让扩散模型先规划再去噪，生成更高效。
Think While You Generate: Discrete Diffusion with Planned Denoising
- 分两阶段：先规划哪些位置需去噪，再按序修复
- 在文本和图像生成上均优于传统方法，语言建模困惑度逼近自回归模型
- 适合追求高效生成、关注推理速度的研究者
离散扩散模型已达到顶尖性能，在标准基准上超越或接近自回归模型。本文提出离散扩散规划去噪框架（DDPD），将生成过程拆分为规划器与去噪器两个模块。推理时，规划器通过识别最严重的污染位置（包括初始污染和需进一步优化的位置），决定下一步去噪的位置。这种计划-去噪策略使生成过程更高效，能按最优顺序迭代修复噪声。DDPD在text8、OpenWebText等语言建模任务以及ImageNet $256 \times 256$ 的基于词元的图像生成任务中表现优异，显著缩小了扩散模型与自回归模型在生成困惑度上的差距。代码已公开于 https://github.com/liusulin/DDPD。
原文摘要 · Abstract (English)
Discrete diffusion has achieved state-of-the-art performance, outperforming or approaching autoregressive models on standard benchmarks. In this work, we introduce Discrete Diffusion with Planned Denoising (DDPD), a novel framework that separates the generation process into two models: a planner and a denoiser. At inference time, the planner selects which positions to denoise next by identifying the most corrupted positions in need of denoising, including both initially corrupted and those requiring additional refinement. This plan-and-denoise approach enables more efficient reconstruction during generation by iteratively identifying and denoising corruptions in the optimal order. DDPD outperforms traditional denoiser-only mask diffusion methods, achieving superior results on language modeling benchmarks such as text8, OpenWebText, and token-based image generation on ImageNet $256 \times 256$. Notably, in language modeling, DDPD significantly reduces the performance gap between diffusion-based and autoregressive methods in terms of generative perplexity. Code is available at https://github.com/liusulin/DDPD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。