Watch Demis Hassabis introduce Gemini Omni at Google I/O 2026. Discover Google's new model that can create anything from any input - starting with video. Demis shares how Google DeepMind is pushing the boundaries of AI research with a new model that can turn any reference — image, text, video or audio — into a single, cohesive output. Learn more about Gemini Omni at: blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-omni 00:36 - World Models 00:57 - Gemini Omni #GoogleIO #GeminiOmni #GoogleDeepMind #AI Subscribe to our Channel: youtube.com/google Find us on X: twitter.com/google Watch us on TikTok: tiktok.com/@google Follow us on Instagram: instagram.com/google Join us on Facebook: facebook.com/Google