research
∙
03/17/2022
Transframer: Arbitrary Frame Prediction with Generative Models
We present a general-purpose framework for image modelling and vision ta...
share
research
∙
02/15/2022
General-purpose, long-context autoregressive modeling with Perceiver AR
Real-world data is high-dimensional: a book, image, or musical performan...
research
∙
06/28/2021
HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps
High Definition (HD) maps are maps with precise definitions of road lane...
research
∙
03/10/2021
Variable-rate discrete representation learning
Semantically meaningful information content in perceptual signals is usu...
research
∙
03/05/2021
Generating Images with Sparse Representations
The high dimensionality of images presents architecture and sampling-eff...
research
∙
02/23/2020
PolyGen: An Autoregressive Generative Model of 3D Meshes
Polygon meshes are an efficient representation of 3D geometry, and are o...
research
∙
10/02/2019
Efficient Graph Generation with Graph Recurrent Attention Networks
We propose a new family of efficient and expressive deep generative mode...
research
∙
04/11/2019
Autoregressive Energy Machines
Neural density estimators are flexible families of parametric models whi...
research
∙
06/01/2018
Inverting Supervised Representations with Autoregressive Neural Density Models
Understanding the nature of representations learned by supervised machin...
research
∙
01/11/2018