Papers › Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images

Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images

20 Nov 2020ICLR 2021 1arXiv:2011.10650archive 2025-07-28

Rewon Child

We present a hierarchical VAE that, for the first time, generates samples quickly while outperforming the PixelCNN in log-likelihood on all natural image benchmarks. We begin by observing that, in theory, VAEs can actually represent autoregressive models, as well as faster, better models if they exist, when made sufficiently deep. Despite this, autoregressive models have historically outperformed VAEs in log-likelihood. We test if insufficient depth explains why by scaling a VAE to greater stochastic depth than previously explored and evaluating it CIFAR-10, ImageNet, and FFHQ. In comparison to the PixelCNN, these very deep VAEs achieve higher likelihoods, use fewer parameters, generate samples thousands of times faster, and are more easily applied to high-resolution images. Qualitative studies suggest this is because the VAE learns efficient hierarchical visual representations. We release our source code and models at https://github.com/openai/vdvae.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples: 8 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 9: 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 4 ran (0 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 4 samples from 3 repositories, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

openai/vdvae officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 4 ran (4 instrument-failed) · 0 unverified report
ericl122333/latent-vae mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
j-towns/vdvae-jax mentioned on GitHubpytorchSyntology: not harvested report
lupalab/posterior-matching mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Discrete Representation Learning (arXiv:1711.00937; that paper's own run record: 64 ran (of which 35 constructed an object rather than computing a result; 60 with no instrument failure: 0 honoured, 0 violated, 60 with no contract checked; 4 where Syntology's instrument failed) · 16 unverified) and Posterior Matching for Arbitrary Conditioning (arXiv:2201.12414; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report
plai-group/ipa mentioned on GitHubpytorchSyntology: not harvested report
tcl9876/visual-vae mentioned on GitHubjaxSyntology: not harvested report
vvvm23/vdvae mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
EugenHotaj/pytorch-generative pytorchSyntology: 1 sample, 0 ran · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

9 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
3ran · our draft was wrong
3ran; the contract check could not run
1unverified

Licence: 4 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

openai/vdvae official repository 4 samples, 4 ran (4 instrument-failed) · 0 unverified
add_vae_arguments hps.py ran · our draft was wrong MIT (permissive) · a169b353d342ad7f · report fixture: signature parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-22
get_width_settings vae.py ran · our draft was wrong fingerprinted MIT (permissive) · 9419abf027f0115d · report fixture: signature width:int/0/int, s:str/0/str · returned defaultdict · level recorded 2026-09-22
pad_channels vae.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · dd095f22dc8304f0 · report fixture: signature t:Tensor/4/float, width:int/0/int · returned Tensor · level recorded 2026-09-22
parse_layer_string vae.py ran · our draft was wrong MIT (permissive) · 95d3df9fe1921426 · report fixture: signature s:str/0/str · returned list · level recorded 2026-09-22
ericl122333/latent-vae community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_evenly_spaced_indices vae/model.py ran · honoured contract fingerprinted no licence file found · pointer only · 2ec4359e4ba42b26 · report fixture: signature N:int/0/int, K:int/0/int · returned list · level recorded 2026-09-22
get_resolutions vae/model.py ran · honoured contract fingerprinted no licence file found · pointer only · 070ddf6b065864d3 · report fixture: signature max_res:int/0/int, num_res:int/0/int · returned list · level recorded 2026-09-22
vvvm23/vdvae community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
draw_gaussian_diag_samples vae.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 31e670f6fff8614d · report fixture: returned Tensor · level recorded 2026-09-22
EugenHotaj/pytorch-generative community (archive-listed) 1 sample, 0 ran · 1 unverified
reproduce in 6 papers pytorch_generative/models/vae/vd_vae.py unverified MIT (permissive) · 6e32683806d3201d · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
gaussian_analytical_kl repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · f8752a89ed52495c · report fixture: returned Tensor · level recorded, date not recorded

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation FFHQ 1024 x 1024 Very Deep VAE bits/dimension 2.42 #20 of 20 Archive leaderboard report
Image Generation FFHQ 256 x 256 Very Deep VAE bits/dimension 0.61 #50 of 51 Archive leaderboard report
Image Generation ImageNet 32x32 Very Deep VAE bpd 3.8 #24 of 35 Archive leaderboard report
Image Generation ImageNet 64x64 Very Deep VAE Bits per dim 3.52 #48 of 65 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Hierarchical VAEStochastic Depth

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