Paper Citation Record · LEDGER

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models

As of 15 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2412.19104.

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

pith.paper-citation-record.v1
2412.19104 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T01:02:56.130644Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:44:32.969001Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-10T21:44:33.449281Z

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy17
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 16711921-5997-4531-a563-f35eaefae475 · outbound

This paper cites Beit: Bert pre-training of image transformers.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Beit: Bert pre-training of image transformers

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.657516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5087204a-062a-409a-b718-f7f3958eb2a1 · outbound

This paper cites End-to- end object detection with transformers.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models End-to- end object detection with transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:55.959353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32281388-d623-4ce1-a379-50e416210459 · outbound

This paper cites Pre-trained image processing transformer.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Pre-trained image processing transformer

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.636932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2701d573-baa7-4bc1-bdf2-a5e256a7d246 · outbound

This paper cites A simple framework for contrastive learning of visual representations.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models A simple framework for contrastive learning of visual representations

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.622645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1396c092-74d4-48ce-aff1-55db76de6ef9 · outbound

This paper cites Context autoencoder for self- supervised representation learning.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Context autoencoder for self- supervised representation learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.610732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d7d51be8-6c58-424d-809a-3ea35b81b605 · outbound

This paper cites Deconstructing Denoising Diffusion Models for Self-Supervised Learning.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Deconstructing Denoising Diffusion Models for Self-Supervised Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:55.977251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5cd8573-1a21-4279-8acb-f726d32b164e · outbound

This paper cites Emerging Property of Masked Token for Effective Pre-training.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Emerging Property of Masked Token for Effective Pre-training

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:55.982018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61993712-0102-4c2a-a66e-f00572367c43 · outbound

This paper cites Salience-based adaptive masking: revisit- ing token dynamics for enhanced pre-training.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Salience-based adaptive masking: revisit- ing token dynamics for enhanced pre-training

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:55.986055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98186132-9faa-425b-9ccc-300f3065584a · outbound

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

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Imagenet: A large-scale hierarchical image database

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.592510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c85341db-e4bf-430b-9759-e2d35b77f496 · outbound

This paper cites Bootstrapped masked autoencoders for vision bert pretraining.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Bootstrapped masked autoencoders for vision bert pretraining

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.580387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c4df558c-a581-40cd-b195-a7ad2a4ebc4c · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:55.997475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bd72a33-0b08-491e-8170-f5dd86aa2b06 · outbound

This paper cites Bootstrap your own latent-a new approach to self-supervised learning.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Bootstrap your own latent-a new approach to self-supervised learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.001518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc3a8e35-3d52-4ab4-9de4-f16633a7ee7b · outbound

This paper cites Momentum contrast for unsupervised visual rep- resentation learning.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Momentum contrast for unsupervised visual rep- resentation learning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.555082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 86a9b906-3589-472f-8b84-a44b2e2780b5 · outbound

This paper cites Masked autoencoders are scalable vision learners.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Masked autoencoders are scalable vision learners

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.542971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4c025cd7-2c8b-41aa-ae69-cc942aacf501 · outbound

This paper cites Unsupervised keypoints from pretrained diffusion models.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Unsupervised keypoints from pretrained diffusion models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.530117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b592c68a-e5d3-41c6-bbc6-8c102808af91 · outbound

This paper cites Unsupervised semantic correspondence using stable diffu- sion.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Unsupervised semantic correspondence using stable diffu- sion

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.515903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 291338fb-aadd-448b-a116-f7d26e922394 · outbound

This paper cites Denoising dif- fusion probabilistic models.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Denoising dif- fusion probabilistic models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.018534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b658b922-b7e5-443e-9cf8-226ffe8eb353 · outbound

This paper cites Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.021927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23cb11a5-a493-41a2-a8c4-70b7c6d91670 · outbound

This paper cites Elucidating the design space of diffusion-based generative models.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Elucidating the design space of diffusion-based generative models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.026556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be2c7a95-e086-42a5-b3d6-133558da4569 · outbound

This paper cites 3d object representations for fine-grained categorization.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models 3d object representations for fine-grained categorization

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.486692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ae5d13f3-306d-4e1d-a894-85f8d185d5df · outbound

This paper cites Microsoft coco: Common objects in context.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Microsoft coco: Common objects in context

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.471380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 94fbd934-087b-4a80-bf16-4acef01956f1 · outbound

This paper cites Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.039956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1a503a7-af4d-4f3f-9d0a-1a8998f08085 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Swin transformer: Hierarchical vision transformer using shifted windows

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.043992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c7668bf-1b5c-4d68-a530-4310e4b1c7c0 · outbound

This paper cites Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.047752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f8750ac-287b-4b24-b12c-c32d67ae9c1f · outbound

This paper cites Diffusion hyperfeatures: Searching through time and space for semantic correspondence.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Diffusion hyperfeatures: Searching through time and space for semantic correspondence

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.051861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9eacf2f-b69f-4cc6-9322-ce74d2f1a1b5 · outbound

This paper cites Fine-Grained Visual Classification of Aircraft.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Fine-Grained Visual Classification of Aircraft

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.056244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 612eb5ba-aade-47ff-9f1a-7232b6554df0 · outbound

This paper cites Improved denoising diffusion probabilistic models.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Improved denoising diffusion probabilistic models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.060588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18bec5c4-2ecb-458b-8f3f-36eb1d70a5ad · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Learning transferable visual models from natural language supervi- sion

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.064746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ec8e3e9-8654-46e0-9131-a11da3de7bde · outbound

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

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Zero-shot text-to-image generation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.401192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d0e1d641-e3ae-421f-935a-9f0e56efedbd · outbound

This paper cites Vi- sion transformers for dense prediction.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Vi- sion transformers for dense prediction

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.385852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dba26b97-fd97-4ae6-8257-6e7627cd1a2a · outbound

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

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models High-resolution image synthesis with latent diffusion models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.076514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51f75e41-5357-4a8c-8600-e8ecf3d88f91 · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Photorealistic text-to-image diffusion models with deep language understanding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.080252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57f56fab-e262-40a6-bff8-b6a7f45af10d · outbound

This paper cites LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.083835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36742fdd-214e-455c-a1d9-bb9a22c92ee1 · outbound

This paper cites Denoising Diffusion Implicit Models.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Denoising Diffusion Implicit Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.087361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91c850b1-cf7c-44a6-a098-f159ba2dc59a · outbound

This paper cites Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.090773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 268ff3d6-50e0-463a-9f0b-b1a741311cdd · outbound

This paper cites The iNaturalist Species Classification and Detection Dataset.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models The iNaturalist Species Classification and Detection Dataset

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.094114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68825b24-dc32-460c-a38f-6accbec73dfa · outbound

This paper cites The inaturalist species classification and de- tection dataset.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models The inaturalist species classification and de- tection dataset

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.097953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f51c4bde-3480-4fdb-a04a-1c68904bdb9b · outbound

This paper cites The caltech-ucsd birds-200-2011 dataset.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models The caltech-ucsd birds-200-2011 dataset

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.341954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f0e5fe92-855a-4733-980d-f7e7da21bf5c · outbound

This paper cites Diffusion models as masked autoencoders.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Diffusion models as masked autoencoders

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.327716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 381dce87-cf43-4677-8762-d4e2ab1c558a · outbound

This paper cites Simmim: A simple framework for masked image modeling.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Simmim: A simple framework for masked image modeling

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T01:02:56.314775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b41bdae4-4d42-4748-97e6-a984aa472455 · outbound

This paper cites Masked Image Modeling with Denoising Contrast.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Masked Image Modeling with Denoising Contrast

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.113714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79d7d66e-c587-4e38-8cd1-03f8cdf3894c · outbound

This paper cites Fast Training of Diffusion Models with Masked Transformers.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Fast Training of Diffusion Models with Masked Transformers

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.117688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ae084a7-dc13-400f-b74c-87767a6ab6d4 · outbound

This paper cites Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.122105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd94211a-ca3e-4b40-9297-b6e0e4920042 · outbound

This paper cites Scene parsing through ade20k dataset.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Scene parsing through ade20k dataset

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.126490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1232b076-f48f-4cc3-a6b9-2e678fbfb910 · outbound

This paper cites Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models Deformable DETR: Deformable Transformers for End-to-End Object Detection

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T01:02:56.130644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b261d85d-9469-407c-83b5-0640b749b916 · inbound

TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning cites this paper.

TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-10T21:44:33.453634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.