A fascinating hypothesis is that human and animal intelligence could be explained by a few
principles (rather than an encyclopaedic list of heuristics). If that hypothesis was correct, we …

The predictive learning of spatiotemporal sequences aims to generate future images by
learning from the historical context, where the visual dynamics are believed to have modular …

Visual environments are structured, consisting of distinct objects or entities. These entities
have properties---visible or latent---that determine the manner in which they interact with one …

To help agents reason about scenes in terms of their building blocks, we wish to extract the
compositional structure of any given scene (in particular, the configuration and …

From an early age, humans perceive the visual world as composed of coherent objects with
distinctive properties such as shape, size, and color. There is great interest in building …

World models learn the consequences of actions in vision-based interactive systems.
However, in practical scenarios such as autonomous driving, there commonly exists …

Motion, measured via optical flow, provides a powerful cue to discover and learn objects in
images and videos. However, compared to using appearance, it has some blind spots, such …

We propose a new approach to learn to segment multiple image objects without manual
supervision. The method can extract objects form still images, but uses videos for …

The ability to discover abstract physical concepts and understand how they work in the world
through observing lies at the core of human intelligence. The acquisition of this ability is …

Visual scenes are composed of visual concepts and have the property of combinatorial
explosion. An important reason for humans to efficiently learn from diverse visual scenes is …