离散扩散模型让大模型生成更快更可控，速度提升10倍。
Discrete Diffusion in Large Language and Multimodal Models: A Survey
- 用去噪机制并行生成多标记，突破传统自回归限制。
- 推理速度最高提升10倍，性能媲美自回归模型。
- 适合需要快速生成和精细控制的场景，如工业应用。
本文系统综述了离散扩散语言模型（dLLMs）与离散扩散多模态语言模型（dMLLMs）。与自回归（AR）模型不同，dLLMs和dMLLMs采用全注意力机制的多标记并行解码策略，基于去噪生成，天然支持并行生成、细粒度输出控制和动态感知，这些能力在传统AR模型中难以实现。越来越多的工业级私有及开源d(M)LLM已证明其性能可媲美自回归模型，同时推理速度最高可达10倍加速。本工作全面梳理了dLLM与dMLLM的研究进展，追溯发展历程，形式化数学框架，列举常用建模方法，分类代表性模型；深入分析训练、推理与量化关键技术；探讨可信性问题，并总结语言、视觉-语言及生物等领域的新兴应用。最后展望未来研究与部署方向。相关论文汇总见 https://github.com/LiQiiiii/Awesome-Discrete-Diffusion-LLM_MLLM。
原文摘要 · Abstract (English)
In this work, we provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs). Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-token, parallel decoding paradigm using full attention and a denoising-based generation strategy. This paradigm naturally enables parallel generation, fine-grained output control, and dynamic perception. These capabilities are previously difficult to achieve with AR models. A growing number of industrial-scale proprietary d(M)LLMs, as well as a large number of open-source academic d(M)LLMs, have demonstrated performance comparable to their autoregressive counterparts, while achieving up to 10$\times$ acceleration in inference speed. These developments position discrete diffusion models as a promising alternative to intelligence based on the traditional autoregressive approach. In this work, we present a comprehensive overview of the research in the dLLM and dMLLM domains. We trace the historical development of dLLMs and dMLLMs, formalize the underlying mathematical frameworks, list commonly-used modeling methods, and categorize representative models. We further analyze key techniques for training, inference, quantization. We also discuss the trustworthy issues and summarize emerging applications across language, vision-language, and biological domains and etc.. We conclude by discussing future directions for research and deployment. Relative papers are collected in https://github.com/LiQiiiii/Awesome-Discrete-Diffusion-LLM_MLLM
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。