We show that imitation learning of human-human interactions in a simulated world, in conjunction with self-supervised learning, is sufficient to produce a multimodal interactive agent, which we call MIA, that successfully interacts with non-adversarial…
Language, and its role in demonstrating and facilitating comprehension – or intelligence – is a fundamental part of being human. It gives people the ability to communicate thoughts and concepts, express ideas, create memories, and build mutual understa…
We show that imitation learning of human-human interactions in a simulated world, in conjunction with self-supervised learning, is sufficient to produce a multimodal interactive agent, which we call MIA, that successfully interacts with non-adversarial…
We explore an alternate path for improving language models: we augment transformers with retrieval over a database of text passages including web pages, books, news and code. We call our method RETRO, for “Retrieval Enhanced TRansfOrmers”.
Language, and its role in demonstrating and facilitating comprehension – or intelligence – is a fundamental part of being human. It gives people the ability to communicate thoughts and concepts, express ideas, create memories, and build mutual understa…
Our main results prove that while reward can express many tasks, there exist instances of each task type that no Markov reward function can capture. We then provide a set of polynomial-time algorithms that construct a reward function which allows an ag…
More than a century ago, Srinivasa Ramanujan shocked the mathematical world with his extraordinary ability to see remarkable patterns in numbers that no one else could see. The self-taught mathematician from India described his insights as deeply intui…
More than a century ago, Srinivasa Ramanujan shocked the mathematical world with his extraordinary ability to see remarkable patterns in numbers that no one else could see. The self-taught mathematician from India described his insights as deeply intui…
Our main results prove that while reward can express many tasks, there exist instances of each task type that no Markov reward function can capture. We then provide a set of polynomial-time algorithms that construct a reward function which allows an ag…
Our brain has an amazing ability to process visual information. We can take one glance at a complex scene, and within milliseconds be able to parse it into objects and their attributes, like colour or size, and use this information to describe the scen…
