NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:3529
Title:BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling

This paper was reviewed by three expert reviewers and received two Accept and one Clear Accept recommendations. All the three reviewers are positive about this paper, and agree that this paper is well written and well motivated. The proposed method is reasonable and novel, and experiments are convincing. The rebuttal further addresses reviewers' comments. Therefore, the AC recommends accepting the paper.