Robotics and automation are entering a new phase of AI. Not driven by narrow, task-specific models but by multimodal foundation models that combine vision, language, and action to enable more adaptive, general-purpose automation.
Join this session to learn how teams take advantage of multimodal AI to modernize autonomous equipment and robotic systems while keeping proprietary data secure and governed.
You will be able to learn about:
What are VLAs and the opportunities they open
Infrastructure requirements for using (inference) and adapting (fine-tuning) models to your organization
Demo: how to streamline multimodal AI deployments with Ray on Anyscale
If you are a computer vision engineer, researcher or ML engineer working on physical AI, this session is for you.