让流模型学会可解释的潜在结构，同时保持生成质量。
Structured Coupling for Flow Matching
- 引入结构化潜在变量与外部噪声，联合学习先验与连续传输路径。
- 在无需模拟的情况下实现高质量生成，且潜空间支持聚类与解耦。
- 适合需要可解释表示的生成建模任务，如无监督表征学习。
标准流匹配方法虽具备良好扩展性，但通常依赖非结构化先验分布，限制了对可解释潜在结构的学习能力。潜变量模型虽能捕捉结构，却常牺牲生成质量。本文提出结构耦合流匹配（SCFM），通过引入结构化潜在变量和外生噪声，将流匹配与结构化潜变量学习相结合。该框架共享一个时变识别网络，同时完成潜变量模型的变分推断与中间时刻流速估计。所得到的模型既具有结构感知能力，又保持无条件生成特性，且无需仿真即可采样。实验表明，SCFM在聚类、解耦和下游任务中有效实现无监督潜变量学习，同时在样本质量上与标准流匹配相当，证明了在不牺牲生成保真度的前提下学习有意义结构的可行性。
原文摘要 · Abstract (English)
Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but often sacrifice generative quality. We bridge this gap by proposing Structured Coupling for Flow Matching (SCFM), a cooperative framework that augments flow matching with structured latent representation learning. By introducing structured latent variables and exogenous noise into the source, SCFM jointly learns a structured prior (via latent variable modeling) and a continuous transport map (via flow matching). It uses a shared time-dependent recognition network for both latent variable model variational inference and intermediate-time flow velocity estimation. This yields a structurally informed yet unconditional, simulation-free flow model, where the latent variable model can also assist flow sampling. Empirically, SCFM facilitates unsupervised latent representation learning for clustering, disentanglement and downstream tasks, while remaining competitive with flow matching in sample quality, showing that meaningful structure can be learned without sacrificing generative fidelity.
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。