English(EN) DUET: Dual-Sparse Inference for Block Diffusion Language Models

Duet框架加速扩散语言模型推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-09 05:00

研究人员推出Duet，一个新颖的无需训练的框架，旨在加速块扩散语言模型的推理。这种双稀疏推理方法解决了历史前缀注意力和当前生成块处理相关的计算成本。Duet通过对历史上下文采用前缀键值稀疏性以及早期查询稀疏性来减少深层计算中不太可能更新的位置，从而实现显著的加速。 AI

影响该框架可能导致在各种应用中更快、更有效地部署扩散语言模型。

排序理由这是一篇详细介绍语言模型新技术框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍语言模型新技术框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Siyuan Yan, Shen Gu, Xiaoxing Ma, Chun Cao, Jingwei Xu · 2026-11-09 05:00

DUET：块扩散语言模型的双稀疏推理

arXiv:2611.09239v1 Announce Type: new Abstract: Diffusion language models (DLMs) enable parallel token generation through iterative denoising, yet their inference remains costly due to repeated attention over a growing historical prefix and repeated processing of the entire curre…