尺度级变分自回归实为离散扩散

摘要

自回归（AR）变换器已成为视觉生成领域的一股强大力量，这主要得益于其可扩展性、计算效率以及与语言和视觉相统一的架构。其中，基于下一尺度预测的视觉自回归生成（VAR）近期展现了卓越性能，甚至超越了基于扩散的模型。在本研究中，我们重新审视VAR并揭示了一个理论洞见：当配备马尔可夫注意力掩码时，VAR在数学上等价于离散扩散。我们将这一重新诠释命名为“基于离散扩散的可扩展视觉精炼”（SRDD），从而在AR变换器与扩散模型之间建立了一座原则性的桥梁。借助这一新视角，我们展示了如何直接将扩散模型的优势，如迭代精炼和减少架构低效性，引入VAR，从而实现更快的收敛、更低的推理成本以及改进的零样本重建。在多个数据集上，我们证明了基于扩散视角的VAR在效率和生成质量上均带来了持续提升。

English

Autoregressive (AR) transformers have emerged as a powerful paradigm for visual generation, largely due to their scalability, computational efficiency and unified architecture with language and vision. Among them, next scale prediction Visual Autoregressive Generation (VAR) has recently demonstrated remarkable performance, even surpassing diffusion-based models. In this work, we revisit VAR and uncover a theoretical insight: when equipped with a Markovian attention mask, VAR is mathematically equivalent to a discrete diffusion. We term this reinterpretation as Scalable Visual Refinement with Discrete Diffusion (SRDD), establishing a principled bridge between AR transformers and diffusion models. Leveraging this new perspective, we show how one can directly import the advantages of diffusion such as iterative refinement and reduce architectural inefficiencies into VAR, yielding faster convergence, lower inference cost, and improved zero-shot reconstruction. Across multiple datasets, we show that the diffusion based perspective of VAR leads to consistent gains in efficiency and generation.

尺度级变分自回归实为离散扩散

Scale-Wise VAR is Secretly Discrete Diffusion

摘要

Support