Paper Citation Record · LEDGER

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

As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 24 inbound Pith citation observations for arXiv:2406.11837.

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

pith.paper-citation-record.v1
2406.11837 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:48:03.489771Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T16:08:37.450322Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 36306d8e-f675-456d-91f7-11a1e0cecabb · inbound

Deep Learning-Based Image Compression for Wireless Communications: Impacts on Reliability,Throughput, and Latency cites this paper.

Deep Learning-Based Image Compression for Wireless Communications: Impacts on Reliability,Throughput, and Latency Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T19:33:24.947232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93290248-c703-4097-aa4b-77e74cd4525f · inbound

Factorized Visual Tokenization and Generation cites this paper.

Factorized Visual Tokenization and Generation Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T12:53:03.179680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec26adc0-ca0f-4719-a6af-816c9277ff18 · inbound

Scalable Image Tokenization with Index Backpropagation Quantization cites this paper.

Scalable Image Tokenization with Index Backpropagation Quantization Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T23:15:46.631242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a578d8-715e-4592-bc2e-8762c087d474 · inbound

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation cites this paper.

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 76

Resolution: malformed identifier; no resolver link, observed 2026-08-11T22:54:20.710373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc3f6384-aede-40b3-bbc3-037859db19ab · inbound

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer cites this paper.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 124

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.683119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 582e0f43-eef2-45f7-99cc-7fc8d2641c8c · inbound

Preventing Local Pitfalls in Vector Quantization via Optimal Transport cites this paper.

Preventing Local Pitfalls in Vector Quantization via Optimal Transport Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T11:38:29.866761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea50a6f4-551d-4743-8670-bc21ae9a44b0 · inbound

Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models cites this paper.

Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T22:34:14.574576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffad08d1-d959-47c7-8ac0-10421ed12af9 · inbound

InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration cites this paper.

InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T13:02:37.551540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d3811b7-d03b-4fa6-9681-480d2b127e50 · inbound

Masked Autoencoders Are Effective Tokenizers for Diffusion Models cites this paper.

Masked Autoencoders Are Effective Tokenizers for Diffusion Models Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T04:47:30.466469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 336f5d11-e67d-4f1b-b457-b757e135dace · inbound

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens cites this paper.

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-16T11:48:03.489771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69267f92-7675-4126-b76f-2b9aa29e46d9 · inbound

Fast Autoregressive Models for Continuous Latent Generation cites this paper.

Fast Autoregressive Models for Continuous Latent Generation Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T10:38:52.748177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dee18e11-8a7f-4bf7-bd7a-55144e5b916e · inbound

UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information cites this paper.

UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:53:18.403349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0468529-a537-472a-aa38-067c6e842efa · inbound

MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation cites this paper.

MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:12:30.315990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6459ee8c-5f34-43d2-9b3e-5fba6bd2d812 · inbound

UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation cites this paper.

UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-06T23:01:49.941622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9739bb18-d759-4093-91f0-3834a5dc1c86 · inbound

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis cites this paper.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T20:49:43.861863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c5cddd5-da6d-4fec-a0e4-672898b727ba · inbound

Hita: Holistic Tokenizer for Autoregressive Image Generation cites this paper.

Hita: Holistic Tokenizer for Autoregressive Image Generation Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 63

Resolution: malformed identifier; no resolver link, observed 2026-08-06T20:38:59.016813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 750424a1-162d-4ad8-82f6-b5b90669c3c6 · inbound

Quantize-then-Rectify: Efficient VQ-VAE Training cites this paper.

Quantize-then-Rectify: Efficient VQ-VAE Training Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:57.408009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization cites this paper.

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.

Observation 4a92f15a-bb73-4e1a-a97a-1392246486f9 · inbound

Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice cites this paper.

Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-20T22:43:51.034253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f2e809a6-712a-4268-aa3a-68b685ee27ce · inbound

Vision Foundation Models as Generalist Tokenizers for Image Generation cites this paper.

Vision Foundation Models as Generalist Tokenizers for Image Generation Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 103

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T11:03:13.425796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 298bf8bd-f40b-41b5-965e-dc8a8efac37b · inbound

HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution cites this paper.

HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-07-01T21:06:13.489175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 80afaa1a-edb8-48a5-bfd4-a95221c22ac1 · inbound

IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder cites this paper.

IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 74

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T05:37:40.265134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 526adc27-5157-4f46-b302-46da018cc692 · 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 Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T05:27:39.717943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 50a5e554-ca50-4fcc-b637-0521da0cabc8 · inbound

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment cites this paper.

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Reference 143

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:08:37.452164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.