提出一种渐进式推测解码方法，提升自回归图像生成速度与质量。
Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
- 基于变分距离优化与扰动分析，设计渐进松弛策略
- 在相同延迟下生成质量更高，或同质量下速度更快
- 适合追求高效高质量图像生成的开发者与研究者
尽管自回归图像生成已取得显著进展，但推理速度仍受限于模型的顺序性与图像标记的模糊性，即使采用推测解码亦然。现有方法虽尝试通过松弛推测解码缓解此问题，但缺乏理论基础。本文建立了松弛推测解码的理论框架，提出COOL-SD——一种基于两个核心洞察的渐进松弛方案。第一，分析目标模型与松弛推测解码间的总变差（TV）距离，推导出最小化上界距离的最优重采样分布；第二，通过扰动分析揭示松弛推测解码中的渐进行为，从而指导设计。二者结合使COOL-SD在保持相近生成质量的同时加速推理，或在相似延迟下实现更优质量。实验验证其在速度-质量权衡上持续优于现有方法。
原文摘要 · Abstract (English)
Despite significant progress in autoregressive image generation, inference remains slow due to the sequential nature of AR models and the ambiguity of image tokens, even when using speculative decoding. Recent works attempt to address this with relaxed speculative decoding but lack theoretical grounding. In this paper, we establish the theoretical basis of relaxed SD and propose COOL-SD, an annealed relaxation of speculative decoding built on two key insights. The first analyzes the total variation (TV) distance between the target model and relaxed speculative decoding and yields an optimal resampling distribution that minimizes an upper bound of the distance. The second uses perturbation analysis to reveal an annealing behaviour in relaxed speculative decoding, motivating our annealed design. Together, these insights enable COOL-SD to generate images faster with comparable quality, or achieve better quality at similar latency. Experiments validate the effectiveness of COOL-SD, showing consistent improvements over prior methods in speed-quality trade-offs.
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。