FastHybrid：利用前瞻与引导解码加速混合自回归图像生成
FastHybrid: Accelerating Hybrid Autoregressive Image Generation with Lookahead and Guided Decoding
把混合自回归生成中的扩散解码头拆成「语义预测」与「细节精修」两条并行分支，并用引导扩散采样压缩去噪步数，为视觉生成中扩散解码器的推理加速提供了可直接复用的解码调度思路。
原文依据 we propose the Lookahead Decoding Strategy, which integrates the strengths of autoregressive and diffusion models by separating the process into two complementary branches
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自回归模型在自然语言处理中取得了显著成功，但将其应用于图像生成仍面临重大挑战。在基于VQ的解码器用于自回归图像生成时，生成的图像通常能保留语义信息，却难以处理细粒度细节。近期的混合自回归图像生成方法通过将扩散模型作为解码器头集成进来以解决这些问题，从而实现更高保真度的生成。然而，基于扩散的去噪过程在推理阶段引入了显著的计算开销。为加速混合自回归图像生成，我们提出了前瞻解码策略，该策略将过程分离为语义预测与细节精修两条互补分支，从而融合自回归模型与扩散模型的优势。自回归分支捕捉高层语义结构，同时对并行分支做出的粗略预测进行精修。此外，我们引入了引导扩散采样来引导扩散去噪轨迹，显著减少了去噪步数。大量实验表明，我们的方法为加速混合自回归图像生成模型提供了一种有效方案。
英文原文摘要 1269 字符
Autoregressive (AR) models have achieved remarkable success in natural language processing, yet their application to image generation faces significant challenges. When implementing VQ-based decoders for autoregressive image generation, the generated images typically preserve semantic information but struggle with fine-grained details. Recent hybrid AR image generation approaches address these issues by integrating diffusion models as decoder heads, enabling more high-fidelity generation. However, the diffusion-based denoising process introduces significant computational overhead during inference.To accelerate hybrid AR image generation, we propose the Lookahead Decoding Strategy, which integrates the strengths of autoregressive and diffusion models by separating the process into two complementary branches: semantic prediction and detail refinement. The autoregressive branch captures high-level semantic structures while refining coarse predictions made by the parallel. Furthermore, we introduce Guided Diffusion Sampling to steer the diffusion denoising trajectory, significantly reducing the number of denoising steps. Extensive experiments demonstrate that our approach provides an effective solution for accelerating hybrid AR image generation models.