mlsanityData to 7 Oct 2026

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

arXiv 2605.00503 ↗First posted 1 May 2026cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 48 of its 55 references that are in the map. First posted on arXiv 1 May 2026.

Builds on

48 of 55 references.

References · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2022Scalable Diffusion Models with Transformerscited by 5,931
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2017Neural Discrete Representation Learningcited by 4,650
  12. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
36 more
  1. 2016Improved Techniques for Training GANscited by 2,938
  2. 2020GLU Variants Improve Transformercited by 1,724
  3. 2019Root Mean Square Layer Normalizationcited by 1,425
  4. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  5. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  6. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  7. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  8. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  9. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
  10. 2022Autoregressive Image Generation using Residual Quantizationcited by 706
  11. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  12. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  13. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  14. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  15. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 425
  16. 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Modelscited by 376
  17. 2024An Image is Worth 32 Tokens for Reconstruction and Generationcited by 295
  18. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286
  19. 2025Diffusion Transformers with Representation Autoencoderscited by 275
  20. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  21. 2025REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformerscited by 212
  22. 2023Making LLaMA SEE and Draw with SEED Tokenizercited by 184
  23. 2023Fast Training of Diffusion Models with Masked Transformerscited by 172
  24. 2024Randomized Autoregressive Visual Generationcited by 125
  25. 2021Regularizing Generative Adversarial Networks under Limited Datacited by 105
  26. 2025FlexTok: Resampling Images into 1D Token Sequences of Flexible Lengthcited by 105
  27. 2025Latent Diffusion Model without Variational Autoencodercited by 83
  28. 2023Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantizationcited by 59
  29. 2025GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generationcited by 55
  30. 2024Scalable Image Tokenization with Index Backpropagation Quantizationcited by 44
  31. 2025AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Modelscited by 35
  32. 2025Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Modelcited by 20
  33. 2025Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generationcited by 20
  34. 2025VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Modelscited by 16
  35. 2025SpectralAR: Spectral Autoregressive Visual Generationcited by 11
  36. 2026ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modelingcited by 2
  2. 2026GEAR: Guided End-to-End AutoRegression for Image Synthesiscited by 1
  3. 2026Beyond Token-Level Cross-Entropy: Fr'echet Distributional Post-Training for Autoregressive Image Generationcited by 0
  4. 2026NesTok: Nested Self-Aligned 1D Tokenizer for Autoregressive Image Generationcited by 0
  5. 2026Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Modelscited by 0