Videos on Edge AI and Visual Intelligence
We hope that the compelling AI and visual intelligence case studies that follow will both entertain and inspire you, and that you’ll regularly revisit this page as new material is added. For more, monitor the News page, where you’ll frequently find video content embedded within the daily writeups.
Alliance Website Videos
“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 titans: autoregressive (AR) transformers, which predict discrete action tokens, and diffusion transformers (DiTs), which refine… “One Silicon, Two Worlds: NPU
“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 architecture, but because real-world training data is structurally incomplete. Sampled data can’t cover combinatorial edge… “Why Edge Vision Models Keep
“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 limited by algorithms; it is constrained by power, latency, system complexity and deployment friction across… “How Qualcomm Is Making Computer
“Democratizing Physical AI: Arduino’s Open Door to Qualcomm’s Platform,” a Presentation from Qualcomm Technologies, Inc.
Olivier Bloch, Director of Developer Relations at Qualcomm Technologies, Inc. presents “Democratizing Physical AI: Arduino’s Open Door to Qualcomm’s Platform” at the May 2026 Embedded Vision Summit. Scaling physical AI breaks at production: prototypes work, then teams rewrite everything for incompatible SDKs, models and control stacks. The core issue is… “Democratizing Physical AI: Arduino’s Open
“Edge AI and Vision in Robotics: From Benchmarks to Fleet-Scale Reality,” an Expert Panel
Dave Tokic, Vice President of Corporate Development at Torc Robotics moderates the “Edge AI and Vision in Robotics: From Benchmarks to Fleet-Scale Reality” expert panel at the May 2026 Embedded Vision Summit. Other panelists include Vlad Branzoi, Perception Sensors Team Lead and Senior Staff Engineer at Agility Robotics, Bob Kunz,… “Edge AI and Vision in
“From Prototype to Production: What Computer Vision Teams Wish They Knew at 100 Devices,” a Presentation from Peridio
Justin Schneck, Co-Founder and CTO at Peridio presents “From Prototype to Production: What Computer Vision Teams Wish They Knew at 100 Devices” at the May 2026 Embedded Vision Summit. Your computer vision prototype works beautifully: USB camera on a Jetson dev kit, software humming, investors impressed. Production isn’t that convenient.… “From Prototype to Production: What
“Enabling “GenAI Everywhere”: Flexible Model Compatibility and Insight-Driven Workflows,” a Presentation from Nota AI
Tae-Ho Kim, Co-Founder and CTO at Nota AI presents “Enabling “GenAI Everywhere”: Flexible Model Compatibility and Insight-Driven Workflows” at the May 2026 Embedded Vision Summit. As generative AI models rapidly evolve—with increasingly dynamic transformer architectures and diverse framework variations—the challenge of bringing these models to the edge has grown dramatically.… “Enabling “GenAI Everywhere”: Flexible Model
“Roads to Robots: How Generative AI Is Redefining Memory and Storage for Embodied AI,” a Presentation from Micron
Saideep Tiku, Principal System Architect at Micron presents “Roads to Robots: How Generative AI Is Redefining Memory and Storage for Embodied AI” at the May 2026 Embedded Vision Summit. Generative AI has accelerated the automation of complex digital tasks, and now multimodal perception and reasoning make embodied AI the next… “Roads to Robots: How Generative
“Speeding Time to Market with Production-Ready Edge AI Solutions: From Wake Word Detection to Face Recognition,” a Presentation from Microchip Technology
Nick De Rosa, Kannan Srinivasagam, Edge AI Marketing Manager at Microchip Technology presents “Speeding Time to Market with Production-Ready Edge AI Solutions: From Wake Word Detection to Face Recognition” at the May 2026 Embedded Vision Summit. Design teams are moving from edge AI evaluation to deployment and need production-ready, system-level… “Speeding Time to Market with
“Invertible Light Technology: A Paradigm Shift for Depth Sensing,” a Presentation from MagikEye
Takeo Miyazawa, Founder and CEO at MagikEye presents “Invertible Light Technology: A Paradigm Shift for Depth Sensing” at the May 2026 Embedded Vision Summit. Invertible Light Technology (ILT) is a physics- and geometry-based depth-sensing approach designed for low algorithmic overhead. Unlike compute-heavy or correlation-intensive methods, ILT performs depth reconstruction using… “Invertible Light Technology: A Paradigm
