arXiv cs.AI· Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim, Mudhakar Srivatsa, Raghu K. Ganti, Minjia Zhang, Naigang Wang·· 4 小时前AI 评分37
XPress：为推测解码中的扩散草稿模型实现并行修正
XPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding
AI 导读
arXiv 论文提出 xPress，一种轻量级因果修正器，通过并行修正恢复 dFlash 等块扩散草稿模型缺失的因果依赖，无需逐 token 循环。在 Qwen3-8B 上的七个数学、代码和聊天基准测试中，相比原 dFlash，xPress 平均将接受长度提升约 30%（最高 +56%），端到端解码吞吐平均提升约 1.3 倍（最高 1.7 倍）。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.02438 [cs.AI] |
| (or arXiv:2608.02438v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.02438 arXiv-issued DOI via DataCite |
Submission history
From: Zheng Wang [view email]
[v1]
Mon, 3 Aug 2026 16:18:22 UTC (103 KB)
[v2]
Mon, 26 Oct 2026 00:18:30 UTC (161 KB)
来源：arXiv cs.AI · arxiv.org