Paper Citation Record · LEDGER

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization

As of 23 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 4 inbound Pith citation observations for arXiv:2507.07997.

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

pith.paper-citation-record.v1
2507.07997 v2

Coverage vector

measured 68 of 68 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:32:54.917657Z

measured 72 of 72 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T06:04:18.168577Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T15:17:07.216858Z

Reference resolution

68 of 68 outbound references displayed

verified exact0
verified fuzzy34
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fa25afe9-7edb-429d-bea0-1266cf94a24a · outbound

This paper cites Cosmos World Foundation Model Platform for Physical AI.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Cosmos World Foundation Model Platform for Physical AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.656073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b7de03b-ad22-4b2b-84fd-e3ee19e7b33f · outbound

This paper cites Soft-to-hard vector quantization for end-to-end learn- ing compressible representations.NeurIPS, 30, 2017.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Soft-to-hard vector quantization for end-to-end learn- ing compressible representations.NeurIPS, 30, 2017

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:59.443908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1db8c4ea-d040-4ad5-b68b-0601ba76c886 · outbound

This paper cites Factorized Visual Tokenization and Generation.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Factorized Visual Tokenization and Generation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.664956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73144590-faef-4b83-b582-dbee1ea9afa8 · outbound

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

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.669038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab12f06f-5158-48ec-a2a1-c0bcf23d67e2 · outbound

This paper cites Matryoshka multimodal models.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Matryoshka multimodal models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:59.328799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 60620f36-263c-4d3e-951e-ba897c60f8f8 · outbound

This paper cites Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.677511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13f3989c-7f60-4ab6-ad48-f535f1370eac · outbound

This paper cites OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.681958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad80db0c-8681-4203-a2f1-25d1571e2008 · outbound

This paper cites Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.685858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0853d326-2f4d-46cb-be17-f8307673a8f8 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Imagenet: A large-scale hierarchical image database

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:59.208196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2fe171f0-ce4b-46ce-b09c-176e1b3af673 · outbound

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

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Taming transformers for high-resolution image synthesis

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:58.960457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c20128ec-3ad6-4173-9dda-f5995c92a6ca · outbound

This paper cites Scaling rectified flow transformers for high-resolution image synthesis.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Scaling rectified flow transformers for high-resolution image synthesis

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.698515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315bc44b-6ed5-477e-a8ff-d4bcc06c5242 · outbound

This paper cites Dynamical Variational Autoencoders: A Comprehensive Review.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Dynamical Variational Autoencoders: A Comprehensive Review

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.702241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 714d8be0-2def-43b2-829d-a69759ee7259 · outbound

This paper cites Vector quantization.IEEE Assp Magazine, 1 (2):4–29, 1984.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Vector quantization.IEEE Assp Magazine, 1 (2):4–29, 1984

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:58.461691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e7e61a31-cdb8-44f3-9958-9a1053b31b4c · outbound

This paper cites DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.709837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09dadb60-9087-4483-9174-0060d7155eec · outbound

This paper cites Learnings from Scaling Visual Tokenizers for Reconstruction and Generation.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Learnings from Scaling Visual Tokenizers for Reconstruction and Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.714314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2409850-6265-41af-87aa-044ac4955e59 · outbound

This paper cites DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.718781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cd1d0cf-b270-4830-9e69-42eba91510b7 · outbound

This paper cites Image-to-image translation with conditional adversarial net- works.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Image-to-image translation with conditional adversarial net- works

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:57.890039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f9c740e7-39c0-402e-aaf7-f78ff48e811b · outbound

This paper cites A style-based generator architecture for generative adversarial networks.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization A style-based generator architecture for generative adversarial networks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:57.609403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5ea2efee-035c-49b7-9d10-f9c4a91f1059 · outbound

This paper cites Auto-encoding variational bayes, 2013.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Auto-encoding variational bayes, 2013

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:57.480027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 712101f3-ed72-41ae-b32a-7cea93161efd · outbound

This paper cites An introduction to variational autoencoders.Foundations and Trends® in Machine Learning, 12(4):307–392, 2019.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization An introduction to variational autoencoders.Foundations and Trends® in Machine Learning, 12(4):307–392, 2019

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:57.301948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2dd59af8-2886-428e-aca6-dcc8275690c2 · outbound

This paper cites Segment any- thing.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Segment any- thing

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:57.125356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 19961738-1c1f-45e5-9d4e-de689cdf467a · outbound

This paper cites Matryoshka representation learning.NeurIPS, 35: 30233–30249, 2022.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Matryoshka representation learning.NeurIPS, 35: 30233–30249, 2022

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:56.927856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9ec191dc-30e3-4ba6-8aa4-6aaf25833d39 · outbound

This paper cites an unresolved cited work.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:32:56.808049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 32561895-2f25-4185-9655-7f12963d76ad · outbound

This paper cites Fast and accurate image super-resolution with deep laplacian pyramid networks.PAMI, 41(11):2599–2613,.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Fast and accurate image super-resolution with deep laplacian pyramid networks.PAMI, 41(11):2599–2613,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:56.646310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 316f5cee-0dbc-474a-97ad-46deae0cb0e4 · outbound

This paper cites Autoregressive image generation using resid- ual quantization.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Autoregressive image generation using resid- ual quantization

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:56.476819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7b2b4650-5df9-4f6d-9f0b-f383f0ea5116 · outbound

This paper cites UNIMO-2: End-to-End Unified Vision-Language Grounded Learning.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization UNIMO-2: End-to-End Unified Vision-Language Grounded Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.755656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff678a4e-6db6-4a6c-b363-e2ab9266e367 · outbound

This paper cites Efficient neural radiance fields for interactive free-viewpoint video.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Efficient neural radiance fields for interactive free-viewpoint video

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.759630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba18f4d1-3c5f-4941-b526-26759292792e · outbound

This paper cites Cross-Modal Discrete Representation Learning.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Cross-Modal Discrete Representation Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.763435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 321fcf6e-1492-40df-8db0-df32a3211422 · outbound

This paper cites an unresolved cited work.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:32:56.305892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 72b9924d-a73a-4392-a3ce-4618461792b4 · outbound

This paper cites Deep learning face attributes in the wild.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Deep learning face attributes in the wild

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:56.099536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 647f1e06-3d2c-4b8f-a764-65e6e8fdb115 · outbound

This paper cites Decoupled Weight Decay Regularization.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Decoupled Weight Decay Regularization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.774843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 347ad2ab-9c45-40af-8a5f-7dd349dc16bc · outbound

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

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.777950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab303b49-c4e5-4430-a397-1d2fc7294130 · outbound

This paper cites Uavid: A semantic segmentation dataset for uav imagery.ISPRS journal of photogrammetry and remote sensing, 165:108–119, 2020.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Uavid: A semantic segmentation dataset for uav imagery.ISPRS journal of photogrammetry and remote sensing, 165:108–119, 2020

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.941806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 97bf4447-1ff3-4ff4-ae8c-00041e1622a6 · outbound

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

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Unitok: A unified tokenizer for visual generation and understanding

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.785868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed12b8b9-3f68-430a-bc32-cfeb824a45de · outbound

This paper cites Discrete Representations Strengthen Vision Transformer Robustness.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Discrete Representations Strengthen Vision Transformer Robustness

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.789146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64b59686-6c1c-448a-ba6f-c15b1167db52 · outbound

This paper cites Spring: A high-resolution high- detail dataset and benchmark for scene flow, optical flow and stereo.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Spring: A high-resolution high- detail dataset and benchmark for scene flow, optical flow and stereo

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.898329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c95d37b3-2ce2-47c8-aaff-35cb4c325d29 · outbound

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

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Finite Scalar Quantization: VQ-VAE Made Simple

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.796784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b279fdcf-2ce6-4b99-9524-7cdf3d08bd4b · outbound

This paper cites The mapillary vistas dataset for semantic understanding of street scenes.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization The mapillary vistas dataset for semantic understanding of street scenes

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.856664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 70b7f29d-03c4-4a4b-a944-87732a6e207e · outbound

This paper cites A benchmark dataset and evaluation methodology for video object segmentation.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization A benchmark dataset and evaluation methodology for video object segmentation

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.828149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7577d47b-25be-48c2-a497-548f77383735 · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.807968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c88a31c9-75f5-4cec-b0c6-e5e6160df8fe · outbound

This paper cites Generat- ing diverse high-fidelity images with vq-vae-2.NeurIPS, 32,.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Generat- ing diverse high-fidelity images with vq-vae-2.NeurIPS, 32,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.803913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6ce2731a-ee8f-41b6-8911-4198a98b8c59 · outbound

This paper cites Learning ordered representations with nested dropout.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Learning ordered representations with nested dropout

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.776776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ca12fda3-c56f-40d9-9efa-7ca4c4c2721f · outbound

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

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization High-resolution image synthesis with latent diffusion models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.751750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 06ec731d-8a51-4ebd-ad68-1c92be8d4a7b · outbound

This paper cites Laion-5b: An open large-scale dataset for training next gener- ation image-text models.NeurIPS, 35:25278–25294, 2022.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Laion-5b: An open large-scale dataset for training next gener- ation image-text models.NeurIPS, 35:25278–25294, 2022

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.727962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 27a94147-c20e-44b9-932b-174afb033e8b · outbound

This paper cites Textocr: Towards large- scale end-to-end reasoning for arbitrary-shaped scene text.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Textocr: Towards large- scale end-to-end reasoning for arbitrary-shaped scene text

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.700458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 28cfce01-97c4-4b8a-8837-c762e5680455 · outbound

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

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.829422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a081a7-63f0-4cb5-8680-99722b6c2972 · outbound

This paper cites SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.833870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a9cddf8-38a7-49d4-879d-6c3057efc929 · outbound

This paper cites Visual autoregressive modeling: Scalable image gen- eration via next-scale prediction.NeurIPS, 37:84839–84865,.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Visual autoregressive modeling: Scalable image gen- eration via next-scale prediction.NeurIPS, 37:84839–84865,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.837875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8bda5d-705c-4e97-a293-282fcb0252d7 · outbound

This paper cites Neural discrete representation learning.NeurIPS, 30, 2017.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Neural discrete representation learning.NeurIPS, 30, 2017

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.666141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 87156a6f-4d3f-4d15-8228-ab7bc6faf0bd · outbound

This paper cites Neural discrete representation learning.NeurIPS, 30, 2017.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Neural discrete representation learning.NeurIPS, 30, 2017

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.649860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9f4df827-a6c2-4f73-ae71-269af5e4a0aa · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Emu3: Next-Token Prediction is All You Need

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.848969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afde9047-e48c-4259-b06e-a2df617f554c · outbound

This paper cites Hierarchical quantized autoen- coders.NeurIPS, 33:4524–4535, 2020.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Hierarchical quantized autoen- coders.NeurIPS, 33:4524–4535, 2020

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.635306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7c3cf0e3-1857-480f-bcf5-a3b6e53a1634 · outbound

This paper cites Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.855897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa95dc1f-7246-4bbf-8cfa-369e5b8ff5ff · outbound

This paper cites Vfhq: A high-quality dataset and benchmark for video face super-resolution.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Vfhq: A high-quality dataset and benchmark for video face super-resolution

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.620759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c1f1d8ef-2e58-4930-a484-411149d45c7c · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.863560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66b9ce63-49de-4252-b813-124bb11a5af3 · outbound

This paper cites Locally hierarchical auto-regressive modeling for image generation.NeurIPS, 35:16360–16372, 2022.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Locally hierarchical auto-regressive modeling for image generation.NeurIPS, 35:16360–16372, 2022

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.603667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation eab746ae-7afe-4f7d-b606-10734b7b2069 · outbound

This paper cites Vector-quantized Image Modeling with Improved VQGAN.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Vector-quantized Image Modeling with Improved VQGAN

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.876303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ff981d7-ad2d-42ce-ad33-c26c8cede6ef · outbound

This paper cites Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.880493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf266951-c957-4104-b4b0-97c5c85a392a · outbound

This paper cites Towards efficient and scale-robust ultra- high-definition image demoir´eing.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Towards efficient and scale-robust ultra- high-definition image demoir´eing

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.589930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0db0ce1f-929a-48cd-880c-256d4cacfda7 · outbound

This paper cites Towards high-resolution salient object detection.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Towards high-resolution salient object detection

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.576020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8bf75040-ee6a-49ed-8862-c2b5f3e60716 · outbound

This paper cites Regularized vector quantization for tokenized image synthesis.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Regularized vector quantization for tokenized image synthesis

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.558567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 82e6a31f-dead-4d43-86a6-b2abc9cee4a0 · outbound

This paper cites Epona: Autoregressive Diffusion World Model for Autonomous Driving.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Epona: Autoregressive Diffusion World Model for Autonomous Driving

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.894607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 855632f1-6695-4218-8881-46c01f201e12 · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization The unreasonable effectiveness of deep features as a perceptual metric

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.898803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8fbd35c-11c8-4da4-b460-e2b025f7ddd7 · outbound

This paper cites Cv-vae: A compatible video vae for latent generative video models.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Cv-vae: A compatible video vae for latent generative video models

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.418337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a92fa275-1fe5-4b84-a263-7b0c0fc36a67 · outbound

This paper cites Online clustered code- book.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Online clustered code- book

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.401129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c29cddbf-4fe0-4516-b321-610f054d3e54 · outbound

This paper cites Movq: Modulating quantized vectors for high-fidelity image generation.NeurIPS, 35:23412–23425, 2022.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Movq: Modulating quantized vectors for high-fidelity image generation.NeurIPS, 35:23412–23425, 2022

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:55.386177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7f52d659-5b7f-457e-b2ad-958dc16b605f · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Open-Sora: Democratizing Efficient Video Production for All

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.914113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b2cd5b7-117a-40be-a8df-9ee90f0ca735 · outbound

This paper cites Address- ing representation collapse in vector quantized models with one linear layer.arXiv preprint arXiv:2411.02038, 2024.

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization Address- ing representation collapse in vector quantized models with one linear layer.arXiv preprint arXiv:2411.02038, 2024

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:54.917657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7c01e3d7-73bc-4b35-a488-e6b6a6cfea42 · inbound

3D and 4D World Modeling: A Survey cites this paper.

3D and 4D World Modeling: A Survey MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization

Reference 103

Resolution: unresolved; no resolver link, observed 2026-08-05T06:04:18.168577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50a07cdc-b07c-495d-98c9-64ee84f7d604 · inbound

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens cites this paper.

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:08:15.852478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6d0577c1-f2bb-47c1-bb07-b7dfcc55092e · inbound

MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts cites this paper.

MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-02T15:17:07.218280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1558fa2a-89c4-46f2-a51f-3476eed44741 · inbound

Pixel-Space Diffusion Transformers cites this paper.

Pixel-Space Diffusion Transformers MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-01T17:35:37.149410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.