Methods › Computer Vision › Likelihood-Based Generative Models › VQ-VAE

VQ-VAE

197 papers tagged archive 2025-07-28

Introduced by Aaron van den Oord et al. in Neural Discrete Representation Learning

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

VQ-VAE is a type of variational autoencoder that uses vector quantisation to obtain a discrete latent representation. It 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, ideas from vector quantisation (VQ) are incorporated. 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.

PaperSource

In Syntology about another paper, arXiv:2606.21970: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2606.21970, while the archive credits arXiv:1711.00937, so it does not say whether this method has code.

From the lookup's note on this name: The same name also belongs to “Vector Quantised-Variational AutoEncoder (VQ-VAE)”, a method in the paper “Neural Discrete Representation Learning” (arXiv:1711.00937, 7,848 citations), which the lookup finds cited far more than the paper this answer is about (citations not recorded), so this answer may be about a different sense of the name. For arXiv:1711.00937: its page on this site · ask the lookup about it.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:2606.21970 (its page on Syntology).

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.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 197 · with a code link: 82 · where Syntology ran a sample: 35 (32 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (35 of 197 tagged: 32 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 197, 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.

Tasks archive 2025-07-28

20 shown of 171 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Quantization30
Decoder28
Image Generation23
Representation Learning17
Motion Generation13
Language Modelling12
Motion Synthesis11
Image Reconstruction10
Language Modeling10
Speech Synthesis10
Disentanglement7
Video Generation7
Clustering6
Denoising6
Diversity6
Music Generation6
Text-to-Image Generation6
Transfer Learning6
Large Language Model5
Self-Supervised Learning5

Usage over time archive 2025-07-28

Papers per year tagged with VQ-VAE: 2017 to 2025, peak 46 46 0 2017: 1 paper 2017 2018: 2 papers 2018 2019: 6 papers 2019 2020: 19 papers 2020 2021: 29 papers 2021 2022: 31 papers 2022 2023: 46 papers 2023 2024: 41 papers 2024 2025: 22 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (197 dated). Bars are counts, not a trend claim.

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

Likelihood-Based Generative ModelsGenerative Models

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