Abstract “Thinking in pictures,”[1] ie, spatial-temporal reasoning, effortless and
instantaneous for humans, is believed to be a significant ability to perform logical induction …

Spatial-temporal reasoning is a challenging task in Artificial Intelligence (AI) due to its
demanding but unique nature: a theoretic requirement on representing and reasoning …

Modern neural network architectures can leverage large amounts of data to generalize well
within the training distribution. However, they are less capable of systematic generalization …

A disentangled representation encodes information about the salient factors of variation in
the data independently. Although it is often argued that this representational format is useful …

A fundamental component of human vision is our ability to parse complex visual scenes and
judge the relations between their constituent objects. AI benchmarks for visual reasoning …

We present a principled approach to uncover the structure of visual data by solving a novel
deep learning task coined visual permutation learning. The goal of this task is to find the …

Abstract visual reasoning (AVR) domain encompasses problems solving which requires the
ability to reason about relations among entities present in a given scene. While humans …

Humans have a remarkable capacity to draw parallels between concepts, generalising their
experience to new domains. This skill is essential to solving the visual problems featured in …

We present the MAC network, a novel fully differentiable neural network architecture,
designed to facilitate explicit and expressive reasoning. MAC moves away from monolithic …

Is intelligence realized by connectionist or classicist? While connectionist approaches have
achieved superhuman performance, there has been growing evidence that such task …