Pith. sign in

Paper Citation Record · LEDGER

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization

As of 6 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 3 inbound Pith citation observations for arXiv:2509.10140.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.10140 v1

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T18:12:48.666757Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T09:39:33.755572Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T05:27:39.704413Z

Reference resolution

59 of 59 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved58
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ed32ebae-949d-41b8-96de-4a4fde58e9bf · outbound

This paper cites write newline.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:44.455615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:44.455615Z digest=sha256:f988e0e2970b0b31ee09a5f9fe6ddf3c68e6621c4515b617f97db036cba0806c

Observation 2f67d640-cc1d-4278-bd5d-963198d7fc23 · outbound

This paper cites Large-dit-imagenet.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Large-dit-imagenet

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:44.549933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:44.549933Z digest=sha256:e9c49d974a685979f94b65894b06e9424876850527e545ff59dfe52c32505aec

Observation 05bf05b2-3367-46a2-9331-c37f12e0ea8e · outbound

This paper cites Qwen Technical Report.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Qwen Technical Report

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:44.625003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:44.625003Z digest=sha256:5144c9240b57a72cc7473ee32fd48266c805045782f4f25696df91941de95ca9

Observation 677a2059-029f-463f-a91a-efd53ef894ea · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:44.717741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:44.717741Z digest=sha256:7dfe9a4f87c646497620c80bebcf2724d5b76cf6cd8d1dc95f347f21aa8fc21f

Observation 3c0ec79f-fd75-4c61-a6e5-5c069766c453 · outbound

This paper cites Large Scale GAN Training for High Fidelity Natural Image Synthesis.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Large Scale GAN Training for High Fidelity Natural Image Synthesis

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:44.810505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:44.810505Z digest=sha256:c05978ac3b0386dd1cb0c8ae35faa67ec33c7e411168785325ea8d4beb62db78

Observation c62f0724-8fc5-49eb-8fb4-262218c28c2f · outbound

This paper cites Language models are few-shot learners.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Language models are few-shot learners

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:44.889358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:44.889358Z digest=sha256:49e6392772f33f71bdc490c790aa9316999b4588bd4a2077b3579b356841c40e

Observation b61311a5-53c9-46dd-a42c-f7d93de3b223 · outbound

This paper cites an unresolved cited work.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Unresolved cited work

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:44.989793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:44.989793Z digest=sha256:703ffde787eea2dbeaf63160cb86e0d3101139ba0d8ccf9998b757e27ec55740

Observation 5ba00256-c63d-4724-8936-6b986b4e7f54 · outbound

This paper cites Generative pretraining from pixels.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Generative pretraining from pixels

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.050577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.050577Z digest=sha256:bc2a6b0ecb4b70221b97e6e86caaed2fc19ff84a78ae4ea3189b3a091fb864a4

Observation 2bcbc62a-7e29-48a3-aae3-3fad01fee5ca · outbound

This paper cites Image N et: A large-scale hierarchical image database.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Image N et: A large-scale hierarchical image database

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.123223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.123223Z digest=sha256:985ce8af57d5ad35426ac86a1ffc4b0eeebc09a7ce761f62281dd81298115619

Observation 453fd2f5-6048-48f0-b1e3-2586b93e8411 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.198607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.198607Z digest=sha256:ff092ab08c004cd80f732e0a32753a0d4ce542d8c3075429bc6ed005d01e5c16

Observation 407e10c1-68bf-49e3-96ef-693007ceda19 · outbound

This paper cites Diffusion models beat gans on image synthesis.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Diffusion models beat gans on image synthesis

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.263732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.263732Z digest=sha256:ba7ffabbd14bf9150b4f4e6faa2d25ceb6bd491b5ecbd8e2eadf444a1b90aea0

Observation ffc0ae6b-53e7-41b9-b777-c28e31aea145 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization An image is worth 16x16 words: Transformers for image recognition at scale

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.335486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.335486Z digest=sha256:65247112ecc4af02dfab9c52a99c3c7aa13dbe2496157cba6a01a601c47b60a5

Observation 4e27dcc3-8f38-44c9-bb76-c7d668eec08c · outbound

This paper cites Taming transformers for high-resolution image synthesis.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Taming transformers for high-resolution image synthesis

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.382165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.382165Z digest=sha256:f9616d5b20ea00db8b7b4de3660ac77737c328e46ec78427bc4d5992b38e064c

Observation 26f0ca7c-45e5-4344-8ae2-0e73958eb24a · outbound

This paper cites The Llama 3 Herd of Models.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization The Llama 3 Herd of Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.470785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.470785Z digest=sha256:bd09eac30fcb57123092c58147a711b34208db2d5e49eebceb8b28be4f4df449

Observation 7f3a140c-dd9a-4f8f-8a2d-5a2af208e6c6 · outbound

This paper cites Denoising diffusion probabilistic models.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Denoising diffusion probabilistic models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.561435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.561435Z digest=sha256:034f30c47634aad2b0c51b82474c6e90e343e94ebc285af7c516b9ee458fcb13

Observation 86a6802d-e4c8-4228-883f-e46364dd7da0 · outbound

This paper cites Cascaded diffusion models for high fidelity image generation.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Cascaded diffusion models for high fidelity image generation

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.659172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.659172Z digest=sha256:e0120806dcac30002f2c7fd15cde11ac1303ab519b509f08fbceb0e0c194caa7

Observation 7cfeb22c-d003-480a-b986-ebe89c637fb3 · outbound

This paper cites Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized networks.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized networks

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.751846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.751846Z digest=sha256:8b7f841ed6e5b437534c5c36564886025c430bfbb4a62e61c0380491a37688ac

Observation fce15510-2ac7-4d24-84d5-83fbf74c88dd · outbound

This paper cites an unresolved cited work.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Unresolved cited work

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.810190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.810190Z digest=sha256:eb755178a11c3838d1b361881efb7a7cd1e84747936340425b9cae33fc5ee602

Observation 8e6af703-fd1f-43a2-95e6-6fb4ff1d15f6 · outbound

This paper cites Scaling up gans for text-to-image synthesis.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Scaling up gans for text-to-image synthesis

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.860281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.860281Z digest=sha256:2946232c2201f9509d973181972da3c0b5a0d52ae7bf80bd6834484372627b07

Observation 89d1cdd7-5c99-490f-9a07-6938d7ccee65 · outbound

This paper cites Auto-Encoding Variational Bayes.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Auto-Encoding Variational Bayes

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.923377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.923377Z digest=sha256:1c17256e3ade11cbae576bb243c0766bd1dcce1f068756f63ca1139895b85115

Observation be6717f7-c37b-4396-ad3e-ccfc206a61ec · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Adam: A Method for Stochastic Optimization

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:45.997737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:45.997737Z digest=sha256:f8b0664ff6b0caf91b48c38aa205e58bb7dec3cbe678fcbf2091b61e2597c62e

Observation 0682fba3-6a86-4519-87bc-e44b1bc805b6 · outbound

This paper cites The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.060491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.060491Z digest=sha256:52ab5b51a117371b7302545606254b09c58e2835291cdeaa0e6d53c0b625beec

Observation ab52ab92-ebd7-4180-8e7c-7f4fdc56879b · outbound

This paper cites Laion-coco 600m.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Laion-coco 600m

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.110344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.110344Z digest=sha256:5b222da7590bcd02c283058a55abe2803fbf46dc8662d32de2cbcd557c11f619

Observation 7af1878d-7f8b-4266-9e2e-128f9716ea1c · outbound

This paper cites Robust training of vector quantized bottleneck models.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Robust training of vector quantized bottleneck models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.161970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.161970Z digest=sha256:3565a2a07eda429674ce75974dc4250a4d521113050c75578e3664b1051cc395

Observation fda13932-b51f-45b8-9c0f-b35896ab5190 · outbound

This paper cites Autoregressive image generation using residual quantization.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Autoregressive image generation using residual quantization

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.238435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.238435Z digest=sha256:57ef06c1607ff5dea6105cd5018d3afd288d584ecd92a8d8383c8af038f8129a

Observation 0882d2e5-5fb7-4928-8e63-a45a1d1aaa23 · outbound

This paper cites Return of unconditional generation: A self-supervised representation generation method.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Return of unconditional generation: A self-supervised representation generation method

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.313796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.313796Z digest=sha256:b513a4b6a249908b676fb3127ab0721619e0c1708cb3baa30fccc149e3ee6b41

Observation 446f4224-f419-4f9c-8afb-694c7fff1172 · outbound

This paper cites Autoregressive Image Generation without Vector Quantization.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Autoregressive Image Generation without Vector Quantization

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.413499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.413499Z digest=sha256:db6c7c8a2798e1fddd2d479d1b5669cb76ee05cd50ae5f5a7bfc74b0aa6791f1

Observation d5e50374-a2b9-449f-87d5-ed9edc794b65 · outbound

This paper cites Flow Matching for Generative Modeling.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Flow Matching for Generative Modeling

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.496749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.496749Z digest=sha256:d22d37f9ff51ec11bc6a553b7ad35b67977657c8d706890d9e3c0ae77935466a

Observation c4f05df4-2edf-460d-a1ef-5bd97dc6147c · outbound

This paper cites Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.580994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.580994Z digest=sha256:eace168b59dff729aab0d5871e87d229e99946b795a241b47d2182bcaa1ab723

Observation 6b1eb43a-6fe1-494c-bde8-b554f9d75662 · outbound

This paper cites Unitok: A unified tokenizer for visual generation and understanding.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Unitok: A unified tokenizer for visual generation and understanding

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.684451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.684451Z digest=sha256:9b69c8cd4bf64d2e6e00d04fd65519af879650388914f5068dda8d61b140f981

Observation 8528b6f5-21f6-4aa4-8087-3840642fe6f1 · outbound

This paper cites Finite Scalar Quantization: VQ-VAE Made Simple.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Finite Scalar Quantization: VQ-VAE Made Simple

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.771609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.771609Z digest=sha256:d0f87e41e0f87da8287ce0cebee831e2c39e36df465c7b21c588c665f9254f10

Observation 5da56636-ee7b-4ba6-bb5d-87f26279110c · outbound

This paper cites RandAR: Decoder-only Autoregressive Visual Generation in Random Orders.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization RandAR: Decoder-only Autoregressive Visual Generation in Random Orders

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.841576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.841576Z digest=sha256:ff686db97ff57a8009634edfeb848a66d81bb453e951240740ddacaaf0a7e23f

Observation 6ab251cf-4b09-455d-a0f6-4d5ea18bd7ac · outbound

This paper cites Scalable diffusion models with transformers.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Scalable diffusion models with transformers

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.922273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.922273Z digest=sha256:0bdb58285bf7e4b2346231d06c0d8ecd8bad29799738dd194c13933e85fdffab

Observation 26e04914-b8fb-4a0f-9f15-669184b67ead · outbound

This paper cites Improving language understanding by generative pre-training.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Improving language understanding by generative pre-training

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:46.980867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:46.980867Z digest=sha256:62e63eea36fdad88307f0832d3f4d5a3302f0ff24634f4ba66b95f2cdbf914fa

Observation e160463f-953f-44da-ac50-eba76c7f0139 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Learning transferable visual models from natural language supervision

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.061086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.061086Z digest=sha256:4302f614fc45398630c97d232ded3fa1f20cd4b0c86f97d035580ff451c065ba

Observation 449e2d80-d8cc-4972-ac8d-b13651eda255 · outbound

This paper cites Zero-shot text-to-image generation.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Zero-shot text-to-image generation

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.141933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.141933Z digest=sha256:516d7f23dcc847723cedb51baad37cca50d4a0fcfe3b693921370e669ad0a42e

Observation 0974a938-b5ef-4773-8b38-8ba879f1bd5d · outbound

This paper cites Generating diverse high-fidelity images with vq-vae-2.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Generating diverse high-fidelity images with vq-vae-2

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.205491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.205491Z digest=sha256:5439de70bfb600615792dc52824c5626756a1b15a7f7524b556f53b375be8e8d

Observation df4d16d9-d29d-4875-b3a7-2a56a8aa15dd · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization High-resolution image synthesis with latent diffusion models

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.246970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.246970Z digest=sha256:7af8dda21030bb0e373ba00bccd8bfcc02f6d870a961f0006c4ebe8419bc3984

Observation 9eb1b2cf-0d10-4a7f-b5f8-d3878639a886 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization High-resolution image synthesis with latent diffusion models

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.329693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.329693Z digest=sha256:52e5c9cf70f30cb3aabaed1bfc0ac3a98d8073d2374d4b200bab8f64e85d9be7

Observation a80b09fb-9c25-4eb7-8583-5ede8ae57cdf · outbound

This paper cites Stylegan-xl: Scaling stylegan to large diverse datasets.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Stylegan-xl: Scaling stylegan to large diverse datasets

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.389768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.389768Z digest=sha256:43eb05bdc8b4ab2e5bcb3eca7f120f559fd9ce7ea5fec57d4a18b098ea209f01

Observation 84c704ae-008d-48e2-9e95-1752a04f3115 · outbound

This paper cites Scalable Image Tokenization with Index Backpropagation Quantization.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Scalable Image Tokenization with Index Backpropagation Quantization

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.447503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.447503Z digest=sha256:d28f3dcf35632087f40db88f237cad9927d3c35674e85819dfab15915743c543

Observation 113d149d-b37f-4560-849c-6258a66f0ce6 · outbound

This paper cites Denoising Diffusion Implicit Models.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Denoising Diffusion Implicit Models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.506172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.506172Z digest=sha256:7c604b681686d18595a40b7d00a922d5a163cf99ac1def358c28c0f8559c0d11

Observation 8d511910-4ad0-401d-8630-a4616be7a80e · outbound

This paper cites Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.561520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.561520Z digest=sha256:5eae6b11b0539f23650c6a4d46c92c5cbe19291972b9c59a5359a9ff87a70ec7

Observation e72b48e1-f76a-42fb-86b3-dcad5db7bf7e · outbound

This paper cites Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.607231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.607231Z digest=sha256:f5629e9822fd9462ca2b15f08eead9841a6deb19d37221c41822103d9ea2c6c3

Observation da219bac-86b1-44e2-935c-4ed412fce074 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization LLaMA: Open and Efficient Foundation Language Models

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.682959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.682959Z digest=sha256:875af04d1a4cdfbb5990447449ef169ff775a33b63b9540e5e7952c44eb73940

Observation 36edb0f2-756a-42d4-9789-a8e4a60d1746 · outbound

This paper cites Conditional image generation with pixelcnn decoders.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Conditional image generation with pixelcnn decoders

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.737180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.737180Z digest=sha256:4cbfa24dd6fc57a739409af52804eb21828f84de3da44e884aab2445a74c1609

Observation 951b700a-5d79-4cf3-b4da-e752e5bb74a7 · outbound

This paper cites Neural discrete representation learning.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Neural discrete representation learning

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.817518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.817518Z digest=sha256:e922edce4a2d88655b8ac084b128a8790600a0a365db20ca9006852594211185

Observation a1f8e1f8-d226-4067-961c-e547f0999382 · outbound

This paper cites Vector-quantized image modeling with improved VQGAN.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Vector-quantized image modeling with improved VQGAN

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.874511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.874511Z digest=sha256:f00dc64ce310e11c607bf0ec79dc8bdb5e1e9916dd295f7928c954d4e1c514b0

Observation fea1c7ea-94a2-4540-8952-86e24a8280d6 · outbound

This paper cites Language model beats diffusion - tokenizer is key to visual generation.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Language model beats diffusion - tokenizer is key to visual generation

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:47.928190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:47.928190Z digest=sha256:7dc2ecc58820f156f7c3e0e13d593b731e8bcacabde3ade1f2340eb0a611e460

Observation 282f7c6d-80b6-4c6c-9a70-54a0225dd3b0 · outbound

This paper cites An Image is Worth 32 Tokens for Reconstruction and Generation.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization An Image is Worth 32 Tokens for Reconstruction and Generation

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.006661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.006661Z digest=sha256:3132a661cfe44a652553713c0c80aeb225cc5390b511f3724ff087f46aca4dc5

Observation ec51c12b-16d3-47ba-9873-85d1bd719e54 · outbound

This paper cites Regularized vector quantization for tokenized image synthesis.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Regularized vector quantization for tokenized image synthesis

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.113131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.113131Z digest=sha256:15e28036f036d5b4ad32699cb124c1bcb18caab70f0a480e8c7a4d2d8e84914f

Observation bb25314f-a770-42c3-8034-5ddc1c4dc9ca · outbound

This paper cites Efros, Eli Shechtman, and Oliver Wang.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Efros, Eli Shechtman, and Oliver Wang

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.194344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.194344Z digest=sha256:f9abe156078d524b93a2fad9e04fc0bbfd2e1907deeb88af5d8836a2d0568834

Observation e4e1c048-9b41-4475-8f96-32fb882334f5 · outbound

This paper cites Online clustered codebook.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Online clustered codebook

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.253777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.253777Z digest=sha256:a4cfe75a5d0df51ae2ce5bc8a742d3b91dc811c0d9bd157ab22ffe56ee3c217a

Observation 7fa93c49-144d-4b09-abb0-e4ccd874215f · outbound

This paper cites Movq: Modulating quantized vectors for high-fidelity image generation.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Movq: Modulating quantized vectors for high-fidelity image generation

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.306046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.306046Z digest=sha256:afee3c429497c46480bdec9531fcbb3f8fd90ea0d035884751afbe9b7c901a73

Observation 8c1944f5-a9c2-48ea-8d90-fe0410a0f41e · outbound

This paper cites Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.383882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.383882Z digest=sha256:37fdc451f4a2e1b131c0fac064e5102f56fcb6a1d16fc5b50e44fa7f41f65f28

Observation ea97fe0f-f14c-4845-ab10-4396f119cf33 · outbound

This paper cites Addressing representation collapse in vector quantized models with one linear layer.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Addressing representation collapse in vector quantized models with one linear layer

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.460590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.460590Z digest=sha256:c0d9357b1c993b5119e16d2caec952ce28bc094246b83ebddec100714d78c6c7

Observation bb459904-ffb9-4ac1-ba4e-416ae4623a31 · outbound

This paper cites @esa (Ref.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization @esa (Ref

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.538179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.538179Z digest=sha256:186106afb64886aa89e5b09b4afbac904fd98208438d268891b1e4c25a8d4445

Observation 0ddec6ed-7caa-469d-aade-769c7adea287 · outbound

This paper cites an unresolved cited work.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Unresolved cited work

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-04T18:12:48.589313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.589313Z digest=sha256:ad1968f790f0b0a5e46b621fb9f9573c8741ce49894cae9e55a5c45fc6f88817

Observation 5aba5afd-1bff-4c84-9716-e0cb5aa3753c · outbound

This paper cites Left: Performance comparison showing generation (FID) and reconstruction (rFID) quality across different methods.

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization Left: Performance comparison showing generation (FID) and reconstruction (rFID) quality across different methods

Reference 59

Resolution
malformed identifier
no resolver link, observed 2026-08-04T18:12:48.666757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T18:12:48.666757Z digest=sha256:7a8f4e45ea745839fe20305b96db0e4f75cbb8aa87ffe48b1a57a53c0c2adc6f

Pith citing papers

Observation fab95155-c004-4647-8004-a03e0967c8d0 · inbound

NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization cites this paper.

NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-07-03T05:27:39.705956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-27T13:18:47.472178Z digest=sha256:149435cf7fd68d9092de9c125a3e0365812e5ca6ce8dc96dc0269b79fac4888e

Observation 7c266761-1fdc-409d-8a94-9c3906cc0e2c · inbound

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis cites this paper.

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization

Reference 20

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T08:14:26.687079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-30T06:07:55.600338Z digest=sha256:f97cdbb2140522786edef96afaf9c3a3fbd7fe26c95848a603089d81eb4a1d0f

Observation 91aa0228-a3ca-4eb1-bc04-95ba5b51e8b6 · inbound

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis cites this paper.

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-02T09:39:33.755572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T09:39:33.755572Z digest=sha256:d686b983129021b21dda0ddbeeb08b23ac3b8683b6ba4367e268950d7a116a31