Implicit planning has emerged as an elegant technique for combining learned models of the
world with end-to-end model-free reinforcement learning. We study the class of implicit …

… Additional model variants have been implemented and evaluated by Yulia Rubanova,
Andreea Deac and Beatrice Bevilacqua. In addition, Andreea advised the project on multi-task …

Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment
and accelerate research, helping scientists to generate hypotheses, design experiments, …

Deploying graph neural networks (GNNs) on whole-graph classification or regression tasks
is known to be challenging: it often requires computing node features that are mindful of both …

Complex or co-existing diseases are commonly treated using drug combinations, which can
lead to higher risk of adverse side effects. The detection of polypharmacy side effects is …

Antibodies are a critical part of the immune system, having the function of recognizing and
mediating the neutralization of undesirable molecules (antigens) for future destruction. Being …

Graph Neural Networks (GNNs) are the state-of-the-art model for machine learning on graph-structured
data. The most popular class of GNNs operate by exchanging information …

Learning to execute algorithms is a fundamental problem that has been widely studied. Prior
work (Veličković et al., 2019) has shown that to enable systematic generalisation on graph …

Antibodies are proteins in the immune system which bind to antigens to detect and neutralise
them. The binding sites in an antibody-antigen interaction are known as the paratope and …

Effectively and efficiently deploying graph neural networks (GNNs) at scale remains one of
the most challenging aspects of graph representation learning. Many powerful solutions have …