Training energy-based models (EBMs) with maximum likelihood estimation o...
Diffusion models in the literature are optimized with various objectives...
Classifier-free guided diffusion models have recently been shown to be h...
We present Imagen Video, a text-conditional video generation system base...
How to effectively represent camera pose is an essential problem in 3D
c...
One of the central problems in machine learning is domain adaptation. Un...
Network pruning is a method for reducing test-time computational resourc...
The grid cells in the mammalian medial entorhinal cortex exhibit strikin...
Learning energy-based model (EBM) requires MCMC sampling of the learned ...
This paper studies a training method to jointly estimate an energy-based...
Learning representations of data is an important problem in statistics a...
Dynamic patterns are characterized by complex spatial and motion pattern...
Neural networks are vulnerable to adversarial examples, i.e. inputs that...
First-order methods such as stochastic gradient descent (SGD) are curren...
This paper entertains the hypothesis that the primary purpose of the cel...
This paper studies the dynamic generator model for spatial-temporal proc...
This paper proposes a model for learning grid-like units for spatial
awa...
The pattern theory of Grenander is a mathematical framework where the
pa...
We propose a deformable generator model to disentangle the appearance an...
This paper proposes a 3D shape descriptor network, which is a deep
convo...
This paper proposes a minimal contrastive divergence method for learning...
This paper studies the cooperative training of two probabilistic models ...