Recursive Flow Matching
- Published
- Source
- arXiv
- Paper number
- 256
- Field
- Machine Learning
- arXiv ID
- 2605.26535
Key points
- Tradeoff removal: while most models force a choice between speed and accuracy, RecFM uses recursive training to improve both at once.
- Explicit scale alignment: unlike consistency models that distill a student from a teacher, RecFM uses a single network and enforces multi-scale alignment internally, which provides a more robust gradient signal during training.
- Physical fidelity: by straightening trajectories, RecFM preserves high-frequency details, such as waves and vortices, that are usually lost when generative models are accelerated.
Paper links
External research summaries. These are not HDATF publications or measured product results.