Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-block parallel denoising. However, in the few-step regime needed for practical acceleration, standard confidence-thresholded decoding is often brittle: aggressive thresholds hurt quality, while conservative thresholds require unnecessary denoising steps. Existing approaches that address this issue either require additional training or incur extra test-time compute. We present S2D2, a training-free self-speculative decoding framework for block-diffusion language models. Our key observation is that a block-diffusion model becomes autoregressive when the block size is reduced to one, allowing the same pretrained model to act as both drafter and verifier. S2D2 inserts a speculative verification step into standard block-diffusion decoding and uses lightweight routing policies to decide when verification is worth its cost. This yields a hybrid decoding trajectory in which diffusion proposes tokens in parallel, while the autoregressive mode acts as a local sequence-level critic. Across three mainstream block-diffusion families, S2D2 consistently improves the accuracy-speed tradeoff over strong confidence-thresholding baselines. On SDAR, we observe up to $4.7\times$ speedup over autoregressive decoding, and up to $1.57\times$ over a tuned dynamic decoding baseline while improving accuracy by up to $4.5$ points. On LLaDA2.1-Mini, S2D2 remains complementary to built-in self-correction, including a conservative setting where it is $4.4\times$ faster than the static baseline with slightly higher accuracy.

翻译：块扩散语言模型通过结合块级自回归解码与块内并行去噪，为实现超越自回归生成的速度提供了有前景的路径。然而，在实际加速所需的少步骤机制中，标准的置信度阈值解码往往不稳定：激进的阈值会损害生成质量，而保守的阈值则导致不必要的去噪步骤。现有解决该问题的方法要么需要额外训练，要么增加测试阶段的计算开销。我们提出S2D2，一种面向块扩散语言模型的免训练自猜测解码框架。关键发现是：当块大小缩减至1时，块扩散模型退化为自回归模型，这使得同一预训练模型可同时充当草稿模型与验证模型。S2D2在标准块扩散解码中插入推测验证步骤，并通过轻量级路由策略决定何时值得进行验证。这形成了混合解码轨迹：扩散模块并行生词元，而自回归模式充当局部序列级评判器。在三个主流块扩散模型家族中，S2D2始终在精度-速度权衡上优于强置信度阈值基线。在SDAR上，相比自回归解码实现高达4.7倍加速，相比调优的动态解码基线实现1.57倍加速，同时精度提升4.5个百分点。在LLaDA2.1-Mini上，S2D2与内建自校正机制互补，在保守设置下相比静态基线提速4.4倍且精度略有提升。