This seminar focuses on recent advances in unsupervised learning, an increasingly important field within machine learning. In unsupervised learning, we use the data itself rather than additional output labels to define a training objective, such as completing a given text sequence or filling in an image region. This way we can learn powerful representations, and stable generative paths. We will discuss new UL methods such as CLIP, DALLE, and FLAMINGO that combine language and image models in joint represenatations.