In many ways, graphs are the main modality of data we receive from nature. This is due to
the fact that most of the patterns we see, both in natural and artificial systems, are elegantly …

Time series are the primary data type used to record dynamic system measurements and
generated in great volume by both physical sensors and online processes (virtual sensors) …

Large language models (LLMs) are shown to possess a wealth of actionable knowledge that
can be extracted for robot manipulation in the form of reasoning and planning. Despite the …

Global medium-range weather forecasting is critical to decision-making across many social
and economic domains. Traditional numerical weather prediction uses increased compute …

Scientific discovery and engineering design are currently limited by the time and cost of
physical experiments. Numerical simulations are an alternative approach but are usually …

Learning to predict agent motions with relationship reasoning is important for many
applications. In motion prediction tasks, maintaining motion equivariance under Euclidean …

We propose the geometry-informed neural operator (GINO), a highly efficient approach for
learning the solution operator of large-scale partial differential equations with varying …

Message passing neural networks (MPNNs) have been shown to suffer from the
phenomenon of over-squashing that causes poor performance for tasks relying on long …

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Recent advances of data-driven machine learning have revolutionized fields like computer
vision, reinforcement learning, and many scientific and engineering domains. In many real …