Tweeted By @dustinvtran

See the arXiv version at https://t.co/DHFf7dZX2F. It includes character-level results (1.38 bpc on PTB; 1.23 bpc on text8) with a RealNVP-like flow model that's 100-1000x faster at generation than state-of-the-art autoregressive baselines. https://t.co/wfa0T0jnal

— Dustin Tran (@dustinvtran) May 28, 2019