectivity and breakthrough applications,” said Ronnie Vasishta, senior vice president of telecom at NVIDIA. “Working with industry leaders, we’ve created an AI-native wireless stack with advanced features to ensure that America will play an instrumental role in the journey to 6G.”
First Made-in-America AI-Native Wireless Stack at NVIDIA
Six months since starting the AI-WIN project, NVIDIA and its partners built an AI-native wireless stack and completed the first user-to-user phone call over the network. The team also developed 6G applications at NVIDIA’s campus in Santa Clara, CA.
The system integrates the NVIDIA AI aerial platform with 5G RAN software from ODC, 5G core and user plane software from Cisco, and 6G applications from MITRE and Booz Allen.
Cisco is contributing to the AI-WIN initiative to support development of secure network connectivity for AI and integrated sensing applications.
“Through this partnership, we are pioneering the future of intelligent, secure connectivity – where AI is infused into the fabric of mobile networks and services,” said Masum Mir, senior vice president and general manager of Cisco provider mobility. “Together, we are harnessing AI to enable networks that sense, learn and act in real time, empowering service providers to deliver high-value business and consumer services in the AI era.”
Cerberus ODC’s 5G RAN, powered by NVIDIA AI Aerial, is setting new standards by enabling simultaneous RAN and AI workloads for enterprise applications, while outperforming legacy RAN systems with 7x greater cell capacity and 3.5x higher power efficiency.
Breakthrough Applications Drive 6G Standards
As part of the collaboration, NVIDIA and Booz Allen developed multimodal ISAC application, fusing camera vision and radio-frequency sensing to enable detection and tracking of objects even in low-visibility conditions.
Cameras can detect moving objects but cannot track their paths or see through obstacles. Radio-frequency sensors can measure an object’s position, speed, and distance without using visible light.
The ISAC application uses camera and radio-frequency data to provide spatial information. It can be applied in public safety, industrial monitoring, and national security.
MITRE has developed an AI-based spectrum management tool that allocates wireless frequencies within a cell site in real time to improve network efficiency.
Unlike traditional methods that shut down network bands when interference occurs, the application uses AI to isolate and block only affected frequencies. This approach improves spectral efficiency and reduces service disruptions in spectrum management and operations.
At NVIDIA GTC, Booz Allen showcased its AI-powered spectrum sensing R.AI.DIO application to detect and classify any type of interference, including signal jammers and unauthorized network users, in real time. This enables operators to respond to threats and mitigate issues to protect network integrity.
NVIDIA aerial framework provides modular, programmable pipelines to integrate third-party applications into the AI-RAN stack. Application programming interfaces enable these applications to access physical-layer data – the base form of data in a radio signal processing pipeline – enhancing training and reinforcement learning for AI models.
AI-native wireless networks provide the path to telecom’s paradigm shift from 5G to 6G, enabling efficient edge AI inference and sensing capabilities to serve billions of network connections and raise revenue for operators.
Source: NVIDIA
About NVIDIA
NVIDIA, founded in 1993 and headquartered in Santa Clara, CA, designs and manufactures graphics processing units, systems on chips, networking hardware, and AI intelligence software such as CUDA. Its products serve industries including gaming, data centers, autonomous vehicles, professional visualization, robotics, health care, and energy. The company introduced the GPU in 1999 and later expanded into accelerated computing and AI infrastructure. In gaming, its GPUs support high-performance rendering, while in AI and high-performance computing, its systems provide the infrastructure for training and deploying large-scale models. NVIDIA also develops tools for robotics and autonomous driving. For the fiscal quarter ending in July 2025, the company reported revenue of $46.7B and net income of $26.4B.