让语言模型单步生成全文，突破传统生成速度瓶颈。
Discrete Flow Maps
- 用离散流映射压缩生成路径，实现单次前向传播完成文本生成。
- 在概率单纯形几何下训练，比现有方法提升生成质量与速度。
- 适合追求高效文本生成的开发者与研究者使用。
自回归语言模型的序列生成机制天然限制了生成速度。尽管连续流模型可实现并行生成，但传统方法需昂贵的迭代积分。流映射通过将生成轨迹压缩为单步映射，理论上可在一次前向传播中从噪声生成完整文本序列。然而，标准方法依赖欧氏回归损失，对离散数据的几何结构不兼容。本文提出离散流映射（Discrete Flow Maps），在概率单纯形几何框架下重构训练机制，使训练动态与语言的离散特性一致。实验证明，该方法在离散流建模任务上超越此前最优结果。
原文摘要 · Abstract (English)
The sequential nature of autoregressive next-token prediction imposes a fundamental speed limit on large language models. While continuous flow models offer a path to parallel generation, they traditionally demand expensive iterative integration. Flow Maps bypass this bottleneck by compressing generative trajectories into single-step mappings, theoretically enabling the generation of full text sequences from noise in a single forward pass. However, standard formulations rely on Euclidean regression losses that are geometrically ill-suited for discrete data. In this work, we resolve this conflict with Discrete Flow Maps, a framework that reconciles trajectory compression with the geometry of the probability simplex. We recast standard flow map training for the discrete domain, aligning the training dynamics with the discrete nature of language. Empirically, this strict geometric alignment allows our method to surpass previous state-of-the-art results in discrete flow modeling.
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。