151 citations · 182 across the 5 of their papers we have counts for
5 papers
PushWorld: A benchmark for manipulation planning with tools and movable obstacles
Ken Kansky, Skanda Vaidyanath, Scott Swingle +3
While recent advances in artificial intelligence have achieved human-level performance in environments like Starcraft and Go, many physical reasoning tasks remain challenging for m…
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
Ken Kansky, Tom Silver, David A. Mély +7
The recent adaptation of deep neural network-based methods to reinforcement learning and planning domains has yielded remarkable progress on individual tasks. Nonetheless, progress…
Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data
Xinghua Lou, Ken Kansky, Wolfgang Lehrach +4
We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer traini…
GRED: Graph-Regularized 3D Shape Reconstruction from Highly Anisotropic and Noisy Images
Christian Widmer, Philipp Drewe, Xinghua Lou +3
Analysis of microscopy images can provide insight into many biological processes. One particularly challenging problem is cell nuclear segmentation in highly anisotropic and noisy…
Structured Learning from Partial Annotations
Xinghua Lou, Fred Hamprecht
Structured learning is appropriate when predicting structured outputs such as trees, graphs, or sequences. Most prior work requires the training set to consist of complete trees, g…