While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently complexity-aware, as evidenced by their variable likelihoods, but are often hindered by lossy discrete tokenization and error accumulation. In this work, we introduce Generative Refinement Networks (GRN), a next-generation visual synthesis paradigm to address these issues. At its core, GRN addresses the discrete tokenization bottleneck through a theoretically near-lossless Hierarchical Binary Quantization (HBQ), achieving a reconstruction quality comparable to continuous counterparts. Built upon HBQ's latent space, GRN fundamentally upgrades AR generation with a global refinement mechanism that progressively perfects and corrects artworks -- like a human artist painting. Besides, GRN integrates an entropy-guided sampling strategy, enabling complexity-aware, adaptive-step generation without compromising visual quality. On the ImageNet benchmark, GRN establishes new records in image reconstruction (0.56 rFID) and class-conditional image generation (1.81 gFID). We also scale GRN to more challenging text-to-image and text-to-video generation, delivering superior performance on an equivalent scale. We release all models and code to foster further research on GRN.

翻译：尽管扩散模型在视觉生成领域占据主导地位，但其计算效率低下，对不同复杂度的任务采用统一的计算量。相比之下，自回归（AR）模型因其可变似然性而天然具备复杂度感知能力，但常受限于有损离散标记化和误差累积。本文提出下一代视觉合成范式——生成式精炼网络（GRN），以解决上述问题。其核心在于通过理论上的近乎无损的分层二元量化（HBQ）突破离散标记化瓶颈，实现与连续模型媲美的重构质量。基于HBQ的潜在空间，GRN从根本上升级了自回归生成，引入全局精炼机制——如同人类画家作画般逐步完善和修正作品。此外，GRN融合了熵引导采样策略，能在不牺牲视觉质量的前提下实现复杂度感知的自适应步长生成。在ImageNet基准测试中，GRN在图像重构（0.56 rFID）和类别条件图像生成（1.81 gFID）任务上创下新纪录。我们还将GRN扩展至更具挑战性的文本到图像与文本到视频生成任务，在同等规模下展现出卓越性能。我们开源所有模型与代码，以促进GRN的进一步研究。