通过熵调控提升图像生成质量与速度，无需额外计算开销。
Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
- 基于空间熵动态调节温度，平衡内容多样性与结构一致性。
- 熵感知的推测解码规则实现近无损生成，推理成本降至常规方法的85%。
- 适用于多种自回归图像生成模型，通用性强且加速明显。
本文重新审视当前自回归图像生成模型的采样问题，发现图像标记的信息密度较低且空间分布不均，不同于文本标记。为此，提出一种基于熵的解码策略，显著提升生成质量并加快合成速度。核心创新包括：1）基于标记分布空间熵的动态温度控制，在掩码和尺度级模型中平衡内容多样性、对齐准确性和结构连贯性，且无额外计算开销；2）在推测解码中引入熵感知接受规则，实现近无损生成，推理成本仅为传统加速方法的约85%。在多个基准测试和多种自回归图像生成模型上进行的大量实验表明，该方法在提升生成质量与采样速度方面具有显著效果和强泛化能力。
原文摘要 · Abstract (English)
In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution. Accordingly, we present an entropy-informed decoding strategy that facilitates higher autoregressive generation quality with faster synthesis speed. Specifically, the proposed method introduces two main innovations: 1) dynamic temperature control guided by spatial entropy of token distributions, enhancing the balance between content diversity, alignment accuracy, and structural coherence in both mask-based and scale-wise models, without extra computational overhead, and 2) entropy-aware acceptance rules in speculative decoding, achieving near-lossless generation at about 85\% of the inference cost of conventional acceleration methods. Extensive experiments across multiple benchmarks using diverse AR image generation models demonstrate the effectiveness and generalizability of our approach in enhancing both generation quality and sampling speed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。