This post is a quick note about some interesting papers/workshop/talk I found when I go through the program NeurIPS 2018. I also jot down some of my thougts. The content mainly focuses on text generatiton, and molecule design (IMO, these two topics share some similarity) and the list is still ongoing…

The rapid development of GAN blossoms into many amazing applications in the continuous data such as image. They can be used to generate high-quality people or objects or translate pictures into different domains. Recently, GAN even starts to serve as a tool for the artist to create their work.