Human communication often involves information gaps between the
interloc...
Despite the seeming success of contemporary grounded text generation sys...
Despite recent advances in natural language understanding and generation...
Supervised learning typically relies on manual annotation of the true la...
The operational flood forecasting system by Google was developed to prov...
In some puzzles, the strategy we need to use near the goal can be quite
...
Image classification models can depend on multiple different semantic
at...
Floods are among the most common and deadly natural disasters in the wor...
Accurate and scalable hydrologic models are essential building blocks of...
A challenging open question in deep learning is how to handle tabular da...
In this letter we propose a convex approach to learning expressive scala...
This paper is concerned with the defense of deep models against adversar...
Multitask learning, i.e. taking advantage of the relatedness of individu...
Effective riverine flood forecasting at scale is hindered by a multitude...
Learning hydrologic models for accurate riverine flood prediction at sca...
Complex classifiers may exhibit "embarassing" failures in cases that wou...
Modern retrieval systems are often driven by an underlying machine learn...
Structured prediction is a powerful framework for coping with joint
pred...
A serious problem in learning probabilistic models is the presence of hi...
Learning with hidden variables is a central challenge in probabilistic
g...
In recent years, there is a growing interest in learning Bayesian networ...
We consider learning continuous probabilistic graphical models in the fa...