mlsanityData to 14 Oct 2026

Randomized Autoregressive Visual Generation

arXiv 2411.00776 ↗First posted 1 Nov 2024cs.CVcited by 127

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The proposed RAR is simple: during a standard autoregressive training process with a next-token prediction objective, the input sequence-typically ordered in raster form-is randomly permuted into different factorization orders with a probability r, where r starts at 1 and linearly decays to 0 over the course of training. This annealing training strategy enables the model to learn to maximize the expected likelihood over all factorization orders and thus effectively improve the model's capability of modeling bidirectional contexts. Importantly, RAR preserves the integrity of the autoregressive modeling framework, ensuring full compatibility with language modeling while significantly improving performance in image generation. On the ImageNet-256 benchmark, RAR achieves an FID score of 1.48, not only surpassing prior state-of-the-art autoregressive image generators but also outperforming leading diffusion-based and masked transformer-based methods. Code and models will be made available at https://github.com/bytedance/1d-tokenizer

Key facts. Cited by 127 papers in the map (data through 14 Oct 2026). Builds on 65 of its 81 references that are in the map. First posted on arXiv 1 Nov 2024.

Builds on

65 of 81 references.

References · 65

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  7. 2023GPT-4 Technical Reportcited by 18,396
  8. 2024The Llama 3 Herd of Modelscited by 14,715
  9. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  10. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  11. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  12. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
38 more
  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  8. 2014Going Deeper with Convolutionscited by 4,241
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  11. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  12. 2023Qwen Technical Reportcited by 3,344
  13. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  14. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  15. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  16. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  17. 2024Qwen2 Technical Reportcited by 2,120
  18. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  19. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  20. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  21. 2023PaLM 2 Technical Reportcited by 1,162
  22. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  23. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  24. 2021Scaling Vision Transformerscited by 999
  25. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  26. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  27. 2016Pixel Recurrent Neural Networkscited by 816
  28. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  29. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  30. 2018Image Transformercited by 772
  31. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 737
  32. 2022Autoregressive Image Generation using Residual Quantizationcited by 722
  33. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  34. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 694
  35. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  36. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
  37. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  38. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 79; 2026: 41.

127 papers.

Sort:

By area:

  1. 2025Improved Mean Flows: On the Challenges of Fastforward Generative Modelscited by 110
  2. 2025DDT: Decoupled Diffusion Transformercited by 109
  3. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 109
  4. 2025MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraftcited by 97
  5. 2025Masked Autoencoders Are Effective Tokenizers for Diffusion Modelscited by 96
  6. 2025Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunitiescited by 85
  7. 2024RandAR: Decoder-only Autoregressive Visual Generation in Random Orderscited by 83
  8. 2024FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matchingcited by 80
  9. 2025Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generationcited by 71
  10. 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
  11. 2025Diffusion Beats Autoregressive in Data-Constrained Settingscited by 63
  12. 2024SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizercited by 56
38 more
  1. 2025GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learningcited by 52
  2. 2025Unified Autoregressive Visual Generation and Understanding with Continuous Tokenscited by 51
  3. 2025Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokenscited by 50
  4. 2025Puppeteer: Rig and Animate Your 3D Modelscited by 43
  5. 2025Diffusion Models without Classifier-free Guidancecited by 33
  6. 2025FlowTok: Flowing Seamlessly Across Text and Image Tokenscited by 33
  7. 2025Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoningcited by 33
  8. 2024Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveycited by 27
  9. 2025Frequency Autoregressive Image Generation with Continuous Tokenscited by 27
  10. 2025"Principal Components" Enable A New Language of Imagescited by 27
  11. 2024Next Patch Prediction for Autoregressive Visual Generationcited by 26
  12. 2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminatorcited by 23
  13. 2025Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspectivecited by 22
  14. 2025Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generationcited by 21
  15. 2025LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimizationcited by 20
  16. 2025Autoregressive Image Generation with Randomized Parallel Decodingcited by 20
  17. 2025Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Modelcited by 20
  18. 2025Latent Denoising Makes Good Tokenizerscited by 20
  19. 2025Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Modelscited by 18
  20. 2025Multi-Token Prediction Needs Registerscited by 16
  21. 2025Watermarking Autoregressive Image Generationcited by 16
  22. 2025Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecturecited by 16
  23. 2025Hyperspherical Latents Improve Continuous-Token Autoregressive Generationcited by 16
  24. 2025Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformerscited by 13
  25. 2025OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Modelscited by 12
  26. 2025MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantizationcited by 12
  27. 2025Image Tokenizer Needs Post-Trainingcited by 12
  28. 2025Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropycited by 12
  29. 2025SpectralAR: Spectral Autoregressive Visual Generationcited by 11
  30. 2025Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesiscited by 10
  31. 2025Locality-aware Parallel Decoding for Efficient Autoregressive Image Generationcited by 10
  32. 2026A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokenscited by 10
  33. 2025Deeply Supervised Flow-Based Generative Modelscited by 9
  34. 2025D-AR: Diffusion via Autoregressive Modelscited by 9
  35. 2026Condition Errors Refinement in Autoregressive Image Generation with Diffusion Losscited by 9
  36. 2026Autoregressive Image Generation with Masked Bit Modelingcited by 9
  37. 2025CODA: Repurposing Continuous VAEs for Discrete Tokenizationcited by 8
  38. 2025Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attackcited by 8

50 most cited of 127 All 127 (JSON)