NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism
Abstract
Flow-based generative models have shown promise in various machine learning applications, but they often face challenges in handling noise and ensuring robustness in trajectory estimation. In this work, we propose NRFlow, a novel extension to flow-based generative modeling that incorporates second-order dynamics through acceleration fields. We develop a comprehensive theoretical framework to analyze the regularization effects of high-order terms and derive noise robustness guarantees. Our method leverages a two-part loss function to simultaneously train first-order velocity fields and high-order acceleration fields, enhancing both smoothness and stability in learned transport trajectories. These results highlight the potential of high-order flow matching for robust generative modeling in complex and noisy environments.
Cite
Text
Chen et al. "NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism." Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, 2025.Markdown
[Chen et al. "NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism." Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, 2025.](https://mlanthology.org/uai/2025/chen2025uai-nrflow/)BibTeX
@inproceedings{chen2025uai-nrflow,
title = {{NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism}},
author = {Chen, Bo and Gong, Chengyue and Li, Xiaoyu and Liang, Yingyu and Sha, Zhizhou and Shi, Zhenmei and Song, Zhao and Wan, Mingda and Ye, Xugang},
booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence},
year = {2025},
pages = {673-704},
volume = {286},
url = {https://mlanthology.org/uai/2025/chen2025uai-nrflow/}
}