AI 中文总结
研究提出源提升流匹配（SL - FM）解决多模态模仿学习中流匹配策略随机性被动问题，核心机制为正交源提升，实验表明其能将被动源随机性转化为可操作变量，提升多模态控制性能。
AI 中文摘要
流匹配策略在模仿学习中很有前景，因其能对复杂多模态动作分布建模。但它们的随机性很大程度上是被动的，用户无法直接在同一状态的有效延续中选择。我们提出源提升流匹配（SL - FM），这是一种源可干预的流匹配策略，在保持速度场共享且无潜在因素的同时提供了这样一种控制手段。核心机制是正交源提升，以防止路径交叉模糊性。实验表明，SL - FM将被动源随机性转化为可操作的干预变量，去除交叉诱导的复合轨迹，在多数匹配前缀干预中改变未来路线，实现了强大的自由部署性能。总体而言，源几何结构提供了可操作的多模态控制，而无需根据所选模式对速度场进行条件设定。
英文摘要
Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity is largely passive: repeated sampling may yield diverse behaviors, but users cannot directly choose among valid continuations from the same state. We propose Source-Lifted Flow Matching (SL-FM), a source-intervenable flow-matching policy that exposes such a handle while keeping the velocity field shared and latent-free (without a separate discrete-handle input). The handle selects only the source endpoint of the conditional flow, not a mode-specific field, preserving the standard formulation while avoiding decomposition into separate mode-conditioned dynamics. The core mechanism is Orthogonal Source Lifting, designed to prevent path-crossing ambiguity. Instead of partitioning target actions by mode, SL-FM lifts handle-specific sources into auxiliary orthogonal coordinates and keeps targets in the original action subspace. This preserves the demonstrated action distribution while allowing one shared field to carry different branches without merging at crossings. To keep handles usable across states, we learn a state-dependent source mixture end to end and use a responsibility floor, giving each handle weak supervision and mitigating dead modes. Experiments on crossing-flow diagnostics and robot-control benchmarks show that SL-FM converts passive source randomness into an actionable intervention variable. It removes crossing-induced composite trajectories, changes future routes in 91.1% of matched-prefix interventions, and achieves strong free-deployment performance, with improvements in several benchmark settings. Overall, source geometry provides actionable multimodal control without conditioning the velocity field on the selected mode.
Comments16 pages, 7 figures. Updated manuscript and author list
