Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics

About

Deep learning has emerged as a promising paradigm for spatio-temporal modeling of fluid dynamics. However, existing approaches often suffer from limited generalization to unseen flow conditions and typically require retraining when applied to new scenarios. In this paper, we present LLM4Fluid, a spatio-temporal prediction framework that leverages Large Language Models (LLMs) as generalizable neural solvers for fluid dynamics. The framework first compresses high-dimensional flow fields into a compact latent space via reduced-order modeling enhanced with a physics-informed disentanglement mechanism, effectively mitigating spatial feature entanglement while preserving essential flow structures. A pretrained LLM then serves as a temporal processor, autoregressively predicting the dynamics of physical sequences with time series prompts. To bridge the modality gap between prompts and physical sequences, which can otherwise degrade prediction accuracy, we propose a dedicated modality alignment strategy that resolves representational mismatch and stabilizes long-term prediction. Extensive experiments across diverse flow scenarios demonstrate that LLM4Fluid functions as a robust and generalizable neural solver without retraining, achieving state-of-the-art accuracy while exhibiting powerful zero-shot and in-context learning capabilities. Code and datasets are publicly available at https://github.com/qisongxiao/LLM4Fluid.

Qisong Xiao, Xinhai Chen, Qinglin Wang, Xiaowei Guo, Binglin Wang, Weifeng Chen, Zhichao Wang, Yunfei Liu, Rui Xia, Hang Zou, Gencheng Liu, Shuai Li, Jie Liu• 2026

Related benchmarks

TaskDatasetResultRank
Fluid Dynamics PredictionLow-Re (test)
MAE0.0185
20
Fluid Dynamics PredictionHigh-Re (test)
MAE0.0514
20
Fluid Dynamics PredictionCavity (test)
MAE0.0058
20
Fluid Dynamics PredictionChannel (test)
MAE0.0264
20
Fluid Dynamics PredictionDam (test)
MAE0.0137
20
Fluid Dynamics PredictionHigh-Re Zero-shot from Low-Re
MAE0.0523
9
Fluid Dynamics PredictionCavity Zero-shot from High-Re
MAE0.0079
9
Fluid Dynamics PredictionChannel Zero-shot from Cavity
MAE0.0423
9
Fluid Dynamics PredictionDam Zero-shot from Channel
MAE0.0256
9
Fluid Dynamics PredictionLow-Re Zero-shot from Dam
MAE0.023
9
Showing 10 of 10 rows

Other info

Follow for update