Language Meets Vision: One Model to rule them all
Three of our recent models – Chinchilla, Flamingo, and Gato – leveraged one another and combined several state-of-the-art pre-training techniques. This talk will describe how this combination yielded even stronger capabilities to achieving complex tasks, in the few-shot setting, and how we are witnessing the beginning of a new era in language and vision research beyond specialization to single tasks.
Dr. Oriol Vinyals
Oriol Vinyals is VP of Research at Google DeepMind, where he is currently co-Technical Lead for Gemini (with Jeff Dean), and Team Lead of the Deep Learning group. He is a world-renowned expert in deep learning, whose work has had a major impact on the field. After obtaining his PhD in EECS from the University of California in Berkeley, Oriol joined Google Brain in 2013 where he made significant contributions to deep learning techniques in ML text, speech and vision, and became a recipient of the 2016 MIT TR35 innovator award. In 2016, he joined the former DeepMind group (now Google DeepMind) with a continued focus on deep learning and artificial intelligence.