Uncertainty quantification (UQ) has increasing importance in the building of robust high-
performance and generalizable materials property prediction models. It can also be used in …

Predictive simulations are essential for applications ranging from weather forecasting to
material design. The veracity of these simulations hinges on their capacity to capture the …

While 3D body reconstruction methods have made remarkable progress recently, it remains
difficult to acquire the sufficiently accurate and numerous 3D supervisions required for …

Uncertainty Quantification (UQ) has gained traction in an attempt to fix the black-box nature
of Deep Learning. Specifically (medical) biosignals such as electroencephalography (EEG) …

Predictive uncertainty--a model's self-awareness regarding its accuracy on an input--is key
for both building robust models via training interventions and for test-time applications such …

Uncertainty quantification, once a singular task, has evolved into a spectrum of tasks,
including abstained prediction, out-of-distribution detection, and aleatoric uncertainty …

Short-term wind power forecasting has become a de facto tool to better facilitate the
integration of such renewable energy resources into modern power grids. Instead of point …

Inter-individual differences are studied in natural systems, such as fish, bees, and humans,
as they contribute to the complexity of both individual and collective behaviors. However …

We introduce a hyperbolic neural network approach to pixel-level active learning for
semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the …

Over the past decade, various artificial intelligence types have made significant progress in
petroleum reservoir modeling, from machine learning to deep learning. These data-driven …