Building and Deploying Generative AI-Powered Visual Agents for Small Edge Devices

Computer vision applications are under transformational change with generative AI. New vision language models that understand both image/video and natural language enable the creation of visual AI agents that understand video footage and respond to prompts in natural language with remarkable precision. In this session, learn how edge-based computing is driving this innovation with NVIDIA's vision language models and NIM inference microservices. Explore how reference workflows allow developers to quickly develop such applications to augment existing computer vision AI applications and have confidence in their deployment.