xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding

AI 中文解读

xPress这项研究给AI加速生成装上了“因果修正器”。过去的高速草稿生成像全班同学同时各写一个字，虽然每个字单独看都不错，但连起来常常逻辑不通，导致整段被AI否决重来。xPress的巧妙在于，它不改变“一次生成整段草稿”的高效模式，而是用一个轻量级修正器把这些词一次性整理通顺，让前后逻辑连贯起来。实测在Qwen3-8B模型上，数学、代码、聊天等七项任务的平均接受长度提升了约30%，最快提升56%；整体解码速度平均提高1.3倍，最高可达1.7倍。对我们普通用户来说，这意味着以后用AI聊天、让它写代码或解数学题时，等待时间会明显缩短，回答质量也更稳定，不再出现“答得快但前后矛盾”的情况。尤其对于需要多步推理的复杂问题，这项技术能让AI在追求速度的同时不丢掉逻辑，让大模型服务真正变得又准又稳。

Block-diffusion drafters like dFlash generate an entire block of draft tokens in a single forward pass, drastically reducing the overhead of multiple-token drafting in speculative decoding. The crucial final step of the single-pass discrete denoising process involves using the logit distribution at each position to sample conditionally independent tokens. The resulting draft is thus a set of per-position marginals, rather than a joint distribution: no draft token is guaranteed to depend on its predecessors. Such independently sampled marginals tend to produce sequences with tokens that are individually likely, but jointly improbable under the target model's distribution, which verifies each token conditionally. This can cause early rejection and limits acceptance length. To address this, we propose xPress as a means to restore the missing causality in diffusion drafters. xPress is a lightweight causal refiner that reconciles the whole diffusion block at once through parallel refinement, restoring and propagating causal dependencies across the draft without a token-by-token loop. On Qwen3-8B, across seven math, code, and chat benchmarks, xPress raises acceptance length by about 30% on average (up to +56%) and its end-to-end decoding throughput by about 1.3 on average (up to 1.7) compared to the original dFlash diffusion drafter.