Resources
In-depth information about the edge AI and vision applications, technologies, products, markets and trends.
The content in this section of the website comes from Edge AI and Vision Alliance members and other industry luminaries.
All Resources
“One Silicon, Two Worlds: NPU Optimization for Autoregressive and Diffusion Transformers,” a Presentation from VeriSilicon
Shang-Hung Lin, Vice President of NPU Technology at VeriSilicon presents “One Silicon, Two Worlds: NPU Optimization for Autoregressive and Diffusion Transformers” at the May 2026 Embedded Vision Summit. Physical AI is caught between two computational
OpenClaw on Jetson (Part 2)
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. OpenClaw also works on Jetson devices. You can run it on a Jetson AGX Orin or AGX Thor, but even if
SiMa.ai Launches Palette Neat, Industry’s First Agentic Environment for Physical AI; Slashes Development from Months to Days
Palette Neat, alongside the production-ready, pin-compatible Modalix™ SoM, dismantles the legacy GPU moat to scale Physical AI SAN JOSE, Calif. — June 16, 2026 — SiMa.ai, a leader in Physical AI, today launched Palette
“Why Edge Vision Models Keep Breaking—and What Complete Training Data Changes,” a Presentation from Synetic
David Scott, Founder and CEO at Synetic presents “Why Edge Vision Models Keep Breaking—and What Complete Training Data Changes” at the May 2026 Embedded Vision Summit. Most edge vision deployments fail not because of model
OpenClaw on Jetson (Part 1)
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. OpenClaw also works on Jetson devices. You can run it on a Jetson AGX Orin or AGX Thor, but even if
Efinix Launches Titanium Edge FPGA Family, Solving the Demanding Requirements of Edge AI
New family delivers breakthrough power reduction, System-in-Package integration, high-speed MIPI I/O, advanced SEU scrubbing, and post-quantum security for constrained edge AI deployments Cupertino, Calif.—June 9, 2026—Efinix® Inc., the FPGA pioneer accelerating edge AI innovation,
Upcoming Webinar to Introduce Industrial Robotics Reference Platform
On June 23, 2026, at 8:00 am PDT (11:00 am EDT / 17:00 CEST) STMicroelectronics, eInfochips and Arrow will deliver a webinar “A Prevalidated AMR Reference Platform for Faster Industrial Robotics Development” From the event
“How Qualcomm Is Making Computer Vision Accessible Across Edge Verticals,” a Presentation from Qualcomm Technologies, Inc.
Derrick Chang, Senior Product Manager at Qualcomm Technologies, Inc. presents “How Qualcomm Is Making Computer Vision Accessible Across Edge Verticals” at the May 2026 Embedded Vision Summit. Computer vision at the edge is no longer
Top Challenges When Implementing AI Inspection and How to Outcome Them
This blog post was originally published at Lincode’s website. It is reprinted here with the permission of Lincode. Why, after all, do AI inspection systems not yield the results that manufacturers expect? Every day, manufacturers face three challenges.
Technologies
“Building a Local Voice Agent on a Raspberry Pi,” a Presentation from Moonshine AI
Pete Warden, CEO at Moonshine AI presents “Building a Local Voice Agent on a Raspberry Pi” at the May 2026 Embedded Vision Summit. In this talk, Warden explains everything you need to know to build your own voice agent running entirely on a stock Raspberry Pi 5, with no internet… “Building a Local Voice Agent
Why Most AI Performance Metrics Break Down in Production
This blog post was originally published at ModelCat’s website. It is reprinted here with the permission of ModelCat. Artificial intelligence systems often appear highly effective during development. Models achieve strong benchmark scores, validation metrics improve over time, and performance looks predictable within controlled environments. But once those same systems are deployed into real-world conditions, results frequently
MemryX Expands Cascade Platform, Bringing Power-Efficient Edge AI to Servers
Introducing an expanded portfolio of modules that gives developers a single, scalable architecture to power everything from low-power devices to enterprise edge infrastructure ANN ARBOR, Mich., June 22, 2026 /PRNewswire/ — As AI moves from cloud environments into factories, transportation systems, robotics, and intelligent infrastructure, developers face growing challenges related to power consumption, memory bandwidth, deployment complexity,
Applications
SiMa.ai and Mistral Solutions, a subsidiary of AXISCADES, Partner to Accelerate Autonomous Drone Intelligence
Joint reference design combines Mistral’s embedded systems expertise with SiMa.ai’s Physical AI platform to deliver the fastest path to autonomous drone deployment. SAN JOSE, Calif. (June 23, 2026) and NEW DELHI (June 24, 2026) — SiMa.ai, a leader in Physical AI, and Mistral Solutions, a leader in embedded systems and drone product engineering, today announced a
BrainChip Unveils Communication Reference Platform, Fueling Signal Intelligence at the Edge
LAGUNA HILLS, Calif. – June 23, 2026 – BrainChip Holdings Ltd. (ASX: BRN, OTCQX: BRCHF, BCHPY), the first commercial producer of neuromorphic artificial intelligence technology, today announced the Akida Communication Reference Platform, a physical development platform for RF signal classification using BrainChip’s Akida AKD1500 neuromorphic processor. The platform is a critical tool for defense contractors and government agencies
Upcoming Workshop on Data-centric Software-defined Vehicle Systems
On July 9-10, 2026 at 11:00 am PDT (2:00 pm EDT), NXP partner ITTIA will present the online workshop “Building Data-Centric SDV Systems on NXP S32 Automotive Processing Platform.” Workshop sessions will also be hosted for Europe attendees June 29-30, 2026 at 3:00 pm CET, and for Asia attendees July 7-9, 2026 at 9:00 am
Functions
AI On: 3 Ways to Bring Agentic AI to Computer Vision Applications
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. Learn how to integrate vision language models into video analytics applications, from AI-powered search to fully automated video analysis. Today’s computer vision systems excel at identifying what happens in physical spaces and processes, but lack the abilities to explain the
SAM3: A New Era for Open‑Vocabulary Segmentation and Edge AI
Quality training data – especially segmented visual data – is a cornerstone of building robust vision models. Meta’s recently announced Segment Anything Model 3 (SAM3) arrives as a potential game-changer in this domain. SAM3 is a unified model that can detect, segment, and even track objects in images and videos using both text and visual
TLens vs VCM Autofocus Technology
This blog post was originally published at e-con Systems’ website. It is reprinted here with the permission of e-con Systems. In this blog, we’ll walk you through how TLens technology differs from traditional VCM autofocus, how TLens combined with e-con Systems’ Tinte ISP enhances camera performance, key advantages of TLens over mechanical autofocus systems, and applications
