SJD-PAC通过主动预 drafting 和自适应延续，让文本生成图像更快更准。
SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
- 主动预 drafting 提升复杂区域的生成接受率
- 自适应延续机制避免重复采样，平均每步接受长度提升3.8倍
- 适合追求高速生成且不牺牲图像质量的研究者
推测性雅可比解码（SJD）提供了一种无需草稿模型的加速自回归文生图方法。然而，视觉生成的高熵特性导致在复杂区域中草稿词元接受率低，成为性能瓶颈。为此，我们提出 SJD-PAC 框架：首先采用主动预起草策略，提升这些高熵区域的局部接受率；其次引入自适应延续机制，在首次拒绝后持续验证序列，无需完全重采样。两者协同工作，显著提升每步平均接受长度，加快推理速度，同时严格保持目标分布。在标准文生图基准测试中，SJD-PAC 实现了 3.8 倍的速度提升，且图像质量无损。代码已开源：https://github.com/KangJialiang/SJD-PAC。
原文摘要 · Abstract (English)
Speculative Jacobi Decoding (SJD) offers a draft-model-free approach to accelerate autoregressive text-to-image synthesis. However, the high-entropy nature of visual generation yields low draft-token acceptance rates in complex regions, creating a bottleneck that severely limits overall throughput. To overcome this, we introduce SJD-PAC, an enhanced SJD framework. First, SJD-PAC employs a proactive drafting strategy to improve local acceptance rates in these challenging high-entropy regions. Second, we introduce an adaptive continuation mechanism that sustains sequence validation after an initial rejection, bypassing the need for full resampling. Working in tandem, these optimizations significantly increase the average acceptance length per step, boosting inference speed while strictly preserving the target distribution. Experiments on standard text-to-image benchmarks demonstrate that SJD-PAC achieves a $3.8\times$ speedup with lossless image quality. Code is available at https://github.com/KangJialiang/SJD-PAC.
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。