Energy-based Generative Models
Energy-Based Generative Models is a class of generative models that defines the probability distribution of data through an energy function, distinguishing itself by modeling unnormalized probability densities whose values are derived from the negative exponential of energies assigned to configurations.
81
Publications
7.5K
Citations
199
Authors
78
Institutions
Publications per year
2017–2026
66
Parents
81
Energy-based Generative Adversarial Network
Junbo Zhao, Michaël Mathieu, Yann LeCun · arXiv (Cornell University) · 2016 · 895 citations · Full text
A Tutorial on Energy-Based Learning
Yann LeCun, Sumit Chopra, Raia Hadsell et al. · 2006 · 794 citations
NVAE: A Deep Hierarchical Variational Autoencoder
Arash Vahdat, Jan Kautz · arXiv (Cornell University) · 2020 · 378 citations · Full text
1–5 of 81
199
14
h-index
13
h-index
9
h-index
6
h-index
6
h-index
1–5 of 199
78
University of California, Los Angeles
Los Angeles, United States
14 h-index
51 publications
3K citations
Google (United States)
Mountain View, United States
5 h-index
7 publications
512 citations
Université de Montréal
Montreal, Canada
5 h-index
9 publications
286 citations
New York University
New York, United States
3 h-index
5 publications
317 citations
Bellevue Hospital Center
New York, United States
3 h-index
4 publications
99 citations
Nvidia (United Kingdom)
Reading, United Kingdom
3 h-index
5 publications
550 citations

Stevens Institute of Technology
Hoboken, United States
3 h-index
3 publications
137 citations
Stanford University
Stanford, United States
3 h-index
8 publications
646 citations
1–8 of 78
Repository · 41 publications · 3.1K citations
23
h-index
TPAMI · 4 publications · 1.8K citations
4
h-index
Conference · 3 publications · 119 citations
3
h-index
3 publications · 135 citations
3
h-index
Conference · 2 publications · 106 citations
2
h-index
1–5