Picture: Illustration · BitBytec · Original illustration, BitBytec
Ceva, Inc. announced on 2 November 2026 that Mobilint has deployed Ceva's SensPro AI DSP and NeuPro-Nano NPU in its REGULUS edge AI System-on-Chip (SoC). This milestone marks the first production deployment of Ceva's NeuPro NPU family, which is designed to deliver advanced sensing and inference capabilities for Physical AI devices [1].
Key facts * Mobilint integrated Ceva's SensPro AI DSP and NeuPro-Nano NPN32 NPU into its REGULUS processing architecture [1]. * The REGULUS SoC delivers 10 TOPS of AI performance at under 3W while supporting up to 8GB of memory [1]. * The chip is designed for real-time AI in power- and space-constrained applications such as robotics, drones, and smart cameras [1]. * REGULUS is already powering commercial products, including the Mobilint MLD-R1 AI USB accelerator [1].
What does REGULUS do? REGULUS functions as a standalone processor for on-device AI that integrates specialized engines for different workloads [1]. The SensPro engine provides programmable processing for sensing and signal-processing tasks, while the NeuPro-Nano engine provides efficient neural processing for always-on inference [1]. This multi-engine architecture allows Physical AI systems to sense, interpret, and respond to their surroundings in real time [1].
Who can use it and when? Mobilint's customers can use REGULUS to build the next generation of intelligent edge devices across various industries [1]. The technology is already being used in the MLD-R1 AI USB accelerator, which supports computer vision, video analytics, and generative AI workloads [1]. Developers can utilize these capabilities within widely used AI frameworks and ecosystems, including PyTorch, ONNX, Hugging Face, TensorFlow, TFLite, and Keras [1].
Why does it matter for Physical AI? As AI becomes embedded across the physical world, workloads are increasingly being processed directly on the device to ensure efficiency [1]. REGULUS addresses the diverse requirements of Physical AI devices by bringing sophisticated AI workloads into tight power constraints [1].
"REGULUS brings together the specialized processing capabilities needed to run sophisticated AI workloads directly on the device within very tight power constraints," said Dongjoo Shin, CEO of Mobilint [1].
Sources
- Ceva and Mobilint Advance Physical AI with REGULUS Edge AI SoC — Cision PR Newswire (primary source)
- The Epstein Files: How the saga unfolded within Trump’s administration | The Independent — The Independent
- Jeffrey Epstein list: Who is named in court filings? — bbc.com
Written with AI from the sources listed, checked against them before publishing.