Pith. sign in

Paper Citation Record · LEDGER

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

As of 22 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2507.01756.

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

pith.paper-citation-record.v1
2507.01756 v2

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:49:43.861863Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+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

52 of 52 outbound references displayed

  • verified exact1
  • verified fuzzy8
  • unresolved43
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a309802a-78df-415a-b8d5-1b36b700a450 · outbound

This paper cites GPT-4 Technical Report.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis GPT-4 Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:40.410671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:40.410671Z digest=sha256:72075f7ac00fd06c92e69d44523979e64d406e0198f6ab01b2ee62f55391151d

Observation cae5366e-7bf8-4e17-83ae-97c1d5955c93 · outbound

This paper cites Maskgit: Masked generative image transformer.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Maskgit: Masked generative image transformer

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:49:46.043806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:40.464546Z digest=sha256:8717262bf3481ff205ea1f81e46f85bae5943f9f2fb0b7e2671bded5f0c5e399

Observation 00cb8b07-238c-497a-97e4-1ca54dcd4c11 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:40.554531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:40.554531Z digest=sha256:4b50dccec128ad1d507db447bfe1b4047750346f9170f54daeec49930f990e31

Observation 4319f330-b1b1-4e59-82b4-f7799b5cbc7d · outbound

This paper cites Flow Matching in Latent Space.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Flow Matching in Latent Space

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:40.625491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:40.625491Z digest=sha256:278cb774379fcfecd0d8c727152c7666723d9b9b1c45cd05eedf18159dca1032

Observation cd55c8ec-1eab-4532-b5ef-62cb9c5f1a27 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Imagenet: A large-scale hierarchical image database

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:40.685526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:40.685526Z digest=sha256:16cd10531bbcf2ffda7478c1d64d423e0339b03f7347a8774eaa31b82c625638

Observation 6e6c8853-496e-4ccf-96fc-b243ef21d0e2 · outbound

This paper cites Diffusion models beat gans on image synthesis.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Diffusion models beat gans on image synthesis

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:40.758768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:40.758768Z digest=sha256:a6dbc13d9309863c965ba8179b8e128801b81c661d0bf39fd26452a131aaee52

Observation 84ddbe34-a503-4eb4-a725-9b3fdef2f40f · outbound

This paper cites Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:40.829577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:40.829577Z digest=sha256:d67666db5844dafef4eefadd51f01d16b5beb88d37f622bddffef31a53548003

Observation 5989a483-4b75-4a5c-b7af-aa9ee27973ad · outbound

This paper cites MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:40.899190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:40.899190Z digest=sha256:83cfd0d2bd5cee22d597e758147139928f2402588e991a427dde86182627671c

Observation 9c513895-3858-44e2-801f-35a7c3973e81 · outbound

This paper cites Generative adversarial nets.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Generative adversarial nets

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:40.947061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:40.947061Z digest=sha256:f340491fe850d00c73aafec1094b61575f5a532a8df56c8c5618dc53b87449da

Observation 89685d0b-7292-4e1c-9d26-b03b9bc061de · outbound

This paper cites Rethinking the objectives of vector- quantized tokenizers for image synthesis.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Rethinking the objectives of vector- quantized tokenizers for image synthesis

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:49:45.775186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:41.014819Z digest=sha256:af89d885053627131eb09ef18d7cfdbcf02e22f604116a3bdd316084443a2804

Observation b0ec6ca0-9a48-423d-809d-19db8a037009 · outbound

This paper cites Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.040335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.040335Z digest=sha256:7a1ba43a5e98685719796613c300c86abc05634d014ca5c1cb519dedb1de45ca

Observation 9b89322d-464a-4921-91dd-8a1d9722eb0c · outbound

This paper cites Masked autoencoders are scalable vision learners.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Masked autoencoders are scalable vision learners

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.107673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.107673Z digest=sha256:bb6cb0fc0cb90ed5c005370c3b5751dbe709d5b70110baf84fbbb1c201583490

Observation 438627f9-f79e-4d63-9689-e9c934ca404e · outbound

This paper cites Acdit: Interpolating autoregressive con- ditional modeling and diffusion transformer.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Acdit: Interpolating autoregressive con- ditional modeling and diffusion transformer

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.159888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.159888Z digest=sha256:f287f206bb8b4bc3855837f59f7076556d0f14b83ab5461d04ef5144c6cf507b

Observation 53ed039c-2ff2-46a5-8a2c-02524a020f09 · outbound

This paper cites Auto-encoding vari- ational bayes, 2013.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Auto-encoding vari- ational bayes, 2013

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.208208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.208208Z digest=sha256:3024645feb223ecd0f4f2cf3b8ac548c41e8772ba8c9ecdf4e70e36e1ef13bda

Observation 2c6b71d6-6bb7-47fe-9e94-52c6d830322a · outbound

This paper cites Autoregressive image generation using residual quantization.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Autoregressive image generation using residual quantization

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.274498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.274498Z digest=sha256:941e4e20c5e801902dcd4bce6cdde4b8cf1cdeaa21c6161de53e92450aaef098

Observation 211cbf41-a61c-4348-acd2-e6d994ebf7a9 · outbound

This paper cites Autoregressive image generation without vec- tor quantization.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Autoregressive image generation without vec- tor quantization

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:49:45.499643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:41.322404Z digest=sha256:084bd819b33725ed79cb9953f1bccf1ce3aceb263141ce7a1326ecc8c841253f

Observation 6069cb31-1933-46e0-98a6-6c8b52e59d4d · outbound

This paper cites Flow Matching for Generative Modeling.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Flow Matching for Generative Modeling

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.373771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.373771Z digest=sha256:cf054dfca117203f954827b461fd7d040c79061d4d16761c84255c405543c440

Observation 22711448-6544-4600-b7b1-fa530e1e7e81 · outbound

This paper cites DeepSeek-V3 Technical Report.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis DeepSeek-V3 Technical Report

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.433253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.433253Z digest=sha256:e06515fbf085e225fbeb266b53f1f644df5aa46881c328aaed3aa13dec088717

Observation 04eaa166-59c1-43ab-8df6-6b53e76d5a05 · outbound

This paper cites Sit: Explor- ing flow and diffusion-based generative models with scalable interpolant transformers.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Sit: Explor- ing flow and diffusion-based generative models with scalable interpolant transformers

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:49:45.275909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:41.493078Z digest=sha256:94bda4d11eacfde85e77ec484a4b4c3ccbbb385f44d22f5227dff0ed322c6db9

Observation a68b95c8-627f-498d-bcf9-ba6bf85e8acb · outbound

This paper cites Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.574998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.574998Z digest=sha256:e31515a7cf377625b2f36550a460b7f2a16a54b623136188bc118e7ed26b6cc6

Observation 67f2e531-6908-4911-8d1d-eda963bcb022 · outbound

This paper cites Training language models to follow instructions with human feedback.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Training language models to follow instructions with human feedback

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:49:45.076547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:41.624361Z digest=sha256:e1de720e6ba4ec10884a5eb2a9f4a95163db236e46dfbf0bab3ddfa78f206a05

Observation bf60b8b0-3048-4fb7-ba33-2c4190826b07 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis RandAR: Decoder-only Autoregressive Visual Generation in Random Orders

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.683560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.683560Z digest=sha256:625f065611960c9aa3b46d4c8a10f04dc80937675ed21c84e7546153716a4abe

Observation 2057b161-365f-474f-a842-59ef6ac87f84 · outbound

This paper cites Scalable diffusion models with transformers.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Scalable diffusion models with transformers

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.750428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.750428Z digest=sha256:0fff2142fc266c7dc57fe4661cc8d575297b226f45e126682b8fa2b422a7152c

Observation 21ac6c67-a52e-4256-8c6e-c813248832d0 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.816574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.816574Z digest=sha256:bf13f0f4693e52e06c833a8e6ef8abd02ebe30e4839dec03620fb5ade43bc058

Observation c1aa9569-6165-4191-ae36-9f863a158d8a · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.857110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.857110Z digest=sha256:cf0b185f68a17beea2b7af9ccf495d939292ae4d175d39796cbb435e20cb5f6e

Observation 4f4a7ad5-af68-4dbb-bc80-118f773917b8 · outbound

This paper cites FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.897149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.897149Z digest=sha256:bf8b72c733574fe8529974a492368aa9c6baf27bd247fc8b108242a4d79e35bd

Observation b8d68fc7-c92d-4fe1-9665-c0699c2bc5a3 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis High-resolution image synthesis with latent diffusion models

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:49:44.887548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:41.937673Z digest=sha256:9b691c15cca74b943c179c32461b6ab636e1d353eb35e81a02b2237e86100ab1

Observation 7d998c79-5c41-4e98-a1c7-c77f1abbcc66 · outbound

This paper cites Scalable Image Tokenization with Index Backpropagation Quantization.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Scalable Image Tokenization with Index Backpropagation Quantization

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:41.987348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:41.987348Z digest=sha256:7a15a71c3c01b93465f094d9d2a6f9e04901ae68643a127005ddd1e8adf363ae

Observation 72d32ee3-09c9-486d-a573-65be95ab85cf · outbound

This paper cites LMFusion: Adapting Pretrained Language Models for Multimodal Generation.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis LMFusion: Adapting Pretrained Language Models for Multimodal Generation

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.028479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.028479Z digest=sha256:4d02810667b43605e9ee09283bd9c26a2783505a9bf5f13785161de7289e9304

Observation b9a6b2cb-bbb3-4952-a9d4-990b1c8e0eb4 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.079729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.079729Z digest=sha256:e31080d7dca8c0403a4e3c843cacd8e22be0bf3dc61a77dc81cd77abd0656f37

Observation e85bd7f2-1e2e-48a9-b97c-fbb89592e658 · outbound

This paper cites HART: Efficient Visual Generation with Hybrid Autoregressive Transformer.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.131239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.131239Z digest=sha256:8df5b3e1cd432944737a70ec219cb562be141bcdb3d2e6e6d2649a3459a7b948

Observation c1306bb1-7de3-49a4-96bc-601b4b48c194 · outbound

This paper cites Chameleon: Mixed-Modal Early-Fusion Foundation Models.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.173644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.173644Z digest=sha256:cdb9ff3ed4c55262c344e282ee168cb28ad6feec6e5a06a8b6a2242495e900b5

Observation 50dc8932-7767-492f-adae-b699fade339b · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Gemini: A Family of Highly Capable Multimodal Models

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.212770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.212770Z digest=sha256:33caf08405b74cfc048d443b4810be3c7581748e91ad80b24a1d0d2456d57f00

Observation 7d50339c-010c-4a7f-a9d9-0fd1ef94e139 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Visual autoregressive modeling: Scalable image generation via next-scale prediction

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:49:44.758230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:42.237158Z digest=sha256:476005581dec3862a684316d762be8743f94ce7c18ef482d4110993da2ae56ff

Observation 322ac4a2-047d-4531-a1be-351033baa8fb · outbound

This paper cites MetaMorph: Multimodal Understanding and Generation via Instruction Tuning.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.284132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.284132Z digest=sha256:72ed6d45ba5d93e5260cce887271ec0ed88114b545d87bdbd3a713fbcd544414

Observation f18bf4f7-eb8f-4599-b64f-9c7078b711ba · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis LLaMA: Open and Efficient Foundation Language Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.287458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.287458Z digest=sha256:20011ed895a47237aeacc663ea708e324fe80cc15fe00eecaae5caafa1f7af72

Observation 60cf142c-0d1e-4891-8013-64c9eb89867e · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Emu3: Next-Token Prediction is All You Need

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.290451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.290451Z digest=sha256:e595a9f05791449a21a9afac540467ed9b466a15293ec845ef5f898da8b84ae6

Observation d1fd3900-2d4a-4d36-ae27-49912d0fd5cb · outbound

This paper cites Parallelized Autoregressive Visual Generation.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Parallelized Autoregressive Visual Generation

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.343208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.343208Z digest=sha256:ee6c904ff5045fc3f8be77f39fb7b47fa4de53606a402219d5377f2e4c2a753f

Observation 85a12cc2-0cc3-45f8-9281-971b9f89b4c1 · outbound

This paper cites MaskBit: Embedding-free Image Generation via Bit Tokens.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis MaskBit: Embedding-free Image Generation via Bit Tokens

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.481613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.481613Z digest=sha256:add8f1c25ca535304f777cc66c46696da9b4184021cddf56d916e80881add962

Observation 02909b14-599a-4213-8fb1-3299d79fad49 · outbound

This paper cites Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.607415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.607415Z digest=sha256:12928751e5d86a69118821cd2b3985e2f3bd1950ebda3db8b1e65359fd9bedf5

Observation 39649940-d2d2-4b84-a25a-18ceaa21d517 · outbound

This paper cites VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.711070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.711070Z digest=sha256:43bcc70f16014dc58438922d125252826a08188ba6980b8549ff2afd2776720c

Observation 869db5e1-b857-47b5-8e0a-695c22df2881 · outbound

This paper cites Show-o: One Single Transformer to Unify Multimodal Understanding and Generation.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.844718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.844718Z digest=sha256:60d32238c152a55985d0fc4a6d2ec555c4ad7a52d0a8c12a5fb3e3e367319bc3

Observation 2f8b32c0-e3f5-4db2-8a04-60aeb491a8b6 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:42.947470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:42.947470Z digest=sha256:174c963a2bc48bddc9c788bd23668f8a8095ec447cebfcb97fef190741433dff

Observation 4264b34a-0145-43a7-b8a9-af568f2feeb6 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Vector-quantized Image Modeling with Improved VQGAN

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:43.043700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:43.043700Z digest=sha256:db10e51650bc9ad12d51cfbd19c62e9b1c2be515dcfcde935d1520cd749972e4

Observation 5243dc39-6e11-4294-8cb1-3398367a1f88 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:43.124751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:43.124751Z digest=sha256:d25062bb204f24336bb7913d18a47515aa477cefbf29d36385b2e3fe254d5b73

Observation bda0f952-1934-40e7-9ecf-3484d0b1c84e · outbound

This paper cites Randomized Autoregressive Visual Generation.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Randomized Autoregressive Visual Generation

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:43.182816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:43.182816Z digest=sha256:8d5b17b7c6d94700d3d85caf0d659231b9c404a320dccf1e3937de93aeee50fb

Observation 15c9e044-620f-4134-bb06-cb48332ec1fc · outbound

This paper cites An image is worth 32 tokens for reconstruction and generation.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis An image is worth 32 tokens for reconstruction and generation

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:49:44.528120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:43.247653Z digest=sha256:438e88290e709340a91ce3083c786b99c0ea4cc6331f5309c28723f27fba1e5f

Observation 671bf3f0-4caa-426b-b482-c9e8b2d400ae · outbound

This paper cites Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:43.401412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:43.401412Z digest=sha256:302e9aa99a883279cc55e1decefa38aa2d09f78bb98ec2c24c7edb4cc2b0b319

Observation 8b75ad89-6988-4f41-a8aa-8ed91ed62049 · outbound

This paper cites E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling

Reference 49

Resolution
verified exact
local_arxiv, observed 2026-08-06T20:49:44.067966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-06T20:49:43.543357Z digest=sha256:ed31e2b67e1fe324f36cc6355b686d8667bc6a12792232bb38bad225e35a99ec

Observation 13829bd9-c1ef-4d9a-b6d1-7032636d9a26 · outbound

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

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Fast Training of Diffusion Models with Masked Transformers

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:43.657417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:43.657417Z digest=sha256:4abd8298b9da3b2da3b21492abcb674d31077613ef31d64459b516edf41085a0

Observation ebe5efca-5ca9-4ca0-89f6-547a70e773c0 · outbound

This paper cites Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-06T20:49:43.758080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:43.758080Z digest=sha256:b4e8c831a26defb75f40c5bed9b419f9d721fc95490035db8e910ad4bd1294b9

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

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

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

Reference 52

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

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:49:43.861863Z digest=sha256:3c17c58b406e1e59ed82ae5ffa25a4f91d69fd1bbd3e490e22f19966e49e3ab2

Pith citing papers

No inbound Pith citation observations are available.