SJD-VP：带有验证预测的推测雅可比解码
SJD-VP: Speculative Jacobi Decoding with Verification Prediction for Autoregressive Image Generation
AI总结：
本文提出SJD-VP，通过利用token概率变化指导采样，提升验证通过率，加速自回归生成并提高图像质量。
摘要：
Speculative Jacobi Decoding (SJD) 已经成为加速自回归图像生成的有前途的方法。尽管其潜力巨大，现有的SJD方法常常因token选择模糊导致推测token的接受率低。最近的工作主要从放松的token验证视角来缓解这一问题，但未能充分利用解码的迭代动态。在本文中，我们进行了深入分析并提出一个新观察：概率增加的token更可能匹配验证接受且正确的token。基于此，我们提出了一个新的Speculative Jacobi Decoding with Verification Prediction (SJD-VP)。关键思想是利用迭代中token概率的变化来指导采样，倾向于概率增加的token。这有效预测了哪些token可能通过后续验证，从而提升接受率。特别是，我们的SJD-VP是即插即用的，可以无缝集成到现有的SJD方法中。在标准基准上的广泛实验表明，我们的SJD-VP方法在加速自回归解码的同时，提高了图像生成的质量。
英文摘要：
Speculative Jacobi Decoding (SJD) has emerged as a promising method for accelerating autoregressive image generation. Despite its potential, existing SJD approaches often suffer from the low acceptance rate issue of speculative tokens due to token selection ambiguity. Recent works attempt to mitigate this issue primarily from the relaxed token verification perspective but fail to fully exploit the iterative dynamics of decoding. In this paper, we conduct an in-depth analysis and make a novel observation that tokens whose probabilities increase are more likely to match the verification-accepted and correct token. Based on this, we propose a novel Speculative Jacobi Decoding with Verification Prediction (SJD-VP). The key idea is to leverage the change in token probabilities across iterations to guide sampling, favoring tokens whose probabilities increase. This effectively predicts which tokens are likely to pass subsequent verification, boosting the acceptance rate. In particular, our SJD-VP is plug-and-play and can be seamlessly integrated into existing SJD methods. Extensive experiments on standard benchmarks demonstrate that our SJD-VP method consistently accelerates autoregressive decoding while improving image generation quality.
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。
