Home › Code › VectorQuantizer

VectorQuantizer

Syntologyentry name in harvested coderead from the graph 2026-09-24

VectorQuantizer appears in the code Syntology harvested for 26 papers, as 34 distinct code bodies found in 34 places (a place is one code body under one paper). At least one of them ran in 19 of the papers; 18 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named VectorQuantizer do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 26 of the 34 distinct code bodies named VectorQuantizer; 8 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
26ran
8unverified
18fingerprinted

Licence is a property of each copy, so it is counted per place: 15 of the 34 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

26 papers shown of 26, newest first; 34 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 8 papers added by Syntology. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
ENSEMBITS: an alphabet of protein conformational ensembles added by Syntology 2026-05 (from id) OliverLaboratory/Ensembits_release/ensembits/tokenizer.py 49fdbdbba8440b92 unverified MIT (permissive)
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion added by Syntology 2026-04 (from id) mikumifa/GS-Quant/codebook/rqvae.py 26dc0a05c9ee3ead ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive)
SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcasting added by Syntology 2026-03 (from id) nstavr04/MasterThesisSnellius/SmaAT-QMix-UNet/models/SmaAT_UNet_VQ_lightning.py 536271aae35f2e3b ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only
VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation added by Syntology 2026-01 (from id) script-Yang/VQ-Seg/model/semseg/dpt.py 72fa99cc5ece854c ran fingerprinted MIT (permissive)
ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation added by Syntology 2026-01 (from id) Kwai-Kolors/ResTok/modeling/restok.py ae6827aeaa6c2f91 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Memory Bank Compression for Continual Adaptation of Large Language Models added by Syntology 2026-01 (from id) Thomkat/MBC/models/modules/membank_comp.py 1dc5a9bfd833f381 ran · metamorphic tier: deterministic fingerprinted MIT (permissive)
D 3 QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection added by Syntology 2025-10 (from id) Zhangyr2022/D3QE/networks/D3QE.py e11ea5361acefa3a unverified MIT (permissive)
RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation added by Syntology 2025-09 (from id) reczoo/RecBase/models/clvae.py d043eebe21f798de ran fingerprinted licence not identified · pointer only
Hita: Holistic Tokenizer for Autoregressive Image Generation 3 Jul 2025 CVMI-Lab/Hita/hita/tokenizer/tokenizer_image/vq_model.py 34bc3c152c7cea14 unverified MIT (permissive)
AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model 5 Jun 2025 ali-vilab/alitok/modeling/alitok.py 8c5d87429839addc ran · metamorphic tier: deterministic no licence file found · pointer only
GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning 22 May 2025 gogoduan/got-r1/src/models/vq_model.py 177a67c6ea19650c ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation 11 Apr 2025 SilentView/GigaTok/tokenizer/tokenizer_image/vq/vq_vit_model.py 03697fde0e20d494 ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only
Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing 17 Mar 2025 Jiayi-Fu/IPC-Dehaze/basicsr/archs/dehazeToken_arch.py d5c7da63d4b432a2 ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only
HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model 17 Mar 2025 yayafengzi/LMM-HiMTok/himt/himt.py 9d5d0b05c060bba6 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
FlowTok: Flowing Seamlessly Across Text and Image Tokens 13 Mar 2025 bytedance/1d-tokenizer/modeling/titok.py c604f5049ddf0f34 ran Apache-2.0 (permissive)
UniTok: A Unified Tokenizer for Visual Generation and Understanding 27 Feb 2025 foundationvision/unitok/models/unitok.py 150dd2792a2bcac8 ran · metamorphic tier: deterministic MIT (permissive)
PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning 11 Feb 2025 angelvillar96/PlaySlot/src/models/Predictors/LatentAction.py 32667968d7719805 unverified no licence file found · pointer only
GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation 17 Oct 2024 chenzRG/GeSubNet/model/SELM_NN.py 32a0c8194804470b unverified no licence file found · pointer only
Return of Unconditional Generation: A Self-supervised Representation Generation Method 6 Dec 2023 LTH14/rcg/pixel_generator/mage/models_mage.py 9d2f5c397afb9f4b ran fingerprinted MIT (permissive)
Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond 18 Jul 2023 TencentARC/GFPGAN/gfpgan/archs/restoreformer_arch.py fe02c4750d678be8 ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only
RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors 8 Apr 2023 RQ-Wu/RIDCP_dehazing/basicsr/archs/dehaze_vq_weight_arch.py 6a91256c000435ed unverified licence not identified · pointer only
Diversity-Measurable Anomaly Detection 9 Mar 2023 FlappyPeggy/DMAD/DMAD-PDM/model/final_future_prediction_avenue.py ceaedbec84a683b3 ran no licence file found · pointer only
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization 16 May 2022 sony/sqvae/vision/quantizer.py 529baf7c9e2e4576 unverified Apache-2.0 (permissive)
AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation 17 Mar 2022 yccyenchicheng/AutoSDF/models/networks/pvqvae_networks/auto_encoder.py 3f682dbc70afb38f ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only
Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE 18 Mar 2021 wuyx517/VQVAE_image_inpainting/model/vqvae.py 4bfddced8570d768 ran no licence file found · pointer only
Neural Discrete Representation Learning 2 Nov 2017 swasun/VQ-VAE-Speech/src/models/vector_quantizer.py 76b559c1503ca76c ran · metamorphic tier: deterministic MIT (permissive)
Neural Discrete Representation Learning 2 Nov 2017 swasun/VQ-VAE-images/src/vector_quantizer.py fbd6f2f3cc98b66f ran · metamorphic tier: deterministic fingerprinted MIT (permissive)
Neural Discrete Representation Learning 2 Nov 2017 MishaLaskin/vq-vae/models/vqvae.py 04236f77961d2db4 ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only
Neural Discrete Representation Learning 2 Nov 2017 ks2labs/modules/models/vqvae/model.py 42a9b84a1bbb0a02 ran · metamorphic tier: deterministic fingerprinted MIT (permissive)
Neural Discrete Representation Learning 2 Nov 2017 buaavrcg/LEGaussians/preprocess/quantizer.py 9c64b505481dc36b ran fingerprinted MIT (permissive)
Neural Discrete Representation Learning 2 Nov 2017 v-iashin/SpecVQGAN/specvqgan/modules/vqvae/quantize.py bf13977cfc8d3cda ran fingerprinted MIT (permissive)
Neural Discrete Representation Learning 2 Nov 2017 airalcorn2/vqvae-pytorch/vqvae.py 8b8f0e96d4c8976a ran fingerprinted Apache-2.0 (permissive)
Neural Discrete Representation Learning 2 Nov 2017 joh-fischer/PlantLDM/model/vqvae/vqvae.py 66c0ecce454f52da ran · metamorphic tier: invariant fingerprinted MIT (permissive)
Neural Discrete Representation Learning 2 Nov 2017 iomanker/VQVAE-TF2/VectorQuantizer.py 7e75344dc933124c unverified no licence file found · pointer only

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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