将高效生成与多步优化结合，实现灵活的质量-效率调节。
Drift Flow Matching
- 用流匹配思想统一漂移模型与迭代生成
- 支持一步生成，也可通过多步提升质量
- 适合需要可调生成效率的场景
迭代生成模型如流匹配和扩散模型表现出显著的测试时扩展能力，即增加推理计算可提升生成质量。相比之下，漂移模型虽具高效的一步生成能力，但其直接生成范式限制了这种灵活性。本文提出漂移流匹配（Drift Flow Matching, DFM），将漂移生成建模与基于流的迭代生成相连接。DFM在保持直接传输映射高效性的同时，允许在需要时通过多步推理逐步优化生成结果。该框架弥合了一步漂移模型与多步流匹配方法之间的差距，提供一种可按需调整采样计算量的新生成范式。跨多种任务与数据集的大量实验验证了该框架的有效性与通用性。
原文摘要 · Abstract (English)
Iterative generative models such as Flow Matching and Diffusion models have demonstrated strong test-time scaling behavior, where additional inference computation can improve generation quality. In contrast, Drift Models offer efficient one-step generation, but their direct generation paradigm limits such flexibility. In this work, we propose Drift Flow Matching (DFM), a framework that connects drifting generative modeling with flow-based iterative generation. DFM preserves the efficiency of direct transport maps while enabling generation to be refined through multiple inference steps when desired. This bridges the gap between one-step Drift Models and multi-step Flow Matching methods, and provides a novel generative paradigm that can adapt sampling computation to different quality--efficiency requirements. Extensive experiments across different tasks and datasets demonstrate the effectiveness and generality of the proposed framework.
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。