PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation 事件

PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation arXiv:2605.28867v1 Announce Type: cross Abstract: Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient alternative to diffusion models, but practical implementations typically rely on a single finite-capacity global vector-field estimator. In s