Dwith Chenna, MTS Product Engineer, AI Inference at AMD presents “Small Language Models for Edge AI: Trade-Offs and Quantization in Practice” at the May 2026 Embedded Vision Summit. Large language models are powerful but often impractical for embedded and on-prem systems due to latency, cost, privacy and memory constraints. Small… “Small Language Models for Edge […]
David Scott, CEO & Founder at Synetic, makes the case for synthetic training data as the most practical solution to edge case coverage in computer vision at the 2025 Embedded Vision Summit. Real-world data collection is slow, expensive, and structurally unable to capture the rare but critical scenarios — adverse lighting, unusual occlusions, extreme environments
Synetic Demonstration of Synthetic Training Data for Computer Vision Edge Case Coverage Read More +
David Scott, CEO & Founder at Synetic, demonstrates the LYNX SDK beta release at the 2026 Embedded Vision Summit. LYNX returns detection, segmentation, depth, and keypoints simultaneously from a single forward pass, eliminating the need to chain multiple models on constrained edge hardware. David highlights several capabilities shipping in the beta: 3D positioning from a
Will Ruffalo, Co-Founder at Synetic, introduces two of the company’s core offerings at the 2026 Embedded Vision Summit: the LYNX computer vision SDK and Synetic’s synthetic data as a service platform. LYNX delivers detection, segmentation, keypoints, and depth in a single inference call, across six platforms, from a single model artifact. Will also demonstrates how
See NovaEyeD in action — ModelNova™’s production-ready Edge AI face recognition model — demonstrated live at the STMicroelectronics booth during the 2026 Embedded Vision Summit. In this demo, we walk through how NovaEyeD delivers efficient, real-time face recognition directly on ST’s STM32N6 MCU, helping ST customers maximize the potential of their silicon. See what makes
NovaEyeD: Real-Time Face Recognition on ST’s STM32N6 Read More +
This blog post was originally published at Renesas’ website. It is reprinted here with the permission of Renesas. In industrial motor-driven systems, belts play a critical role in enabling the smooth and efficient transfer of mechanical power between rotating elements. These components connect two shafts, one driven by a motor and the other powered through a
Reinventing Belt Monitoring: How AI Detects Damage Before Failure Read More +
Ken Wenger, Founder and CTO at Squint Cognition, demonstrates Squint Vision Studio, the company’s AI safety and performance tooling for vision-based systems, at the 2026 Embedded Vision Summit. Squint Vision Studio is built for anywhere a confidently wrong perception model is a liability; inventory and loss prevention, industrial, agriculture, defense, aerospace. Costly at best, hazardous
Ken Wenger, Founder and CTO at Squint Cognition, demonstrates the company’s squinting model technology at the 2026 Embedded Vision Summit. Using Skittles and M&Ms, Wenger shows where a standard YOLO object detection model confuses one candy for the other; and does so with high confidence, offering no signal that anything is wrong. He then runs
This video was originally published at OpenCV’s website. It is republished here with the permission of OpenCV. Our guest is Alireza Taheritajar, a Ph.D. Student an Augusta University focusing on In-Situ Intelligent Mixed Reality Assistants for Adaptive Human-AI Collaboration. Mixed-reality overlays have been around for awhile, but with the recent upgrades in camera quality, lens
In-Situ Intelligent Mixed Reality Assistants for Adaptive Human-AI Collaboration Read More +
News Summary: NVIDIA expands NVIDIA Agent Toolkit with re-architected NVIDIA PhysicsNeMo libraries and updated NVIDIA CUDA-X libraries, enabling software developers to build autonomous AI engineers with AI physics skills, accelerated solvers and quantum chemistry capabilities. NVIDIA Nemotron 3 Ultra leads among open models in agentic register-transfer level coding with the ACE-RTL agent from NVIDIA Research,
Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.
Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596
