UniFluids: Unified Neural Operator Learning with Conditional Flow-matching

Read full text Summarise with VIRAT
Authors: Haosen Li, Qi Meng, Jiahao Li, Rui Zhang, Ruihua Song, Liang Ma, Zhi-Ming Ma
Cited by: 0
References: 59

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Partial differential equation (PDE) simulation holds extensive significance in scientific research. Currently, the integration of deep neural networks to learn solution operators of PDEs has introduced great potential. In this paper, we present UniFluids, a conditional flow-matching framework that harnesses the scalability of diffusion Transformer to unify learning of solution operators across diverse PDEs with varying dimensionality and physical variables. Unlike the autoregressive PDE foundation models, UniFluids adopts flow-matching to achieve parallel sequence generation, making it the first such approach for unified operator learning. Specifically, the introduction of a unified four-dimensional spatiotemporal representation for the heterogeneous PDE datasets enables joint training and conditional encoding. Furthermore, we find the effective dimension of the PDE dataset is much lower than its patch dimension. We thus employ $x$-prediction in the flow-matching operator learning, which is verified to significantly improve prediction accuracy. We conduct a large-scale evaluation of UniFluids on several PDE datasets covering spatial dimensions 1D, 2D and 3D. Experimental results show that UniFluids achieves strong prediction accuracy and demonstrates good scalability and cross-scenario generalization capability. The code will be released later.

Fields of Study & Subjects

Model Reduction and Neural Networks Neural Networks and Applications Gaussian Processes and Bayesian Inference

Publication details

Journal / source
arXiv (Cornell University)
Publication date
19 March 2026
Language
EN
Document type
Preprint