Causal reasoning is a crucial part of science and human intelligence. In order to discover
causal relationships from data, we need structure discovery methods. We provide a review …

The world contains not only objects and features (red apples, glass bowls, wooden tables),
but also relations holding between them (apples contained in bowls, bowls supported by …

The visual world can be parsimoniously characterized in terms of distinct entities with sparse
interactions. Discovering this compositional structure in dynamic visual scenes has proven …

Contemporary neural networks still fall short of human-level generalization, which extends
far beyond our direct experiences. In this paper, we argue that the underlying cause for this …

Object-centric representations are a promising path toward more systematic generalization
by providing flexible abstractions upon which compositional world models can be built …

This article does not describe a working system. Instead, it presents a single idea about
representation that allows advances made by several different groups to be combined into …

Existing 3D-aware image synthesis approaches mainly focus on generating a single
canonical object and show limited capacity in composing a complex scene containing a …

Training on large-scale graphs has achieved remarkable results in graph representation
learning, but its cost and storage have attracted increasing concerns. Existing graph …

Advances in unsupervised learning of object-representations have culminated in the
development of a broad range of methods for unsupervised object segmentation and …

Although deep reinforcement learning has become a promising machine learning approach
for sequential decision-making problems, it is still not mature enough for high-stake domains …