arXiv cs.CL· Amir Mann, Jonathan Fhima, Shaked Brody, Or Avitan, Asif Zamir, Shahar Tsiper, Niv Nayman·· 10 小时前AI 评分29
B3：用重叠块去噪模糊块边界，为扩散语言模型提速 11.5-14.5%
Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models
AI 导读
研究者提出 Blurring the Block Boundaries（B3），让两个块在同一次前向传播中并行细化，从而加速自编辑式块扩散语言模型。B3 无需训练、无需调超参数，可即插即用地集成进任意自编辑块扩散模型，并在模型准备好时动态开启下一块。在 10 个覆盖不同任务与难度的数据集上评测，B3 生成质量与基座模型持平，速度提升 11.5-14.5%。
正文 · 原文
Abstract:Diffusion Language Models (DLMs) have emerged as effective alternatives to autoregressive models for latency-critical tasks, enabling faster token generation. Recent advances employ block diffusion with self-editing capabilities, where each block refines tokens iteratively before advancing to the next one. Yet each block is only as fast as its slowest token, and the next block cannot start before it. We suggest Blurring the Block Boundaries (B3), a novel method with which two blocks are refined in parallel within a shared forward pass. B3 calibrates itself on the fly, opening the next block only once the model is ready to start generating it. It is a training-free and hyperparameter-free acceleration method which seamlessly integrates within any self-editing block diffusion model. Evaluated on state-of-the-art DLMs across 10 diverse datasets spanning varied tasks and difficulty levels, B3 results in on par generation quality and 11.5-14.5% speedup compared to the base model, pushing the Pareto frontier for latency-quality trade-offs in DLM inference.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2611.14387 [cs.CL] |
| (or arXiv:2611.14387v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14387 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Niv Nayman [view email]
[v1]
Tue, 10 Nov 2026 17:40:24 UTC (768 KB)
来源：arXiv cs.CL · arxiv.org