5.7k citations · 11.9k across the 19 of their papers we have counts for
3 papers · 1 filter
Axial Attention in Multidimensional Transformers
Jonathan Ho, Nal Kalchbrenner, Dirk Weissenborn +1
We propose Axial Transformers, a self-attention-based autoregressive model for images and other data organized as high dimensional tensors. Existing autoregressive models either su…
Natural Image Manipulation for Autoregressive Models Using Fisher Scores
Wilson Yan, Jonathan Ho, Pieter Abbeel
Deep autoregressive models are one of the most powerful models that exist today which achieve state-of-the-art bits per dim. However, they lie at a strict disadvantage when it come…
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
Jonathan Ho, Xi Chen, Aravind Srinivas +2
Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have mu…