cs.CVJan 4, 2026

Improving Flexible Image Tokenizers for Autoregressive Image Generation

Authors: Zixuan Fu, Lanqing Guo, Chong Wang, Binbin Song, Ding Liu, Bihan Wen

Organizations: Nanyang Technological University · The University of Texas at Austin · Harbin Institute of Technology · Meta AI

Abstract

Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is randomly truncated during training, and the image is reconstructed using the remaining preceding sequence. However, this tail-truncation strategy inherently concentrates the image information in the early tokens, limiting the effectiveness of downstream AutoRegressive (AR) image generation as the token length increases. To overcome these limitations, we propose ReToK, a flexible tokenizer with Redundant Token Padding and Hierarchical Semantic Regularization, designed to fully exploit all tokens for enhanced latent modeling. Specifically, we introduce Redundant Token Padding to activate tail tokens more frequently, thereby alleviating information over-concentration in the early tokens. In addition, we apply Hierarchical Semantic Regularization to align the decoding features of earlier tokens with those from a pre-trained vision foundation model, while progressively reducing the regularization strength toward the tail to allow finer low-level detail reconstruction. Extensive experiments demonstrate the effectiveness of ReTok: on ImageNet 256×\times256, our method achieves superior generation performance compared with both flexible and fixed-length tokenizers. Code will be available at: https://github.com/zfu006/ReTok

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. NesTok: Nested Self-Aligned 1D Tokenizer for Autoregressive Image Generation

    Sep 29, 2026Jiawei Zhang, Shuhao Liu, Rong Huang +4Autoregressive Image GenerationVisual Token Compression

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

    May 1, 2026Wenda Chu, Bingliang Zhang, Jiaqi Han +4Image TokenizationVisual Tokenization

  3. QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation

    Oct 7, 2026Yucheng Mao, Zeyuan Chen, Xiaojun Shan +4Visual TokenizationDiscrete Visual Tokenization