Meta releases V-JEPA, an AI model that learns by predicting missing or masked parts of unlabeled video to develop a conceptual understanding of the world (Mark Sullivan/Fast Company)

Mark Sullivan / Fast Company:

Meta releases V-JEPA, an AI model that learns by predicting missing or masked parts of unlabeled video to develop a conceptual understanding of the world  —  Meta's AI researchers have released a new model that's trained in a similar way as today's large language models, but instead of learning from words …

ai model jepa meta releases understanding video world