Pith. sign in

Paper Citation Record · LEDGER

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering

As of 10 August 2026, this Paper Citation Record lists 83 of 83 outbound references and 0 inbound Pith citation observations for arXiv:2606.01911.

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

pith.paper-citation-record.v1
2606.01911 v1

Coverage vector

measured 83 of 83 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T15:39:15.744954Z

measured 83 of 83 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

83 of 83 outbound references displayed

  • verified exact5
  • verified fuzzy0
  • unresolved74
  • parse uncertain0
  • malformed identifier4
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 84d4a13c-076d-433c-96ec-7af92811463a · outbound

This paper cites Efficient-vqgan: To- wards high-resolution image generation with efficient vision transformers.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Efficient-vqgan: To- wards high-resolution image generation with efficient vision transformers

Reference 1

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:12a15880ba2f4021e92bbef4beeb88c0ff8af2777aa6a7a6f0d880d95362bf70

Observation 8671d9d9-3181-452e-b3a7-5db9f5f7b694 · outbound

This paper cites an unresolved cited work.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Unresolved cited work

Reference 2

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:bbcff5b683cced6d07bcd0927aa9b48609f49d61eb1398e4d7ffebba30e88880

Observation 5d6cf722-45bf-4684-83cc-64aa2ee7a75a · outbound

This paper cites Softvq-vae: Efficient 1-dimensional contin- uous tokenizer.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Softvq-vae: Efficient 1-dimensional contin- uous tokenizer

Reference 3

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:b850dd276a1ba8c6b438b3002c5fc6070c0d53c7e240743f23ed6da5aac6c458

Observation 96ef95ec-9411-4a5e-b5d4-81e88b48039c · outbound

This paper cites Textdiffuser: Diffusion models as text painters, 2023.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Textdiffuser: Diffusion models as text painters, 2023

Reference 4

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:f2e0690a1a169f98904a0ee52fb77bece0c5317d563a3926f3915a5edb4a575f

Observation aa68bbc6-79d8-4158-b629-c48becafca55 · outbound

This paper cites Blip3- o: A family of fully open unified multimodal models- architecture, training and dataset, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Blip3- o: A family of fully open unified multimodal models- architecture, training and dataset, 2025

Reference 5

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:6de368547c5984e9b3b7386f8d58a33751ca130f84ab53ec3725e6386b274cc1

Observation a52712f6-0746-4499-9726-9989d1753cf7 · outbound

This paper cites Janus- pro: Unified multimodal understanding and generation with data and model scaling, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Janus- pro: Unified multimodal understanding and generation with data and model scaling, 2025

Reference 6

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:3edef251682179da619a6eef113902b970b634b15c6cff734abb884ca37ac72f

Observation d22bdeb7-8cee-4fa9-a231-e74f51984567 · outbound

This paper cites Paddleocr-vl: Boosting multilingual document parsing via a 0.9b ultra-compact vision-language model, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Paddleocr-vl: Boosting multilingual document parsing via a 0.9b ultra-compact vision-language model, 2025

Reference 7

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:3bb6f415bb99e66375054253798ec98de7d47db652f15d7a43fa7a503abe6ffe

Observation b55fd121-4881-4a56-8b32-7e5209aed037 · outbound

This paper cites Paddleocr 3.0 technical report, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Paddleocr 3.0 technical report, 2025

Reference 8

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:5c80747a06e64cbe28398fa31a47f4e4d11a82e0f7e87ca5f8b4bb5e0eecf6b4

Observation 1e59ac32-b4e0-4254-aa80-79bc8c9dda3f · outbound

This paper cites Emerging properties in unified multimodal pretraining, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Emerging properties in unified multimodal pretraining, 2025

Reference 9

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:79364572e812f8590d013ab98db6dfc07822bf5276c55eef2fd95bda056d92d0

Observation d60d169a-2e43-455d-a89a-42d46209cd5d · outbound

This paper cites Cogview: Mastering text-to- image generation via transformers, 2021.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Cogview: Mastering text-to- image generation via transformers, 2021

Reference 10

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:3dde43f7ab10357cde4c4dc1c78a852a9dbff3a8c30faf7bbf5440c753175d95

Observation 9e7f0d52-0bfb-421f-a0f3-5bf12562f2b5 · outbound

This paper cites Textcrafter: Accurately rendering multiple texts in complex visual scenes, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Textcrafter: Accurately rendering multiple texts in complex visual scenes, 2025

Reference 11

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:ffcd87359c096ec3371a8e47c4d29dd604905a2f5660baad391060a815a87f0b

Observation 8fbdda5e-995f-4fa1-93b4-853199aa0e43 · outbound

This paper cites Taming transformers for high-resolution image synthesis, 2021.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Taming transformers for high-resolution image synthesis, 2021

Reference 12

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:d96730a153add2e42af1d9fcd2ac66f9c2414079b27a2217766eb6984c43b70b

Observation 9da316e0-0e0b-46bc-ad4d-436c51228666 · outbound

This paper cites D-ar: Diffusion via au- toregressive models, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering D-ar: Diffusion via au- toregressive models, 2025

Reference 13

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:c107e2602aab25a9909b74fb9fb0cc4d6a3ef72cb5015348cd684bbe94ee44f9

Observation 8346a156-16fe-4566-9159-f5b6e419f57a · outbound

This paper cites X-omni: Reinforcement learning makes discrete autoregressive image generative models great again, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering X-omni: Reinforcement learning makes discrete autoregressive image generative models great again, 2025

Reference 14

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:f60a1298e91b7413434daf4676fc31d3fd065cd404b1eea34f60f29162bfbf73

Observation 3687ca55-3ff9-4e3f-a0bc-71af85e59c14 · outbound

This paper cites Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-07-01T22:16:15.745397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:48cfc61a7cb04bf571bc26d1f2c6c0e572aa6865e922d8a64e0961509af70c06

Observation 9f7d4dca-f645-4a9e-9590-ffa86f1dc3ec · outbound

This paper cites Flowtok: Flowing seamlessly across text and image tokens.arXiv preprint arXiv:2503.10772.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Flowtok: Flowing seamlessly across text and image tokens.arXiv preprint arXiv:2503.10772

Reference 16

Resolution
verified exact
arxiv_id, observed 2026-07-01T22:16:15.734967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:3cd33eb3631d50921e244b87a55a6ca2be5dd85e4ab4a843ff44382f577e4b0d

Observation b7aa1964-ef95-4e3c-b6e7-a9b43942feec · outbound

This paper cites Rear: Rethinking visual autoregressive models via generator-tokenizer consistency regularization, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Rear: Rethinking visual autoregressive models via generator-tokenizer consistency regularization, 2025

Reference 17

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:71978d1a5381c29b0f8697d3a9863308ccfa9c9f46b752cb344dce2f16586147

Observation 206687de-7616-4d95-ae15-2199076ccb4f · outbound

This paper cites Plangen: Towards unified layout planning and image generation in auto-regressive vision language models,.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Plangen: Towards unified layout planning and image generation in auto-regressive vision language models,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:00025d3b4da09e3fd713847e9f6e8fa8b5967916163ded51560cb0222c61d6d4

Observation 5f5df810-a32f-4a3f-95aa-d2d422e9ae37 · outbound

This paper cites Denoising diffu- sion probabilistic models, 2020.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Denoising diffu- sion probabilistic models, 2020

Reference 19

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:fc8cb7cea9ab8556d2171e03b31bed29d6a67c7570b45a6b3bb5aff20b6a5ab6

Observation 04dab875-d3b6-4b1d-ab30-96c41dce988c · outbound

This paper cites Flux.https://github.com/ black-forest-labs/flux, 2024.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Flux.https://github.com/ black-forest-labs/flux, 2024

Reference 20

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:70185981d56a1e36a2ece59cbd01e54ba2a191e51ebd03eef73428a8f5ab7ffe

Observation 7989ab84-de44-450c-adc5-358b0af6d990 · outbound

This paper cites Unleashing in-context learning of autoregressive models for few-shot image manipulation.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Unleashing in-context learning of autoregressive models for few-shot image manipulation

Reference 21

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:2a236cb8ba68594e457867a0a0e685c06bfb4ffa00bd80b2a3d1dc7d6ffbd2f7

Observation 2426eb64-4c45-4774-8331-dd0e82e81024 · outbound

This paper cites Photo-realistic single image super-resolution using a generative adversarial network, 2017.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Photo-realistic single image super-resolution using a generative adversarial network, 2017

Reference 22

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:c44edd73fa34ebfe109f850e956463d09929f3824346d2703b3b8cd690c0ba16

Observation 0c8fb87a-e8c6-451e-9a15-a6431372b68a · outbound

This paper cites Draft-and-revise: Effective image gen- eration with contextual rq-transformer.Advances in Neural Information Processing Systems, 35:30127–30138, 2022.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Draft-and-revise: Effective image gen- eration with contextual rq-transformer.Advances in Neural Information Processing Systems, 35:30127–30138, 2022

Reference 23

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:a13cacddbb430d35c39ebc2141f87abc6c8c6994e7020731cb8fd32e33e95b94

Observation b57906cb-d3ad-43db-a766-994c5d763d5b · outbound

This paper cites Autoregressive image generation using residual quantization, 2022.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Autoregressive image generation using residual quantization, 2022

Reference 24

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:7a5e64126c122ddb2864fc8e280438c13b2608766dd813b417d1c4279c787047

Observation 052a591c-bedb-44e2-9833-7b7391fec011 · outbound

This paper cites Vt- bench: Evaluating visual tokenizers for autoregressive image generation, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Vt- bench: Evaluating visual tokenizers for autoregressive image generation, 2025

Reference 25

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:930f895730196f141aafe2a44a952082a643a488c75d24427a06067f910d6e5a

Observation 4618e59e-c303-48aa-a055-c39eabdf4add · outbound

This paper cites Lumina-mgpt: Illuminate flexible photorealistic text- to-image generation with multimodal generative pretraining,.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Lumina-mgpt: Illuminate flexible photorealistic text- to-image generation with multimodal generative pretraining,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:2f0de37801acda806068e3c71562e1d1a39078de0355162192f688116487a7ab

Observation f148564a-c58b-4cbc-b20d-7a616eaecfdf · outbound

This paper cites Decoupled weight decay regularization, 2019.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Decoupled weight decay regularization, 2019

Reference 27

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:51915cf6abcc52c9ac879508ee788f0fd175cae824b3891c28c01268db4e336d

Observation 7a1ae1db-0ab0-4a4a-97e9-2588ba7329d7 · outbound

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

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Reference 28

Resolution
verified exact
arxiv_id, observed 2026-07-01T22:16:15.740095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:2214f120a992e50a666a43622d96f658b3495e8863ba713e9869c014b4550356

Observation e25a254a-ade5-458a-82c3-072ab01e9aca · outbound

This paper cites Unitok: A uni- 9 fied tokenizer for visual generation and understanding, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Unitok: A uni- 9 fied tokenizer for visual generation and understanding, 2025

Reference 29

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:f5a87c92840bba28a0afe2ba6755847115010018b9669db80ec3a4d3c8df6a3d

Observation 940ec236-2923-447c-8c0f-48a08d75eeaf · outbound

This paper cites Textground4m: A prompt-aligned dataset for layout-aware text rendering.Proceedings of the AAAI Conference on Artificial Intelligence, 40(10): 7918–7926, 2026.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Textground4m: A prompt-aligned dataset for layout-aware text rendering.Proceedings of the AAAI Conference on Artificial Intelligence, 40(10): 7918–7926, 2026

Reference 30

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:9a589a467abfc74faae497fb9d25f646d9d58d464a015891827a30d3ba702edc

Observation 7ef17556-cf28-4a45-9f25-74e1c07836a6 · outbound

This paper cites Hello gpt-4o, 2024.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Hello gpt-4o, 2024

Reference 31

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:cfb1da9e3ba6cf8369727bfbc315e80a616c602eb83062cc51ccd3f07abe1dec

Observation 85d29aff-36ab-4ebc-a8f0-7c323f3294e6 · outbound

This paper cites Janus-pro-r1: Ad- vancing collaborative visual comprehension and generation via reinforcement learning, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Janus-pro-r1: Ad- vancing collaborative visual comprehension and generation via reinforcement learning, 2025

Reference 32

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:026dce7b5a4b1dcf3c7887bb76e8673bdf04c4ef597aa65b4ef1f36973a6cc16

Observation e1050b96-f101-46d7-ab70-eb22190db4bc · outbound

This paper cites Im- age transformer.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Im- age transformer

Reference 33

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:6b48fc526d7e94d651788ef01c76be2963551962c6a0e5b40c65b371bf23101b

Observation 965217c3-7293-4b2a-83aa-9bd22c94bb43 · outbound

This paper cites Scalable diffusion models with transformers, 2023.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Scalable diffusion models with transformers, 2023

Reference 34

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:7b43facab294d6009ebee0a993cbfa3114de3b1b1e0a488da976620cca484678

Observation 7b1ffbb8-dc0f-4923-84c6-d9108f18a211 · outbound

This paper cites Du, Zehuan Yuan, and Xin- glong Wu.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Du, Zehuan Yuan, and Xin- glong Wu

Reference 35

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:0c541b830d1e992084c4eb98369901d1ab3cfa0a8220028c2b7c79d1aab67951

Observation 21a17780-8058-45f0-8c00-acf0f386719a · outbound

This paper cites Zero-shot text-to-image generation, 2021.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Zero-shot text-to-image generation, 2021

Reference 36

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:8857af81bdf52803f9aec342bc2aba22c094ecd48ef7e6abdc01e67c5438c94d

Observation 2f0ad994-4c3b-4c7b-b3fc-85c91c3b8db3 · outbound

This paper cites Gener- ating diverse high-fidelity images with vq-vae-2, 2019.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Gener- ating diverse high-fidelity images with vq-vae-2, 2019

Reference 37

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:a9bc57b75c1c61c91e4381ef0677f93d191b63972d63740910b5b246338701b0

Observation 34737376-6930-4226-bd7b-64cae19633a7 · outbound

This paper cites High-resolution image syn- thesis with latent diffusion models, 2022.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering High-resolution image syn- thesis with latent diffusion models, 2022

Reference 38

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:d03915804d46e67842ee99aaf0f9a81e8f009765e19d96cedf533c0642bdcdf2

Observation 22ee4f31-9642-45b2-9894-ce4c80816767 · outbound

This paper cites Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi

Reference 39

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:3cce7e399487d9a5c8b3828ca3ebe4636ad09bc7f45ed93ea5914c6c68a9bc12

Observation 199ff914-243d-4fb8-8450-fcedb0d9d883 · outbound

This paper cites Very deep convo- lutional networks for large-scale image recognition, 2015.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Very deep convo- lutional networks for large-scale image recognition, 2015

Reference 40

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:d379329dd6f0770d780a7599a779f5940d57d22c95ce76fa8f3e5215ab22b324

Observation e3060709-217e-45b1-aed9-f92140552e66 · outbound

This paper cites Denois- ing diffusion implicit models, 2022.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Denois- ing diffusion implicit models, 2022

Reference 41

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:0ee72371128f98dfd4857e0ea49ba93e14edc34bbac953d4653a272341cb27c4

Observation 0166f496-7245-444f-8c0a-8ffb99af42e6 · outbound

This paper cites Autoregressive model beats diffusion: Llama for scalable image generation, 2024.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Autoregressive model beats diffusion: Llama for scalable image generation, 2024

Reference 42

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:c2baec511798779ddfa0f919620e52c3deabcbbd90e099c2e76bd847e27f5162

Observation 36d8027c-fd4a-457f-9522-fdf6c082d0fd · outbound

This paper cites Chameleon: Mixed-modal early-fusion foundation models, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Chameleon: Mixed-modal early-fusion foundation models, 2025

Reference 43

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:cfde193af1b8fc0c7f20e0a9a89c74094d03815940c3d14d6affdde25639e280

Observation fa427dc8-4abe-491e-a3b2-3416948cbd8a · outbound

This paper cites Visual autoregressive modeling: Scalable image generation via next-scale prediction.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Visual autoregressive modeling: Scalable image generation via next-scale prediction

Reference 44

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:767e00a85842202bcbd70c1c0f6e05760dd601b26f59497fe59ec6edb9e25f55

Observation e03e88ab-c840-45cf-b37f-ac5c873ea6f5 · outbound

This paper cites Metamorph: Multimodal un- derstanding and generation via instruction tuning, 2024.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Metamorph: Multimodal un- derstanding and generation via instruction tuning, 2024

Reference 45

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:da35a4f533b8610eb18f18546d0fb05fa4601691b8fff3fdc6d1e1d44c05ef77

Observation 92fb6bd9-cb7e-448e-855c-a1393f7928bc · outbound

This paper cites Anytext: Multilingual visual text gener- ation and editing, 2024.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Anytext: Multilingual visual text gener- ation and editing, 2024

Reference 46

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:a2a7399be63bc190f7dde66bd6d0de3d8fba84b11fedc87c380144e7baa035a3

Observation a6a09a0c-23c3-4423-80d2-8aceb6f8b2ed · outbound

This paper cites Neural discrete representation learning,.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Neural discrete representation learning,

Reference 47

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:fd7513df729b875e929328fea22fe9de29875f71df2bcf8dc74da06529fa34c6

Observation e82f315e-bcd7-4a6c-ab21-0a44bd71a4c9 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 48

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:2fd9c079d48d1c492cba268e36d95bcaabd6f33bd0d061d7b008bec3c123ba7f

Observation 5427aecc-b855-4453-87ba-638a9fdc1d6f · outbound

This paper cites Beyond words: Advancing long-text im- age generation via multimodal autoregressive models, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Beyond words: Advancing long-text im- age generation via multimodal autoregressive models, 2025

Reference 49

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:bcd32dd99588dfa98cb4f64d0ce9a995c464bd7cf0376aeb64517a474ea4a981

Observation 15d66f9c-b175-46c2-8864-5addc3c100e0 · outbound

This paper cites Textat- las5m: A large-scale dataset for dense text image generation,.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Textat- las5m: A large-scale dataset for dense text image generation,

Reference 50

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:57ef59d474e7d1ebf5c753e398b371c62eea0c0f4d10a2817a078bf4c0067901

Observation fe0f6595-77d7-4641-986b-a5853b3475fe · outbound

This paper cites Emu3: Next-token prediction is all you need, 2024.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Emu3: Next-token prediction is all you need, 2024

Reference 51

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:b3e29d9f477b45d55191b355f3ecd6e021480250bdcbff3689354c88e4e80231

Observation 349366ed-76a1-4535-896f-3eba36214e17 · outbound

This paper cites Edge-enhanced feature distillation network for efficient super-resolution, 2022.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Edge-enhanced feature distillation network for efficient super-resolution, 2022

Reference 52

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:4a58a4354c1f8bd815d15d08bf12638fa975d1151c5eca2fbd13a0e931a1dc4f

Observation 21c76b93-28b0-44a6-affb-6acc73e886b4 · outbound

This paper cites Autoregressive visual tracking.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Autoregressive visual tracking

Reference 53

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:bf93377204db8af97ccc43acc202aba355f078d364aeecde5207cf5035c53fb9

Observation cb9f19e8-a502-42bc-9b21-fe551c561085 · outbound

This paper cites Janus: Decoupling visual encoding for unified multimodal understanding and genera- tion, 2024.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Janus: Decoupling visual encoding for unified multimodal understanding and genera- tion, 2024

Reference 54

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:64a9a3b25dffabd62bc8423fcfa78b0b6d5f84093b026e188abba0f7b1a45239

Observation d516eb55-b8c8-493d-a498-6d8e3310826a · outbound

This paper cites Qwen-image technical report,.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Qwen-image technical report,

Reference 56

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:056c573d313dfcb1684e16e0a0fcbbf20a7eb5eb724b083ceff52e946e82c976

Observation c8c1e1de-1f72-430c-a84b-da1b93988149 · outbound

This paper cites Vila-u: a unified founda- tion model integrating visual understanding and generation,.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Vila-u: a unified founda- tion model integrating visual understanding and generation,

Reference 57

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:37baca78b68edb230e64d342e9320283536470693a74314609302f9952706265

Observation 0ef21c97-a801-42c5-9cf6-f5d435d29a09 · outbound

This paper cites StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation

Reference 58

Resolution
verified exact
arxiv_id, observed 2026-07-01T22:16:15.737555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:985926afeb1e7d971a303861d810196d026bb0b48323037d768ba3394e4b04a3

Observation 80e5f71a-4ede-4141-9176-b9c730a719f8 · outbound

This paper cites Sana: Efficient high-resolution im- age synthesis with linear diffusion transformers, 2024.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Sana: Efficient high-resolution im- age synthesis with linear diffusion transformers, 2024

Reference 59

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:545ffbd52b372ab791f290b3a9f1cfc6c980f15f434715d4b1f69d6a1b8dcd80

Observation eec97dd5-5875-48f1-b50d-52b3a6adc65a · outbound

This paper cites Sana 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer,.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Sana 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer,

Reference 60

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:9bc86586cf5ae02f65b4461c3efea220419735bace6951407e4aa3f9427a8aa9

Observation 2a736dac-29f0-4080-8ea5-e5447ba6a2d2 · outbound

This paper cites Lumina-mgpt 2.0: Stand-alone autoregressive image model- ing, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Lumina-mgpt 2.0: Stand-alone autoregressive image model- ing, 2025

Reference 61

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:8ffff2d07a3ca2c2943ee4689c90a7a0def2997c4da2a71c44862ac12899d534

Observation 9f8d8736-e5be-4b23-b158-2679537e9488 · outbound

This paper cites Gigatok: Scaling visual tokenizers to 3 billion parameters for autoregressive image generation, 2025.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Gigatok: Scaling visual tokenizers to 3 billion parameters for autoregressive image generation, 2025

Reference 62

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:dc71bd80025b334e8671e13a41c4a664b37c8ff7e09e338294a9fffdb6f5ed8a

Observation dd42602b-959f-418f-bc50-a9f7b670458c · outbound

This paper cites Vector-quantized image modeling with improved vqgan, 2022.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Vector-quantized image modeling with improved vqgan, 2022

Reference 63

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:43a1edaf56f1d38ae34fa84ff081cae13c7dee6d0d23502f0328766d79d5b638

Observation dc66bf53-9459-4617-8aca-e92dbae2054f · outbound

This paper cites Randomized autoregressive visual generation.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Randomized autoregressive visual generation

Reference 64

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:0ec69c1f96eb50a28b2b016e9b871193430c61147ce95563309af0ef246535af

Observation de16643e-ba72-45d9-b6ef-8b741acce30a · outbound

This paper cites Regularized vector quantization for tokenized im- age synthesis.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Regularized vector quantization for tokenized im- age synthesis

Reference 65

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:74cc4a505c733e76152c8b9a4e26daf60403b843519eb63d9bfdec8aac8912f4

Observation 2ed570ed-756f-4582-943b-ae8a3e520d0e · outbound

This paper cites Distilling Inter-Class Distance for Semantic Segmentation.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Distilling Inter-Class Distance for Semantic Segmentation

Reference 66

Resolution
verified exact
arxiv_id, observed 2026-07-01T22:16:15.742625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:8b6faeaf064f376c379b91be912c63378e34eac8d1817a2781989df102c4a784

Observation 2ba6c6e8-6e18-40c4-8a09-e6ee8b5f7eef · outbound

This paper cites Diff-tracker: text-to-image diffusion models are un- supervised trackers.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Diff-tracker: text-to-image diffusion models are un- supervised trackers

Reference 67

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:ad2340db016e3d1214fa8cb74b3f20001233f6f938d1a64ec8333e9fe87f7ab6

Observation e3e8d907-4dd0-4534-a6d4-ecd02cfe841c · outbound

This paper cites Performing defocus deblurring by model- ing its formation process.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Performing defocus deblurring by model- ing its formation process

Reference 68

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:61525113e6c739ba9f5af70b2170984d4dbc9262ba230ccdbe5ea8196842d259

Observation 72a2da84-6fb1-44c5-a8af-939fa9a77904 · outbound

This paper cites Visual prompting for one-shot controllable video editing without inversion.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Visual prompting for one-shot controllable video editing without inversion

Reference 69

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:6cda3c8c1fba142aa128069449fb55188fa8cc91a435cf315a33c8187e6ebe37

Observation 0a6ee3f8-de01-4f11-acbb-0e2468d2a9c3 · outbound

This paper cites Movq: Modulating quantized vectors for high- fidelity image generation.Advances in Neural Information Processing Systems, 35:23412–23425, 2022.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Movq: Modulating quantized vectors for high- fidelity image generation.Advances in Neural Information Processing Systems, 35:23412–23425, 2022

Reference 70

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:ddb9a644cdc19a77f05abd20794f707fa3cbca01ab51c673af413abc68d7a773

Observation 6d03612f-66d4-4738-b8dc-0847f903e505 · outbound

This paper cites Shared-ID Hint Codebook.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Shared-ID Hint Codebook

Reference 71

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:8d4852247f410766efee868bb5d63c6451cdceb96c8e4eb582f17cd6ed7b132c

Observation 82b5e3b0-ed2e-476f-bf13-d519e0182b13 · outbound

This paper cites Implementation details.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Implementation details

Reference 72

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:e59d71d6c30245cfd371f9f72e6a9bba4eadf59cc977d49e9e2e0e28468ef21a

Observation ab512638-2452-4f52-b79f-a143fe3fa574 · outbound

This paper cites Model Architecture.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Model Architecture

Reference 73

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:0eeb14153365bd7b3b3a6bfddb186adced1b4cd52b530e9be37bc71e4085bdff

Observation 6e49e047-323d-41dd-b474-99ecc8a0f6ce · outbound

This paper cites Parameters and Latency.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Parameters and Latency

Reference 74

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:836b9a6c41f5355eddc8b216b16264de90ee8c475f823d463f9297da13eeccc9

Observation abc1ed11-b4ce-4994-a6e5-8c7a7f3a099b · outbound

This paper cites Tokenizer Reconstruction Limit.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Tokenizer Reconstruction Limit

Reference 75

Resolution
malformed identifier
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:d8bcb538cb95655754f4b741ed52cf5297d950ef97dab69740df4b6c31b02c05

Observation c2df0dd5-30d6-4d08-bcfb-9c8eef6dae22 · outbound

This paper cites Model Architecture Hint CodebookWe instantiate a paired codebook that mir- rors the size and index space of the original tokenizer code- book.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Model Architecture Hint CodebookWe instantiate a paired codebook that mir- rors the size and index space of the original tokenizer code- book

Reference 76

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:7ce742825127b40e7b5cb0fdd785e8339a7ea106273c72ce7f40001483322647

Observation eeb35c84-a469-490e-9f25-85958291fecb · outbound

This paper cites Parameters and Latency Tab.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Parameters and Latency Tab

Reference 77

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:504353c18bc1d943c838f6b09b0c84f0db1b508d851aa28b51425c1e456e4d10

Observation 2590dfab-48a3-42ce-893b-3208a35013d8 · outbound

This paper cites Tokenizer Reconstruction Limit We verify that the base tokenizer exhibits inherent recon- struction limitations even when provided perfect ground- truth input.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Tokenizer Reconstruction Limit We verify that the base tokenizer exhibits inherent recon- struction limitations even when provided perfect ground- truth input

Reference 78

Resolution
malformed identifier
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:e6c1d10410099eb20f008393fd92e1350d622672ffab83a4c560715dda62c05e

Observation 87fa9167-65b7-4e48-9a2d-a5f090de1182 · outbound

This paper cites Tokenizer-Level Failures When characters are extremely small or visually ambigu- ous, the tokenizer may assign incorrect visual tokens, lead- ing to unrecoverable errors.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Tokenizer-Level Failures When characters are extremely small or visually ambigu- ous, the tokenizer may assign incorrect visual tokens, lead- ing to unrecoverable errors

Reference 79

Resolution
malformed identifier
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:8f3d81ee183efe341ef48ac464dee4fae4456e310748438a2f318e739d07f792

Observation 5ef6ee9f-2db6-487b-9393-8416d77bb1d2 · outbound

This paper cites Training Stability and Convergence Fig.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Training Stability and Convergence Fig

Reference 80

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:798b853b82fafe54c1ac7f070b1ce1bd26e37460af21d33336d8f23957adb9d5

Observation 5f79b6ba-8353-4157-8e96-9a35684fc0a8 · outbound

This paper cites Why Shared-ID Preserves Compatibility The Shared-ID mechanism ensures that the token ID distri- bution remains identical to the base tokenizer.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Why Shared-ID Preserves Compatibility The Shared-ID mechanism ensures that the token ID distri- bution remains identical to the base tokenizer

Reference 81

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:07a5cc244ffdcbc8bd01e388d376cdc1e6e919d87443421f87d5c60832ec98fa

Observation ca134d90-e047-4119-a979-2af1d325e7b1 · outbound

This paper cites Tokenizer Results on Additional Datasets We also conduct evaluations on StyledTextVisionBlend and TextScenesHQ of TextAtlasEval [50, 66–69] to assess ro- bustness.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Tokenizer Results on Additional Datasets We also conduct evaluations on StyledTextVisionBlend and TextScenesHQ of TextAtlasEval [50, 66–69] to assess ro- bustness

Reference 82

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:d20687551beae22df40749b3b465cd63dcca13ff2782dffc311999365079721e

Observation c8cd67b9-6b62-4f39-9ec3-5103aa087381 · outbound

This paper cites Tokenizer Reconstruction Results We evaluate the reconstruction quality of different im- age tokenizers, including LlamaGen-VQ and Chameleon- VQ [43], across multiple datasets.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Tokenizer Reconstruction Results We evaluate the reconstruction quality of different im- age tokenizers, including LlamaGen-VQ and Chameleon- VQ [43], across multiple datasets

Reference 83

Resolution
malformed identifier
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:6c580e3229f8e1893b5b99b932cbd383263fa2903f11eaa371676032a6cd6531

Observation 81bfd86a-3778-4720-b47b-d67f8702d628 · outbound

This paper cites an unresolved cited work.

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering Unresolved cited work

Reference 84

Resolution
unresolved
no resolver link, observed 2026-06-28T15:39:15.744954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T15:39:15.744954Z digest=sha256:1bebbeb54ad45c0b53ed63fad2f84e6c32ca0c5949ffdd1a21166bb8f511fc75

Pith citing papers

No inbound Pith citation observations are available.