Papers › Neural Discrete Representation Learning

Neural Discrete Representation Learning

2 Nov 2017NeurIPS 2017 12arXiv:1711.00937archive 2025-07-28

Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Variational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discrete latent representation, we incorporate ideas from vector quantisation (VQ). Using the VQ method allows the model to circumvent issues of "posterior collapse" -- where the latents are ignored when they are paired with a powerful autoregressive decoder -- typically observed in the VAE framework. Pairing these representations with an autoregressive prior, the model can generate high quality images, videos, and speech as well as doing high quality speaker conversion and unsupervised learning of phonemes, providing further evidence of the utility of the learnt representations.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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

The archive's official repository (deepmind/sonnet) was not harvested; the 80 samples below come from 26 community repositories.

Syntology 80 code samples harvested from 26 repositories linked to this paper: 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. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 80 samples from 26 repositories, 64 ran (60 with no instrument failure; 4 where Syntology's instrument failed). 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 8 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

50 repositories listed; official and paper-mentioned ones first.

deepmind/sonnet officialtfSyntology: not harvested report
AntixK/PyTorch-VAE mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
AnzorGozalishvili/autoencoders_playground mentioned on GitHubSyntology: not harvested report
Geson-anko/VQ_AutoEncoder mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
HenningBuhl/VQ-VAE_Keras_Implementation mentioned on GitHubtfSyntology: not harvested report
MishaLaskin/vq-vae mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
MishaLaskin/vqvae mentioned on GitHubpytorchSyntology: not harvested report
StanislavParovoy/VQ-VAE-WaveNet mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
airalcorn2/vqvae-pytorch mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
andrecianflone/vector_quantization mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
archinetai/bitcodes-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
artem-gorodetskii/wikiart-latent-diffusion mentioned on GitHubpytorchSyntology: not harvested report
awei669/VQ-Font mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Few shot font generation via transferring similarity guided global style and... (arXiv:2309.00827; that paper's own run record: 14 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
bshall/VectorQuantizedCPC mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
bshall/ZeroSpeech mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
buaavrcg/LEGaussians mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
clementchadebec/benchmark_VAE mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Variational Inference with Normalizing Flows (arXiv:1505.05770; that paper's own run record: 21 ran (of which 13 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
dhgrs/chainer-VQ-VAE mentioned on GitHubSyntology: not harvested report
explainingai-code/VQVAE-Pytorch mentioned on GitHubpytorchSyntology: 7 samples, 6 ran (2 instrument-failed) · 1 unverified report
hiwonjoon/tf-vqvae mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
inzva/music-generation mentioned on GitHubMITSyntology: not harvested report
iomanker/VQVAE-TF2 mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
jackson-kang/pytorch-vae-tutorial mentioned on GitHubpytorchSyntology: not harvested report
jaywalnut310/Vector-Quantized-Autoencoders mentioned on GitHubtfSyntology: not harvested report
joh-fischer/PlantLDM mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
ks2labs/modules mentioned on GitHubpytorchSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
lupalab/posterior-matching mentioned on GitHubjaxSyntology: 4 samples, 0 ran · 4 unverified report
nadavbh12/VQ-VAE mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
nicolaffETHZ/Brain2Word_paper mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
opendrivelab/univla mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UniVLA: Learning to Act Anywhere with Task-centric Latent Actions (arXiv:2505.06111; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
rhoposit/icassp2021 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rsn870/VQ-VAE mentioned on GitHubpytorchSyntology: not harvested report
sisl/MultiAgentVariationalOcclusionInference mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (1 instrument-failed) · 2 unverified report
swasun/VQ-VAE-Speech mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
swasun/VQ-VAE-images mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
unixpickle/vq-draw mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
v-iashin/SpecVQGAN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
vignesh-creator/VectorQuantized-VAE mentioned on GitHubpytorchSyntology: not harvested report
yashgarg98/VQ-VAE mentioned on GitHubSyntology: not harvested report
yhy258/VariationalAutoEncoders-Pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Understanding disentangling in β-VAE (arXiv:1804.03599; that paper's own run record: 9 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; 7 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yjlolo/vae-audio mentioned on GitHubpytorchMITSyntology: 12 samples, 11 ran (0 instrument-failed) · 1 unverified report
EugenHotaj/pytorch-generative pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MADE: Masked Autoencoder for Distribution Estimation (arXiv:1502.03509; that paper's own run record: 5 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; 3 where Syntology's instrument failed) · 4 unverified), Neural Autoregressive Distribution Estimation (arXiv:1605.02226; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), Conditional Image Generation with PixelCNN Decoders (arXiv:1606.05328; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
karpathy/deep-vector-quantization pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Categorical Reparameterization with Gumbel-Softmax (arXiv:1611.01144; that paper's own run record: 12 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
keras-team/keras-io tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Forward-Forward Algorithm: Some Preliminary Investigations (arXiv:2212.13345; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
lucidrains/vector-quantize-pytorch pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Addressing Representation Collapse in Vector Quantized Models with One Linear Layer (arXiv:2411.02038; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 6 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
sarus-tech/tf2-published-models tfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
wayexists02/vqvae-pytorch-impl pytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
zer0sh0t/artificial_intelligence pytorchSyntology: not harvested 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

80 samples harvested: 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. “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.

4ran · our draft was wrong
60ran
16unverified

Licence: 32 of the 80 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 26 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. “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”. For 28 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Geson-anko/VQ_AutoEncoder community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Quantizing quantizing_layers.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 2332d2c1ae59a613 · report fixture: returned Quantizing · level recorded 2026-09-22
MishaLaskin/vq-vae community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Decoder in 210 papers models/vqvae.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7ec86ce9f1243c09 · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers models/vqvae.py ran · metamorphic tier: deterministic no licence file found · pointer only · 37323902f8998883 · report fixture: returned Encoder · level recorded 2026-09-22
ResidualStack models/vqvae.py ran · metamorphic tier: deterministic no licence file found · pointer only · 717b778f8ecfc744 · report fixture: returned ResidualStack · level recorded 2026-09-22
VectorQuantizer in 26 papers models/vqvae.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 04236f77961d2db4 · report fixture: returned VectorQuantizer · level recorded 2026-09-22
VQVAE models/vqvae.py unverified no licence file found · pointer only · 66a0dc4e92a4979d · report
StanislavParovoy/VQ-VAE-WaveNet community (archive-listed) 1 sample, 0 ran · 1 unverified
VQVAE model.py unverified no licence file found · pointer only · 90df58e23d19cc6e · report
airalcorn2/vqvae-pytorch community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
Decoder in 210 papers vqvae.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 6cff5e6be156f653 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Encoder in 278 papers vqvae.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 31f17da0e35924e8 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ResidualStack vqvae.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 9a0e3f52b1b95012 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SonnetExponentialMovingAverage vqvae.py ran Apache-2.0 (permissive) · a7bbba1a7d675924 · report fixture: signature value:Tensor/2/float · returned Tensor · level recorded 2026-09-24
VectorQuantizer in 26 papers vqvae.py ran fingerprinted Apache-2.0 (permissive) · 8b8f0e96d4c8976a · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-24
VQVAE vqvae.py unverified Apache-2.0 (permissive) · 3df5033bc998fdf6 · report
andrecianflone/vector_quantization community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Decoder in 210 papers vqvae.py ran fingerprinted no licence file found · pointer only · 4c2e3405d250cb33 · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers vqvae.py ran fingerprinted no licence file found · pointer only · b371a7a9f919c844 · report fixture: returned Encoder · level recorded 2026-09-22
Quantize vqvae.py ran no licence file found · pointer only · 11e9c619687afa02 · report fixture: returned Quantize · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
vqvae.py ran fingerprinted no licence file found · pointer only · e208e656b3429e2c · report fixture: returned ResBlock · level recorded 2026-09-22
VQVAE vqvae.py unverified no licence file found · pointer only · c3e34fc264fea0f3 · report
archinetai/bitcodes-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Bitcodes bitcodes_pytorch/bitcodes.py ran · metamorphic tier: deterministic MIT (permissive) · 81037b2a5a5b548e · report fixture: returned Bitcodes · level recorded 2026-09-22
bshall/VectorQuantizedCPC community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VQEmbeddingEMA model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a9d07171b60f51f8 · report fixture: returned VQEmbeddingEMA · level recorded 2026-09-22
bshall/ZeroSpeech community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VQEmbeddingEMA model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · b5071cb976519bd8 · report fixture: returned VQEmbeddingEMA · level recorded 2026-09-22
buaavrcg/LEGaussians community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VectorQuantizer in 26 papers preprocess/quantizer.py ran fingerprinted MIT (permissive) · 9c64b505481dc36b · report fixture: returned VectorQuantizer · level recorded 2026-09-22
explainingai-code/VQVAE-Pytorch community (archive-listed) 7 samples, 6 ran (2 instrument-failed) · 1 unverified
Decoder in 210 papers model/vqvae.py ran no licence file found · pointer only · e11e4311fbf78fb4 · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers model/vqvae.py ran fingerprinted no licence file found · pointer only · cbc53e73ec7ded92 · report fixture: returned Encoder · level recorded 2026-09-22
Quantizer in 10 papers model/vqvae.py ran fingerprinted no licence file found · pointer only · 61f7701b94565897 · report fixture: returned Quantizer · level recorded 2026-09-22
VQVAE model/vqvae.py ran fingerprinted no licence file found · pointer only · cae2955852764a22 · report fixture: returned VQVAE · level recorded 2026-09-22
get_decoder in 13 papers model/vqvae.py ran · our draft was wrong no licence file found · pointer only · 32ad87238c5e79f6 · report fixture: signature config:dict/0/? · returned Decoder · level recorded 2026-09-22
get_quantizer model/vqvae.py ran · our draft was wrong no licence file found · pointer only · fcbc4b1a03ccbcab · report fixture: signature config:dict/0/? · returned Quantizer · level recorded 2026-09-22
get_encoder in 45 papers model/vqvae.py unverified no licence file found · pointer only · a22596d18953971d · report
hiwonjoon/tf-vqvae community (archive-listed) 1 sample, 0 ran · 1 unverified
VQVAE model.py unverified no licence file found · pointer only · fc6668704a278e9f · report
iomanker/VQVAE-TF2 community (archive-listed) 1 sample, 0 ran · 1 unverified
VectorQuantizer in 26 papers VectorQuantizer.py unverified no licence file found · pointer only · 7e75344dc933124c · report
joh-fischer/PlantLDM community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
Decoder in 210 papers model/vqvae/vqvae.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 29d1b1a70747fecf · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Encoder in 278 papers model/vqvae/vqvae.py ran · metamorphic tier: invariant MIT (permissive) · b7ef8e42168ed9bc · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ResidualLayer in 5 papers model/vqvae/vqvae.py ran fingerprinted MIT (permissive) · c92e0eaec11f87ef · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
VQVAE model/vqvae/vqvae.py ran · metamorphic tier: deterministic MIT (permissive) · d26761dae4136be0 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-22
VectorQuantizer in 26 papers model/vqvae/vqvae.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 66c0ecce454f52da · report fixture: signature z:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ks2labs/modules community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
Decoder in 210 papers models/vqvae/model.py ran · metamorphic tier: deterministic MIT (permissive) · 9cef9b557ff5124b · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers models/vqvae/model.py ran · metamorphic tier: deterministic MIT (permissive) · 5dc946b372865ded · report fixture: returned Encoder · level recorded 2026-09-22
Residual in 24 papers models/vqvae/model.py ran · metamorphic tier: deterministic MIT (permissive) · 230f3bafb927fa9b · report fixture: returned Residual · level recorded 2026-09-22
ResidualStack models/vqvae/model.py ran · metamorphic tier: deterministic MIT (permissive) · 2826483ff96d8731 · report fixture: returned ResidualStack · level recorded 2026-09-22
VQVAE models/vqvae/model.py ran fingerprinted MIT (permissive) · 49e082f17ee0f50c · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-24
VectorQuantizer in 26 papers models/vqvae/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 42a9b84a1bbb0a02 · report fixture: returned VectorQuantizer · level recorded 2026-09-22
lupalab/posterior-matching community (archive-listed) 4 samples, 0 ran · 4 unverified
ConvResidualDecoder posterior_matching/models/vqvae.py unverified no licence file found · pointer only · 9a6d83ab3c03ff62 · report
ConvResidualEncoder posterior_matching/models/vqvae.py unverified no licence file found · pointer only · bdde96f49863b40f · report
ConvResidualStack posterior_matching/models/vqvae.py unverified no licence file found · pointer only · aee55bc39a8d091c · report
VQVAE posterior_matching/models/vqvae.py unverified no licence file found · pointer only · 44b6bd0978746277 · report
nadavbh12/VQ-VAE community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
NearestEmbed vq_vae/auto_encoder.py ran fingerprinted BSD-3-Clause (permissive) · 4db13c56150e213c · report fixture: signature x:Tensor/3/float, weight_sg:bool/0/bool · returned tuple · level recorded 2026-09-24
NearestEmbedFunc vq_vae/auto_encoder.py ran BSD-3-Clause (permissive) · 56b746f89213fdc4 · report fixture: returned NearestEmbedFunc · level recorded 2026-09-22
VQ_VAE vq_vae/auto_encoder.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · 811d0edff7823e5b · report fixture: returned VQ_VAE · level recorded 2026-09-22
nearest_embed vq_vae/auto_encoder.py ran · our draft was wrong BSD-3-Clause (permissive) · d25e16de44180a86 · report fixture: signature x:Tensor/3/float, emb:Tensor/2/float · returned tuple · level recorded 2026-09-22
nicolaffETHZ/Brain2Word_paper community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VQVAELayer models.py ran no licence file found · pointer only · 18395ffd69df1890 · report fixture: returned VQVAELayer · level recorded 2026-09-22
rhoposit/icassp2021 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VectorQuant layers/vector_quant.py ran MIT (permissive) · 4926226bc5727d02 · report fixture: returned VectorQuant · level recorded 2026-09-22
sisl/MultiAgentVariationalOcclusionInference community (archive-listed) 5 samples, 3 ran (1 instrument-failed) · 2 unverified
Decoder in 210 papers src/driver_sensor_model/models_cvae.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 5aeaa611b1aa19e0 · report fixture: signature z:Tensor/2/float · returned Tensor · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
src/driver_sensor_model/models_cvae.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · a7d565fc7647b7f9 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
sample_p src/driver_sensor_model/models_cvae.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 6ed722b4d3b12944 · report fixture: signature alpha:Tensor/1/float, batch_size:int/0/int · returned Tensor · level recorded 2026-09-22
Encoder in 278 papers src/driver_sensor_model/models_cvae.py unverified Apache-2.0 (permissive) · b06a9d10ea85ce50 · report
VAE in 29 papers src/driver_sensor_model/models_cvae.py unverified Apache-2.0 (permissive) · 1924bf1dbccafe70 · report
swasun/VQ-VAE-Speech community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VectorQuantizer in 26 papers src/models/vector_quantizer.py ran · metamorphic tier: deterministic MIT (permissive) · 76b559c1503ca76c · report fixture: returned VectorQuantizer · level recorded 2026-09-22
swasun/VQ-VAE-images community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VectorQuantizer in 26 papers src/vector_quantizer.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · fbd6f2f3cc98b66f · report fixture: returned VectorQuantizer · level recorded 2026-09-22
unixpickle/vq-draw community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Encoder in 278 papers vq_draw/encoder.py ran no licence file found · pointer only · 2e0e8c659d27a232 · report fixture: returned Encoder · level recorded 2026-09-22
v-iashin/SpecVQGAN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VectorQuantizer in 26 papers specvqgan/modules/vqvae/quantize.py ran fingerprinted MIT (permissive) · bf13977cfc8d3cda · report fixture: returned VectorQuantizer · level recorded 2026-09-22
yjlolo/vae-audio community (archive-listed) 12 samples, 11 ran (0 instrument-failed) · 1 unverified
approx_qy_x base/base_model.py ran MIT (permissive) · 56dc0f7a70802e2c · report fixture: signature z:Tensor/2/float, mu_lookup:callable/0/?, logvar_lookup:callable/0/?, n_component:int/0/int · returned tuple · level recorded 2026-09-26
fc in 16 papers model/model.py ran MIT (permissive) · f2450ca8951604d7 · report fixture: signature n_layer:int/0/int, n_channel:list/1/int, activation:str/0/str, batchNorm:bool/0/bool · returned Sequential · level recorded 2026-09-26
get_instance in 9 papers dataset/audio_transform.py ran MIT (permissive) · d21115129d752c6b · report fixture: signature module:callable/0/?, name:str/0/str, config:dict/0/? · returned LinearLayer · level recorded 2026-09-26
gmvae_loss model/loss.py ran MIT (permissive) · e051edb2ab2c496e · report fixture: signature output:Tensor/2/float, target:Tensor/2/float, logLogit_qy_x:Tensor/2/float, qy_x:Tensor/2/float, q_mu:Tensor/2/float, q_logvar:Tensor/2/float, mu_lookup:callable/0/?, logvar_lookup:callable/0/?, n_component:int/0/int · returned tuple · level recorded 2026-09-26
mse_loss in 73 papers
census: 8 implementations from 12 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
model/loss.py ran MIT (permissive) · 3b8e8d5673b757b1 · report fixture: signature output:Tensor/3/float, target:Tensor/3/float, avg_batch:bool/0/bool · returned Tensor · level recorded 2026-09-26
my_metric model/metric.py ran MIT (permissive) · fcdafb2d7a652e72 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int · returned float · level recorded 2026-09-24
my_metric2 model/metric.py ran fingerprinted MIT (permissive) · be926d5a1cd922e3 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, k:int/0/int · returned float · level recorded 2026-09-26
sampling_gaussian base/base_model.py ran fingerprinted MIT (permissive) · dc65914e8be186c4 · report fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float · returned tuple · level recorded 2026-09-26
spec_conv1d model/model.py ran MIT (permissive) · 93c25da3337bd3cd · report fixture: signature n_layer:int/0/int, n_channel:list/1/int, filter_size:list/1/int, stride:list/1/int · returned Sequential · level recorded 2026-09-26
spec_deconv1d model/model.py ran MIT (permissive) · 081ebe5df943cdc9 · report fixture: signature n_layer:int/0/int, n_channel:list/1/int, filter_size:list/1/int, stride:list/1/int · returned Sequential · level recorded 2026-09-26
vae_loss in 8 papers model/loss.py ran fingerprinted MIT (permissive) · afb08782fd097f05 · report fixture: signature q_mu:Tensor/2/float, q_logvar:Tensor/2/float, output:Tensor/2/float, target:Tensor/2/float · returned tuple · level recorded 2026-09-26
filter_file dataset/nsynth_subset.py unverified MIT (permissive) · 7e0c1e9c66dce9fd · report
sarus-tech/tf2-published-models community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
VQVAE vqvae/model.py ran Apache-2.0 (permissive) · a9ecf52cfae83fc0 · report fixture: returned VQVAE · level recorded 2026-09-22
VectorQuantizerEMA vqvae/model.py ran Apache-2.0 (permissive) · 63f246fab2a847d8 · report fixture: returned VectorQuantizerEMA · level recorded 2026-09-22
wayexists02/vqvae-pytorch-impl community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Encoder in 278 papers models/vqvae.py ran fingerprinted no licence file found · pointer only · 33fe2331161629b0 · report fixture: returned Encoder · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
models/vqvae.py ran fingerprinted no licence file found · pointer only · d14328d52ad612df · report fixture: returned ResBlock · level recorded 2026-09-22
ResTransposeBlock models/vqvae.py ran no licence file found · pointer only · dc26380ed75e55c0 · report fixture: returned ResTransposeBlock · level recorded 2026-09-22
Decoder in 210 papers models/vqvae.py unverified no licence file found · pointer only · 53be403a488d20dc · report
VqVae models/vqvae.py unverified no licence file found · pointer only · e81df514f25b789c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

26 assemblies on this paper: 26 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

26 sibling assemblies for Vector Quantised-Variational AutoEncoder (VQ-VAE) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 26 sibling assemblies; the other 14 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 26 siblings

  1. VectorQuantizer entry · level 1 · ran · 76b559c1503ca76c

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 26 siblings

  1. VectorQuantizer entry · level 1 · ran · fbd6f2f3cc98b66f

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 6 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 26 siblings

  1. VQVAE entry · level 0 · unverified · 66a0dc4e92a4979d
  2. Decoder model · level 1 · ran · 7ec86ce9f1243c09
  3. Encoder model · level 1 · ran · 37323902f8998883
  4. VectorQuantizer model · level 1 · ran · 04236f77961d2db4
  5. ResidualStack helper · level 1 · ran · 717b778f8ecfc744
  6. ResidualLayer helper · level 1 · ran · be684a447b37f7e7

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 26 siblings

  1. VectorQuantizer entry · level 0 · unverified · 7e75344dc933124c

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 26 siblings

  1. VQVAE entry · level 1 · ran · a9ecf52cfae83fc0
  2. VectorQuantizerEMA model · level 1 · ran · 63f246fab2a847d8

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 26 siblings

  1. VQEmbeddingEMA entry · level 1 · ran · a9d07171b60f51f8

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 26 siblings

  1. Bitcodes entry · level 1 · ran · 81037b2a5a5b548e

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 26 siblings

  1. Quantizing entry · level 1 · ran · 2332d2c1ae59a613

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 26 siblings

  1. VQEmbeddingEMA entry · level 1 · ran · b5071cb976519bd8

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 26 siblings

  1. VQVAE entry · level 1 · ran · 49e082f17ee0f50c
  2. Decoder model · level 1 · ran · 9cef9b557ff5124b
  3. Encoder model · level 1 · ran · 5dc946b372865ded
  4. VectorQuantizer model · level 1 · ran · 42a9b84a1bbb0a02
  5. ResidualStack model · level 1 · ran · 2826483ff96d8731
  6. Residual model · level 1 · ran · 230f3bafb927fa9b

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 26 siblings

  1. VQ_VAE entry · level 1 · ran · 811d0edff7823e5b
  2. NearestEmbed model · level 1 · ran · 4db13c56150e213c
  3. nearest_embed helper · level 1 · ran · our draft was wrong · d25e16de44180a86
  4. NearestEmbedFunc helper · level 1 · ran · 56b746f89213fdc4

harvested Assembly for Vector Quantised-Variational AutoEncoder (VQ-VAE) (graph method: Vector Quantised-Variational AutoEncoder (VQ-VAE)). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

one of 26 siblings

  1. VQVAE entry · level 0 · unverified · 44b6bd0978746277
  2. ConvResidualDecoder model · level 0 · unverified · 9a6d83ab3c03ff62
  3. ConvResidualEncoder model · level 0 · unverified · bdde96f49863b40f
  4. ConvResidualStack helper · level 0 · unverified · aee55bc39a8d091c
  1. VectorQuantizer · 60dcbfea532f4857 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. VectorQuant · 6c089fa2252db2dc · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. VQVAELayer · 836b3833e2d499ac · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. VqVae · 925f8bb2dfc6b213 · 5 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. VQVAE · 947b7f4619362f18 · 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. VQVAE · 9747ad9def579d9d · 7 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. VQVAE · 99e35257dee32963 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. Memory · 9f6dd4e6a12c26b0 · 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. Encoder · a52b61f5a2517f07 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. VectorQuantizer · ab167ae662813eb2 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. VQVAE · cbcb5c41abc79a15 · 6 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. VQVAE · cefa9424ccdfe9ea · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. VQVAE · d1e76c35296dad19 · 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  14. VAE · d57c317b00646457 · 5 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[25] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1711.00937") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: VQ-VAE

AdamBatch NormalizationConvolutionDilated Causal ConvolutionReLUResidual BlockResidual ConnectionVQ-VAE

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