mlsanityData to 7 Oct 2026

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

arXiv 2501.07730 ↗First posted 13 Jan 2025cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them challenging to replicate. In this work, we introduce Text-Aware Transformer-based 1-Dimensional Tokenizer (TA-TiTok), an efficient and powerful image tokenizer that can utilize either discrete or continuous 1-dimensional tokens. TA-TiTok uniquely integrates textual information during the tokenizer decoding stage (i.e., de-tokenization), accelerating convergence and enhancing performance. TA-TiTok also benefits from a simplified, yet effective, one-stage training process, eliminating the need for the complex two-stage distillation used in previous 1-dimensional tokenizers. This design allows for seamless scalability to large datasets. Building on this, we introduce a family of text-to-image Masked Generative Models (MaskGen), trained exclusively on open data while achieving comparable performance to models trained on private data. We aim to release both the efficient, strong TA-TiTok tokenizers and the open-data, open-weight MaskGen models to promote broader access and democratize the field of text-to-image masked generative models.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 57 of its 72 references that are in the map. First posted on arXiv 13 Jan 2025.

Builds on

57 of 72 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  8. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  9. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  10. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  11. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  12. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
38 more
  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  2. 2022Scalable Diffusion Models with Transformerscited by 5,931
  3. 2022Classifier-Free Diffusion Guidancecited by 5,717
  4. 2016Layer Normalizationcited by 5,579
  5. 2017Neural Discrete Representation Learningcited by 4,650
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2016Improved Techniques for Training GANscited by 2,938
  12. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  13. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  14. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  15. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  16. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  17. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
  18. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  19. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  20. 2018Image Transformercited by 770
  21. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
  22. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  23. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  24. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  25. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
  26. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  27. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  28. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 498
  29. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  30. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  31. 2022MAGVIT: Masked Generative Video Transformercited by 341
  32. 2024An Image is Worth 32 Tokens for Reconstruction and Generationcited by 295
  33. 2016Using the Output Embedding to Improve Language Modelscited by 266
  34. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 249
  35. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 222
  36. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 203
  37. 2024Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generationcited by 153
  38. 2024Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokenscited by 147

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 22; 2026: 26.

48 papers.

Sort:

By area:

  1. 2025REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformerscited by 212
  2. 2025Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generationcited by 71
  3. 2025UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editingcited by 43
  4. 2025FlowTok: Flowing Seamlessly Across Text and Image Tokenscited by 31
  5. 2025AToken: A Unified Tokenizer for Visioncited by 30
  6. 2025Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Modelcited by 20
  7. 2025Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformerscited by 13
  8. 2025DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizercited by 13
  9. 2025Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generationcited by 12
  10. 2025Image Tokenizer Needs Post-Trainingcited by 10
  11. 2025Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesiscited by 9
  12. 2026A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokenscited by 9
36 more
  1. 2025Deeply Supervised Flow-Based Generative Modelscited by 8
  2. 2026Laminating Representation Autoencoders for Efficient Diffusioncited by 6
  3. 2026Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Modelcited by 6
  4. 2025Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generationcited by 5
  5. 2025Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddingscited by 5
  6. 2025Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Modelcited by 5
  7. 2026CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenizationcited by 5
  8. 2026PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulationcited by 4
  9. 2026DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignmentcited by 4
  10. 2025Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokenscited by 3
  11. 2025FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokenscited by 3
  12. 2025Plan-X: Instruct Video Generation via Semantic Planningcited by 3
  13. 2026Adaptive 1D Video Diffusion Autoencodercited by 3
  14. 2026UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Modelscited by 3
  15. 2026Baton: Explicit Semantic Blueprints for Joint Video-Audio Generationcited by 3
  16. 2025Aligning Latent Spaces with Flow Priorscited by 2
  17. 2025Discrete JEPA: Learning Discrete Token Representations without Reconstructioncited by 2
  18. 2026TaskTok: Delving into Task Tokens for Task-driven Image Restorationcited by 2
  19. 2025Improved Masked Image Generation with Knowledge-Augmented Token Representationscited by 1
  20. 2026Soft Tail-dropping for Adaptive Visual Tokenizationcited by 1
  21. 2026Kelix Technical Reportcited by 1
  22. 2026Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewardscited by 1
  23. 2026Generative Video Compression with One-Dimensional Latent Representationcited by 1
  24. 2026FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matchingcited by 1
  25. 2026VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generationscited by 1
  26. 2026One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iterationcited by 1
  27. 2026AVTok: 1D Unified Tokenization for Holistic Audio-Video Generationcited by 1
  28. 2025Temporal-Visual Semantic Alignment: A Unified Architecture for Transferring Spatial Priors from Vision Models to Zero-Shot Temporal Taskscited by 0
  29. 2026Semantic-Aware Prefix Learning for Token-Efficient Image Generationcited by 0
  30. 2026Autoregressive Visual Generation Needs a Prologuecited by 0
  31. 2026Channel-wise Vector Quantizationcited by 0
  32. 2026MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Mergingcited by 0
  33. 2026Balancing Image Compression and Generation with Bootstrapped Tokenizationcited by 0
  34. 2026Test-Time Registers as Global Priors for Tokenized Image Generationcited by 0
  35. 2026Studying Image Tokenizers as Visual Languages in Unified Multimodal Modelscited by 0
  36. 2026NesTok: Nested Self-Aligned 1D Tokenizer for Autoregressive Image Generationcited by 0