Hu et al 2017 - On Unifying Deep Generative Models Unifies GANs and Variational Autoencoders (VAEs) with the sleep-wake algorithm, and improves upon them. See Eric's slides in his course http://www.cs.cmu.edu/~epxing/Class/10708-20/lectures.html Feb 24 and 26 for more details.

Arjovsky & Bottou 2017 - Towards Principled Methods for Training Generative Adversarial Networks

WGANs: Arjovsky et al 2017 - Wasserstein Generative Adversarial Networks