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

• URL: http://arxiv.org/abs/2605.00503v2
• Date: Mon, 04 May 2026 10:19:31 GMT
• Title: End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
• Abstract summary: Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations.<n>We design an end-to-end training pipeline that jointly optimize reconstruction and generation, enabling direct supervision from generation results to the tokenizer.<n>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.
• Score: 43.94302725619101
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training [23.632047555553324]
  We introduce a novel two-stage training framework for pixel-space diffusion and consistency models.<n>Our training framework demonstrates strong empirical performance on ImageNet dataset.<n>To the best of our knowledge, this marks the first successful training of a consistency model directly on high-resolution images.
  arXiv  Detail & Related papers  (2025-10-14T14:41:16Z)
• NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale [101.57871281101747]
  NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks.<n>Our method shows strong performance in image editing, highlighting the power and versatility of our unified approach.
  arXiv  Detail & Related papers  (2025-08-14T14:54:22Z)
• Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation [52.261584726401686]
  We present a novel direction to build an image tokenizer directly on top of a frozen vision foundation model.<n>Based on these designs, our proposed image tokenizer, VFMTok, achieves substantial improvements in image reconstruction and generation quality.
  arXiv  Detail & Related papers  (2025-07-11T09:32:45Z)
• Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation [27.795313102716726]
  We introduce 1D binary image latents for compact discrete representation of images.<n>Our approach preserves high-resolution details while maintaining the compactness of 1D latents.<n>Our text-to-image models are the first to achieve competitive performance in both diffusion and auto-regressive generation.
  arXiv  Detail & Related papers  (2025-06-26T05:48:36Z)
• D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens [80.75893450536577]
  We propose D2C, a novel two-stage method to enhance model generation capacity.<n>In the first stage, the discrete-valued tokens representing coarse-grained image features are sampled by employing a small discrete-valued generator.<n>In the second stage, the continuous-valued tokens representing fine-grained image features are learned conditioned on the discrete token sequence.
  arXiv  Detail & Related papers  (2025-03-21T13:58:49Z)
• Frequency Autoregressive Image Generation with Continuous Tokens [31.833852108014312]
  We introduce the frequency progressive autoregressive (textbfFAR) paradigm and instantiate FAR with the continuous tokenizer.<n>We demonstrate the efficacy of FAR through comprehensive experiments on the ImageNet dataset.
  arXiv  Detail & Related papers  (2025-03-07T10:34:04Z)
• ARFlow: Autoregressive Flow with Hybrid Linear Attention [48.707933347079894]
  Flow models are effective at progressively generating realistic images.<n>They struggle to capture long-range dependencies during the generation process.<n>We propose integrating autoregressive modeling into flow models.
  arXiv  Detail & Related papers  (2025-01-27T14:33:27Z)
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [62.57727062920458]
  We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL.<n>We leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers.<n>Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images.
  arXiv  Detail & Related papers  (2024-10-10T17:59:17Z)
• Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation [52.509092010267665]
  We introduce LlamaGen, a new family of image generation models that apply original next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive models, e.g., Llama, without inductive biases on visual signals can achieve state-of-the-art image generation performance if scaling properly.
  arXiv  Detail & Related papers  (2024-06-10T17:59:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.