ResTok：面向自回归图像生成的一维视觉分词器分层残差学习

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation

January 7, 2026

作者: Xu Zhang, Cheng Da, Huan Yang, Kun Gai, Ming Lu, Zhan Ma

cs.AI

摘要

现有的一维视觉分词器在自回归生成任务中主要遵循语言模型的设计原则，这些方法直接基于源自语言先验的Transformer架构，生成单层次潜在标记，并将视觉数据视为扁平化的序列标记流。然而，这种类语言的处理方式忽略了视觉数据的关键特性，尤其是长期以来对视觉模型收敛性和效率至关重要的层次化结构与残差网络设计。为了将"视觉本质"重新引入视觉任务，我们提出残差分词器（ResTok），这是一种通过构建图像标记和潜在标记的层次化残差的一维视觉分词器。通过逐级合并获得的层次化表征，可在每一层实现跨层级特征融合，显著提升表征能力。同时，层次间的语义残差可避免信息重叠，生成更集中的潜在分布，从而更易于自回归建模。这种设计自然催生了无需显式约束的跨层级绑定机制。为加速生成过程，我们进一步提出层次化自回归生成器，通过一次性预测整个层级的潜在标记而非严格逐标记生成，大幅减少采样步数。大量实验表明，在视觉分词中恢复层次化残差先验能显著提升自回归图像生成效果，在ImageNet-256数据集上仅需9个采样步数即可达到2.34的gFID指标。代码已开源：https://github.com/Kwai-Kolors/ResTok。

English

Existing 1D visual tokenizers for autoregressive (AR) generation largely follow the design principles of language modeling, as they are built directly upon transformers whose priors originate in language, yielding single-hierarchy latent tokens and treating visual data as flat sequential token streams. However, this language-like formulation overlooks key properties of vision, particularly the hierarchical and residual network designs that have long been essential for convergence and efficiency in visual models. To bring "vision" back to vision, we propose the Residual Tokenizer (ResTok), a 1D visual tokenizer that builds hierarchical residuals for both image tokens and latent tokens. The hierarchical representations obtained through progressively merging enable cross-level feature fusion at each layer, substantially enhancing representational capacity. Meanwhile, the semantic residuals between hierarchies prevent information overlap, yielding more concentrated latent distributions that are easier for AR modeling. Cross-level bindings consequently emerge without any explicit constraints. To accelerate the generation process, we further introduce a hierarchical AR generator that substantially reduces sampling steps by predicting an entire level of latent tokens at once rather than generating them strictly token-by-token. Extensive experiments demonstrate that restoring hierarchical residual priors in visual tokenization significantly improves AR image generation, achieving a gFID of 2.34 on ImageNet-256 with only 9 sampling steps. Code is available at https://github.com/Kwai-Kolors/ResTok.