Modern climate projections lack adequate spatial and temporal resolution...
To balance quality and cost, various domain areas of science and enginee...
Recent work has shown that simple linear models can outperform several
T...
Understanding player shooting profiles is an essential part of basketbal...
Despite the success of equivariant neural networks in scientific
applica...
Graph Transformer (GT) recently has emerged as a new paradigm of graph
l...
Accurate uncertainty measurement is a key step to building robust and
re...
Generation of drug-like molecules with high binding affinity to target
p...
Science and engineering fields use computer simulation extensively. Thes...
In mathematical optimization, second-order Newton's methods generally
co...
Existing gradient-based optimization methods update the parameters local...
Trajectory prediction is a core AI problem with broad applications in
ro...
Artificial intelligence (AI) and machine learning (ML) are expanding in
...
Deep probabilistic forecasting is gaining attention in numerous applicat...
Identifying novel drug-target interactions (DTI) is a critical and rate
...
Learning the dynamics of spatiotemporal events is a fundamental problem....
Existing equivariant neural networks for continuous groups require
discr...
Stochastic simulations such as large-scale, spatiotemporal, age-structur...
Deep learning is gaining increasing popularity for spatiotemporal
foreca...
We take the first step in using vehicle-to-vehicle (V2V) communication t...
Image recovery from compressive measurements requires a signal prior for...
Current deep learning models for dynamics forecasting struggle with
gene...
We introduce DeepGLEAM, a hybrid model for COVID-19 forecasting. DeepGLE...
How can we learn a dynamical system to make forecasts, when some variabl...
Trajectory prediction is a critical part of many AI applications, for
ex...
We present a deep imitation learning framework for robotic bimanual
mani...
Missing data poses significant challenges while learning representations...
Locating the source of an epidemic, or patient zero (P0), can provide
cr...
Mean aortic pressure is a major determinant of perfusion in all organ
sy...
Efficient and interpretable spatial analysis is crucial in many fields s...
Training machine learning models that can learn complex spatiotemporal
d...
While deep learning has shown tremendous success in a wide range of doma...
To deepen our understanding of graph neural networks, we investigate the...
Missing value imputation is a fundamental problem in modeling spatiotemp...
Precise trajectory control near ground is difficult for multi-rotor dron...
We study the problem of learning latent feature models (LFMs) for tensor...
High-dimensional tensor models are notoriously computationally expensive...
Low-rank tensor regression, a new model class that learns high-order
cor...
Spatiotemporal forecasting has various applications in neuroscience, cli...
A challenge in training discriminative models like neural networks is
ob...