A "GAN" stands for Generative Adversarial Network, which is a class of machine learning framework and a prominent framework for approaching generative AI. It is a deep learning architecture that consists of two neural networks competing against each other in a zero-sum game framework. The goal of GANs is to generate new, synthetic data that resembles some known data distribution. The two sub-models of a GAN are the generator model, which generates new examples, and the discriminator model, which tries to classify examples as either real or fake. The two models are trained together in a zero-sum game, adversarial, until the discriminator model is fooled about half the time, meaning the generator model is generating plausible examples. GANs are used for unsupervised learning and can be used for problems involving image-to-image translation, text-to-image synthesis, and creating new data instances that resemble the training data.