Foundation Models, particularly Large Vision Language Models, have dramatically transformed our understanding of what’s possible in AI. While groundbreaking, tools like ChatGPT, Bard, and Claude are confined to the digital realm, communicating solely through text. But what if we could extend their capabilities beyond the screen? This tech talk delves into the possibility of using these digital geniuses as the ‘brains’ for embodied agents, effectively translating their textual thoughts into tangible actions in the real world.
Norman di Palo, an alumnus of the first Session of the School of AI and a renowned researcher, shares his groundbreaking work conducted at Imperial College London and Google DeepMind. He brings a decade of experience working with diverse robotic forms – from space rovers to humanoid robots. His talk presents his latest research findings and provide an insightful overview of state-of-the-art robotics for everyday environments.
This tech talk is more than just a lecture; it’s an opportunity to glimpse the future. Whether you’re a tech enthusiast, a professional in the field, or simply curious about the advancements in robotics and AI, this event is for you. Here’s why you should watch it: