Kevin Ellis's work on visual program induction from hand-drawn graph sketches accepted as a spotlight presentation at NIPS 2018.
Aaron Gokaslan and Vivek Ramanujan's work on unsupervised image translation with large shape deformation to be presented at ECCV 2018.
New paper on deep convolutional scene synthesis models accepted to SIGGRAPH 2018.
Angela Dai's work on large-scale 3D scan completion accepted to CVPR 2018.
New paper on learning procedural models from examples accepted to Eurographics 2018.
Maxime Voisin's work on improved training for neural autoregressive data completion models accepted to the NIPS 2017 Bayesian Deep Learning Workshop.
New post about an algorithm for writing research papers.
Moved to Brown!
Interview about Neurally-Guided Procedural Models on the AI Guild podcast.
Posted tech report on deep amortized inference for probabilistic programs.
Neurally-Guided Procedural Models paper accepted to NIPS 2016.