Edge AI

Edge AI is the deployment of machine learning inference directly on local hardware such as cameras, sensors, vehicles and industrial devices. Truncated covers hardware releases, efficiency improvements, software frameworks, security practices and real-world deployment challenges.

Yesterday · Tue 10 Nov

Intel and Altera expand collaboration to simplify sensor integration for physical AI

AI-generated summary Intel Corp. and Altera Corp. announced that they are jointly developing flexible, real-time, sensor-bridge reference systems for edge and physical AI applications including robotics. The companies state that their collaboration combines Intel compute, connectivity, and software with Altera field-programmable gate arrays or FPGAs to help manufacturers simplify sensor integration.

Monday 9 November

Sunday 8 November

DFRobot’s DX-M1 Is An AI Accelerator That Uses Your M.2 Slot And Brings 25 TOPS Of Performance At 5W For Just $139, But Forget About Running Heavy LLMs

AI-generated summary DFRobot introduces the DX-M1 AI accelerator, which utilizes an M.2 slot to deliver 25 TOPS of performance while consuming between 2W and 5W of power. Priced at $139, the hardware includes 4GB of onboard LPDDR5 RAM and 1Tbit of QSPI NAND Flash, though it is not designed to run heavy LLMs locally.

Friday 6 November

Thursday 5 November

PATEO puts ByteDance's most powerful AI model inside a car — no internet needed

PATEO AI Box

AI-generated summary On November 3, 2026, PATEO announced the AI Box, which is a modular compute unit built on the NVIDIA DRIVE AGX Thor platform to run offline in-car artificial intelligence. PATEO says the system integrates NVIDIA Nemotron 3.5 ASR and ByteDance's Doubao language model to provide voice-activated cabin controls and real-time hazard awareness without needing a cellular signal.