Thibault Castells, Research Engineer at Nota AI, demonstrates the company’s latest edge AI and vision technologies at the 2026 Embedded Vision Summit. Specifically, he demonstrates VLA optimization on Qualcomm Dragonwing™ IQ-9075, powered by NetsPresso®. Using an Action Head-only optimization approach, Nota AI achieves 7x faster Action Head speed (218ms → 31ms) and 1.6x faster end-to-end speed (505ms → 310ms), with virtually no accuracy loss. This demonstration highlights how NetsPresso® makes real-time robotic AI deployment practical and scalable on edge hardware.
To learn more about NetsPresso®, visit: https://www.nota.ai/netspresso
