Hawk：利用空间上下文实现更快的自回归文本到图像生成
Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
AI总结：
针对自回归图像生成模型推理慢、推测解码在图像领域应用受限的问题，提出利用图像空间结构引导推测解码的Hawk方法，在保保真度和多样性的同时实现1.71倍加速。
摘要：
自回归（AR）图像生成模型能够生成高保真图像，但由于其固有的逐token序列解码过程，推理速度通常较慢。推测解码采用轻量级草稿模型来近似更大规模AR模型的输出，已在不损失质量的前提下加速文本生成方面展现出潜力，但其在图像生成领域的应用仍远未得到充分探索。相关挑战源于采样空间显著更大，这加剧了草稿模型与目标模型输出对齐的难度，再加上对图像固有的二维空间结构利用不足，限制了对局部依赖关系的建模。为克服这些挑战，我们提出Hawk——一种利用图像空间结构引导推测模型做出更准确高效预测的新方法。在多个文本到图像基准上的实验结果表明，该方法相比标准AR模型实现了1.71倍的加速，同时保留了图像保真度和多样性。
英文摘要：
Autoregressive (AR) image generation models are capable of producing high-fidelity images but often suffer from slow inference due to their inherently sequential, token-by-token decoding process. Speculative decoding, which employs a lightweight draft model to approximate the output of a larger AR model, has shown promise in accelerating text generation without compromising quality. However, its application to image generation remains largely underexplored. The challenges stem from a significantly larger sampling space, which complicates the alignment between the draft and target model outputs, coupled with the inadequate use of the two-dimensional spatial structure inherent in images, thereby limiting the modeling of local dependencies. To overcome these challenges, we introduce Hawk, a new approach that harnesses the spatial structure of images to guide the speculative model toward more accurate and efficient predictions. Experimental results on multiple text-to-image benchmarks demonstrate a 1.71x speedup over standard AR models, while preserving both image fidelity and diversity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
