Natural language is often seen as the single factor that explains the cognitive singularity of
the human species. Instead, we propose that humans possess multiple internal languages …

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 …

Graph neural networks (GNNs) have emerged as a series of competent graph learning
methods for diverse real-world scenarios, ranging from daily applications like …

Numerous deep learning algorithms have been inspired by and understood via the notion of
information bottleneck, where unnecessary information is (often implicitly) minimized while …

A central challenge for cognitive science is to explain how abstract concepts are acquired
from limited experience. This has often been framed in terms of a dichotomy between …

Molecular representation learning lays the foundation for drug discovery. However, existing
methods suffer from poor out-of-distribution (OOD) generalization, particularly when data for …

Compositional generalization, the ability of an agent to generalize to unseen combinations
of latent factors, is easy for humans but hard for deep neural networks. A line of research in …

Deep neural networks perform well on classification tasks where data streams are iid and
labeled data is abundant. Challenges emerge with non-stationary training data streams …

The key to high-level cognition is believed to be the ability to systematically manipulate and
compose knowledge pieces. While token-like structured knowledge representations are …

Machine learning has long since become a keystone technology, accelerating science and
applications in a broad range of domains. Consequently, the notion of applying learning …