DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer | Paper Citation Record

Observation 34dd3310-39fe-4f53-a573-f35974eb1cd1 · outbound

This paper cites FlexTok: Resampling Images into 1D Token Sequences of Flexible Length.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.597184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12388c83-15cb-42a7-aad7-f388b1f89336 · outbound

This paper cites Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.601433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b34dd59c-ddf7-498e-8ecd-29082de15795 · outbound

This paper cites All are worth words: A vit backbone for diffusion models.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer All are worth words: A vit backbone for diffusion models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.602385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1b725b72-339a-46c0-8f26-3a378878204c · outbound

This paper cites Flux, 2024.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Flux, 2024

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.593338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4cec7b2a-686c-4369-a2fd-a9e758073b30 · outbound

This paper cites Efficientvit: Lightweight multi-scale attention for high- resolution dense prediction.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Efficientvit: Lightweight multi-scale attention for high- resolution dense prediction

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.583437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 745ad257-39eb-4eba-aade-9af00a02f3e0 · outbound

This paper cites Condition-aware neural network for controlled image generation.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Condition-aware neural network for controlled image generation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.572142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 047dad19-1554-4487-9528-3b8954e7e9d6 · outbound

This paper cites Maskgit: Masked generative image transformer.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Maskgit: Masked generative image transformer

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.560754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0757d32b-5882-4aac-a7ab-e83195aef7f6 · outbound

This paper cites Muse: Text-To-Image Generation via Masked Generative Transformers.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Muse: Text-To-Image Generation via Masked Generative Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.621281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f40565-28e3-4d95-bbfe-fa5f79d53533 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.624757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 137e2f05-51d3-4712-84a0-7b96c1511d17 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Masked Autoencoders Are Effective Tokenizers for Diffusion Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.628002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a32b09d4-4e31-4bb0-b5a3-beb141350c54 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.631407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ba7edef-3ab1-4b73-a8ab-98746842fe2c · outbound

This paper cites Pixart- σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Pixart- σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.550348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1ccf0a15-739d-47c5-9915-32ae42beb7c9 · outbound

This paper cites PIXART-{\delta}: Fast and Controllable Image Generation with Latent Consistency Models.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer PIXART-{\delta}: Fast and Controllable Image Generation with Latent Consistency Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.637843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f6b40b9-ce03-41c3-9da7-c0df6c9da372 · outbound

This paper cites Pixart- α: Fast training of diffusion transformer for photorealistic text-to-image synthesis.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Pixart- α: Fast training of diffusion transformer for photorealistic text-to-image synthesis

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.539299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e8a436c8-2254-4d9e-92f2-2f1249cd3316 · outbound

This paper cites MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.643833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db8be56c-dd30-42d4-8ed1-30208cf160cb · outbound

This paper cites Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.646952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3f8b3ac-f320-46cd-8758-8e241995f1bb · outbound

This paper cites Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.650563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1905c30c-1215-4bfb-b4ec-04f85879daa4 · outbound

This paper cites Vqgan-clip: Open domain image generation and editing with natural language guidance.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Vqgan-clip: Open domain image generation and editing with natural language guidance

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.528012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2e503436-5d51-4628-b25e-9fff171b8223 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Imagenet: A large-scale hierarchical image database

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.517000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3dc5b9e6-e0b5-4149-b72d-e91cbb5a07dd · outbound

This paper cites Bert: Pre-training of deep bidirectional trans- formers for language understanding.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Bert: Pre-training of deep bidirectional trans- formers for language understanding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.659371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b26dfbd7-02f7-408d-a6c8-daa19cfa3668 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Cogview: Mastering text-to-image generation via transformers

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.499523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ed0c676b-6098-46ad-aa37-1aa6ec6573e9 · outbound

This paper cites Cogview2: Faster and better text-to-image generation via hierarchical transformers.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Cogview2: Faster and better text-to-image generation via hierarchical transformers

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.487740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bf37ec64-e006-42f6-a2c2-d3cb9b640474 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Taming transformers for high-resolution image synthesis

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.668024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd3707a4-1393-4e79-a4a8-870fe9598436 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.670970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff003569-80a0-4a66-a324-9c1a05f1c1a9 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.673806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cbe8f3e-1ded-4354-af83-b2672b2a4d1d · outbound

This paper cites Make-a-scene: Scene- based text-to-image generation with human priors.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Make-a-scene: Scene- based text-to-image generation with human priors

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.453151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 02221b71-5d38-4501-90ea-30a1900a85e3 · outbound

This paper cites Geneval: An object-focused framework for evaluating text- to-image alignment.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Geneval: An object-focused framework for evaluating text- to-image alignment

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.442337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4ad5d9f1-7fac-4d07-8739-4632c1a45992 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.683029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 188553c7-4b49-4eb3-a5f5-8047a6497060 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilib- rium.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Gans trained by a two time-scale update rule converge to a local nash equilib- rium

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.685861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7737570e-471b-4ad9-8965-39b0e94ec915 · outbound

This paper cites LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.688829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d468d8-6607-4641-8640-b7445fdc2ca0 · outbound

This paper cites Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.691857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14c41753-a012-4487-a846-551f7d8cc919 · outbound

This paper cites Videopoet: A large language model for zero-shot video gen- eration.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Videopoet: A large language model for zero-shot video gen- eration

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.425715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ad64d74f-3a96-4457-af1b-4ad3542c923a · outbound

This paper cites Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.697555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d018cac0-b23c-4277-9dc4-1541957b1376 · outbound

This paper cites Mage: Masked generative encoder to unify representation learning and image synthe- sis.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Mage: Masked generative encoder to unify representation learning and image synthe- sis

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.700734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b558d4a-4b2c-4a46-acf1-1aa8dd686bf9 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Autoregressive image generation without vec- tor quantization

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.406704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation da46fd01-6f63-4522-9731-2f592007beca · outbound

This paper cites ControlVAR: Exploring Controllable Visual Autoregressive Modeling.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer ControlVAR: Exploring Controllable Visual Autoregressive Modeling

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.707412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61176306-b6d5-4f11-adea-42bbed8557de · outbound

This paper cites Vila: On pre-training for vi- sual language models.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Vila: On pre-training for vi- sual language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.395848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7a3d0dcb-6129-494c-8159-78cd2e95eefa · outbound

This paper cites Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.713635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2bd89df-c72d-4e5d-8a5c-2f7b2e9f196a · outbound

This paper cites Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.716761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e17c38-ac4e-4510-a198-8794726844f2 · outbound

This paper cites World Model on Million-Length Video And Language With Blockwise RingAttention.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer World Model on Million-Length Video And Language With Blockwise RingAttention

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.720034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05608fb7-ecfb-41a0-b473-66459712bb50 · outbound

This paper cites Exploring the role of large language models in prompt encoding for diffusion models.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Exploring the role of large language models in prompt encoding for diffusion models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.385166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 217bf85a-1191-4a80-8f3b-3e43d2497ea0 · outbound

This paper cites STAR: Scale-wise Text-conditioned AutoRegressive image generation.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer STAR: Scale-wise Text-conditioned AutoRegressive image generation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.726623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a459c38-41de-4b25-bb4f-1463c15ff854 · outbound

This paper cites Hello gpt-4o, 2024.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Hello gpt-4o, 2024

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.373082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e70fe837-c7d5-4f4b-b432-cad4b1270b93 · outbound

This paper cites Scalable diffusion models with transformers.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Scalable diffusion models with transformers

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.732818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d32be879-4738-4d53-8d2a-1f2e9962b981 · outbound

This paper cites W ¨urstchen: An ef- ficient architecture for large-scale text-to-image diffusion models.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer W ¨urstchen: An ef- ficient architecture for large-scale text-to-image diffusion models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.356049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 387bf42c-f125-42aa-942a-126750c839f8 · outbound

This paper cites Sdxl: Improving latent diffusion models for high-resolution image synthesis.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Sdxl: Improving latent diffusion models for high-resolution image synthesis

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.345544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e77a85cc-3c45-4774-b6cd-e6648a3feeb8 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.743296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96036b35-5845-4c61-89e6-8ba9814ae24e · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Exploring the limits of transfer learning with a unified text-to-text transformer

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.334820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 514fabfe-dc50-4fb9-8220-db01381d887b · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Zero-shot text-to-image generation

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.749368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b59c94d5-6f14-4b37-a016-3c49affc816d · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer High-resolution image synthesis with latent diffusion models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.752473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98a0a5e4-7bc7-4417-86af-e1c317274499 · outbound

This paper cites Journeydb: A benchmark for generative im- age understanding.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Journeydb: A benchmark for generative im- age understanding

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.310911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b3db0879-fb1b-466e-8256-142c6ec613f1 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.758914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32ffb138-09c0-44ba-ae2e-ee0063776e3d · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.762860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef40a9a9-7bfc-4dea-91d1-b34525e77634 · outbound

This paper cites Introducing auraflow v0.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Introducing auraflow v0

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.299918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ea4877f2-701f-4f21-a926-cce601e32e35 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Gemini: A Family of Highly Capable Multimodal Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.769261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05c6b64d-7efb-40a4-b309-aa4736357ae1 · outbound

This paper cites Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.289469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 47186ff9-ba17-4818-a852-85093f69afeb · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Visual autoregressive modeling: Scalable image generation via next-scale prediction

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.277788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 24ca1245-6f49-4bc6-8998-30b18845bdf7 · outbound

This paper cites Neural discrete representation learning.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Neural discrete representation learning

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.778537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e18e3c3e-01c1-45dd-a062-775cf528945c · outbound

This paper cites Phenaki: Variable Length Video Generation From Open Domain Textual Description.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Phenaki: Variable Length Video Generation From Open Domain Textual Description

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.781644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b48ac4f-56d7-4001-9c42-9910aba55a29 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Emu3: Next-Token Prediction is All You Need

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.784989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeb2ad6d-4043-4c25-9816-35067e89fed0 · outbound

This paper cites Parallelized Autoregressive Visual Generation.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Parallelized Autoregressive Visual Generation

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.788082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e389e7-0f61-43f6-b4b9-303926d15be5 · outbound

This paper cites Maskbit: Embedding-free image generation via bit tokens.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Maskbit: Embedding-free image generation via bit tokens

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.258779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b6830a1d-9454-4d9e-9dc4-fdfa04d5e7f3 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.793876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d49930b-816d-492d-a59a-bb82a5337018 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.796917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a94fa02-2984-48fc-8485-0a6fe88377f3 · outbound

This paper cites SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.799913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17170477-082e-4982-9a7a-c920950cf2bd · outbound

This paper cites SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.803601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d9a9c8d-afb2-4b25-9f0c-0017bc5bd809 · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.806841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7220a54c-9e3d-467b-bfcd-98c904db1064 · outbound

This paper cites CAR: Controllable Autoregressive Modeling for Visual Generation.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer CAR: Controllable Autoregressive Modeling for Visual Generation

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.810106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d469825-40e3-496d-81ae-64fe1f51a583 · outbound

This paper cites Scaling autoregres- sive models for content-rich text-to-image generation.Trans.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Scaling autoregres- sive models for content-rich text-to-image generation.Trans

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.247703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a4399186-bebf-4829-8b73-eacedc0fa28e · outbound

This paper cites Magvit: Masked generative video transformer.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Magvit: Masked generative video transformer

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.237240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 852f6685-331f-4262-8912-dd1508fe325f · outbound

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

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer An image is worth 32 tokens for reconstruction and generation

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.226993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0cbbcf26-880c-45f5-b390-3b08383a86aa · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.821729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04a282f2-e224-4651-b17e-bd2a670c7af5 · outbound

This paper cites Language-Guided Image Tokenization for Generation.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Language-Guided Image Tokenization for Generation

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.825012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43ad1ff8-72f0-4a82-99e6-2f3e1f952c7e · outbound

This paper cites VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.828655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b79ced7-fa55-4df9-a90c-e187a0b47102 · outbound

This paper cites A red heart.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer A red heart

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:41:24.215300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers