mlsanityData to 14 Oct 2026

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

arXiv 2507.04947 ↗First posted 7 Jul 2025cs.CV cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency. Due to the tokenizers' limitations, prior masked AR models have lagged behind diffusion models in terms of quality or efficiency. We overcome this limitation by introducing DC-HT - a deep compression hybrid tokenizer for AR models that achieves a 32x spatial compression ratio while maintaining high reconstruction fidelity and cross-resolution generalization ability. Building upon DC-HT, we extend MaskGIT and create a new hybrid masked autoregressive image generation framework that first produces the structural elements through discrete tokens and then applies refinements via residual tokens. DC-AR achieves state-of-the-art results with a gFID of 5.49 on MJHQ-30K and an overall score of 0.69 on GenEval, while offering 1.5-7.9x higher throughput and 2.0-3.5x lower latency compared to prior leading diffusion and autoregressive models.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 64 of its 72 references that are in the map. First posted on arXiv 7 Jul 2025.

Builds on

64 of 72 references.

References · 64

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  8. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  11. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  12. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
38 more
  1. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  2. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  3. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  4. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  5. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  6. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  7. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  8. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  9. 2023VILA: On Pre-training for Visual Language Modelscited by 692
  10. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
  11. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  12. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  13. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 492
  14. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  15. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 484
  16. 2022MAGVIT: Masked Generative Video Transformercited by 346
  17. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 340
  18. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 329
  19. 2022CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformerscited by 307
  20. 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 304
  21. 2024An Image is Worth 32 Tokens for Reconstruction and Generationcited by 302
  22. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationcited by 295
  23. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  24. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 256
  25. 2024ShieldGemma: Generative AI Content Moderation Based on Gemmacited by 243
  26. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 227
  27. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 217
  28. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 205
  29. 2024TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generationcited by 202
  30. 2024World Model on Million-Length Video And Language With Blockwise RingAttentioncited by 198
  31. 2025SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformercited by 165
  32. 2024Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretrainingcited by 150
  33. 2024Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokenscited by 147
  34. 2024PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Modelscited by 141
  35. 2024HART: Efficient Visual Generation with Hybrid Autoregressive Transformercited by 132
  36. 2024Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Modelscited by 116
  37. 2025FlexTok: Resampling Images into 1D Token Sequences of Flexible Lengthcited by 110
  38. 2024MaskBit: Embedding-free Image Generation via Bit Tokenscited by 98

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 9.

13 papers.

Sort:

By area:

  1. 2025HPSv3: Towards Wide-Spectrum Human Preference Scorecited by 211
  2. 2025Next-Embedding Prediction Makes Strong Vision Learnerscited by 23
  3. 2026Let EEG Models Learn EEGcited by 7
  4. 2025Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddingscited by 6
  5. 2026TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Modelscited by 4
  6. 2026From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Modelscited by 3
  7. 2026VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generationscited by 1
  8. 2025Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learningcited by 0
  9. 2026LINA: Linear Autoregressive Image Generative Models with Continuous Tokenscited by 0
  10. 2026High-Fidelity Text-to-Image Generation from Pre-Trained Vision-Language Models via Distribution-Conditioned Diffusion Decodingcited by 0
  11. 2026Conditional Predictive Sufficient Statistics for Visual Representation Learningcited by 0
  12. 2026Generative Residual Factorizationcited by 0
1 more
  1. 2026One-Step Next-Latent Prediction Is Not a World Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation
  2. 2025Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens
  3. 2025Fast Autoregressive Models for Continuous Latent Generation
  4. 2025Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
  5. 2026Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation
  6. 2024Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
  7. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
  8. 2025Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation