paper-with-me

홈 › Papers

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

2026-05-01 · Wenda Chu, Bingliang Zhang, Jiaqi Han, Yizhuo Li, Linjie Yang, Yisong Yue, Qiushan Guo 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.

📄 PDF Abstract BibTeX arXiv:2605.00503

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Results from the Paper

RankTaskDatasetModelMetrics
#24 Image Generation ImageNet 256x256 End-to-End Autoregressive Image Generati FID: 1.48

Similar Papers 제목 키워드 기반

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

2025-04-11 · Tianwei Xiong, Jun Hao Liew, Zilong Huang, Jiashi Feng 외

In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token predict…

DecoderImage GenerationImage ReconstructionRepresentation Learning

ImageFolder: Autoregressive Image Generation with Folded Tokens

2024-10-02 · Xiang Li, Kai Qiu, Hao Chen, Jason Kuen 외

Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approa…

Image GenerationImage ReconstructionQuantization

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

2025-07-11 · Anlin Zheng, Xin Wen, Xuanyang Zhang, Chuofan Ma 외

Leveraging the powerful representations of pre-trained vision foundation models -- traditionally used for visual comprehension -- we explore a novel direction: building an image tokenizer directly atop such models, a lar…

Image GenerationImage ReconstructionQuantization

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging

2026-05-29 · Luyuan Zhang, Siyuan Li, Zedong Wang, Qingsong Xie 외 arxiv

Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dense, entangled latents that are poorly sui…

Image Generation

Heptapod: Language Modeling on Visual Signals

2025-10-08 · Yongxin Zhu, Jiawei Chen, Yuanzhe Chen, Zhuo Chen 외 arxiv

We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs \textbf{causal attention}, \textbf{eliminates reliance on CFG}, and \textbf{eschews …

Self-Supervised Learning