Methods › Computer Vision › Generative Models › NVAE
Nouveau VAE
NVAE
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
NVAE, or Nouveau VAE, is deep, hierarchical variational autoencoder. It can be trained with the original VAE objective, unlike alternatives such as VQ-VAE-2. NVAE’s design focuses on tackling two main challenges: (i) designing expressive neural networks specifically for VAEs, and (ii) scaling up the training to a large number of hierarchical groups and image sizes while maintaining training stability.
To tackle long-range correlations in the data, the model employs hierarchical multi-scale modelling. The generative model starts from a small spatially arranged latent variables as z₁ and samples from the hierarchy group-by-group while gradually doubling the spatial dimensions. This multi-scale approach enables NVAE to capture global long-range correlations at the top of the hierarchy and local fine-grained dependencies at the lower groups.
Additional design choices include the use of residual cells for the generative models and the encoder, which employ a number of tricks and modules to achieve good performance, and the use of residual normal distributions to smooth optimization. See the components section for more details.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 10 in the graph, strongest link: official). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2007.03898) is about this method is not checked.
Origin paper of this answer, arXiv:2007.03898 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 26 ran (of which 15 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 0 violated, 18 with no contract checked; 5 where Syntology's instrument failed) · 15 unverified (of 41 harvested samples) · 23 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 5 · with a code link: 3 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 5 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 5 of 5, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck 27 Jul 2022 · 0 repositories · arXiv:2207.13529
-
Alleviating Adversarial Attacks on Variational Autoencoders with MCMC 18 Mar 2022 · 1 repository · arXiv:2203.09940
-
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values 3 Mar 2022 · 1 repository · arXiv:2203.01993
-
NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection 8 Jan 2021 · 0 repositories · arXiv:2101.02908
-
NVAE: A Deep Hierarchical Variational Autoencoder 8 Jul 2020 · 10 repositories · arXiv:2007.03898Syntology official (archive's flag): 9 ran · 26 ran (of which 15 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 0 violated, 18 with no contract checked; 5 where Syntology's instrument failed) · 15 unverified (of 41 harvested samples) · 23 pointer-only (licence)
Tasks archive 2025-07-28
9 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Image Generation | 2 |
| Adversarial Attack | 1 |
| Anomaly Detection | 1 |
| Decoder | 1 |
| Diversity | 1 |
| Time Series | 1 |
| Time Series Analysis | 1 |
| Time Series Anomaly Detection | 1 |
| Unconditional Image Generation | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections