In contrastive representation learning, data representation is trained s...
Out-of-Distribution (OOD) generalization problem is a problem of seeking...
Learning controllable and generalizable representation of multivariate d...
Meta-Learning is a family of methods that use a set of interrelated task...
Practical reinforcement learning problems are often formulated as constr...
The purpose of this study is to introduce new design-criteria for
next-g...
Recomputation algorithms collectively refer to a family of methods that ...
What is the role of unlabeled data in an inference problem, when the pre...
Hyperbolic space is a geometry that is known to be well-suited for
repre...
Recently, Graph Neural Networks (GNNs) are trending in the machine learn...
We present a novel CNN-based image editing method that allows the user t...
One of the challenges in the study of generative adversarial networks is...
We propose a novel, projection based way to incorporate the conditional
...
We propose a new regularization method based on virtual adversarial loss...
We propose local distributional smoothness (LDS), a new notion of smooth...
As a technology to read brain states from measurable brain activities, b...
We present a novel algorithm (Principal Sensitivity Analysis; PSA) to an...