reference-guided

ReGeN is a reference-guided generative pipeline for multivariate time series data that decomposes observed sequences into periodic backbone, stochastic residuals, and cross-variable dependencies to synthesize controllable synthetic data. It demonstrates that generated data can substitute for real data in forecasting tasks, outperforming prior synthetic data generators.

Introduces Reference-Guided Flow Matching, a method that uses a reference distribution to guide the flow matching process, improving sample quality and generation efficiency.

This paper introduces a method for controllable generation in flow matching by adjusting the conditional endpoint mean using a reference set, offering both training-free and semi-parametric guidance for style and content control.

AutoFigure-Edit generates editable scientific illustrations from text descriptions and reference images, enabling flexible style adaptation and efficient refinement.