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

TL;DR

LLM4Fluid introduces a novel framework that uses large language models combined with reduced-order modeling to accurately predict fluid dynamics across various scenarios without retraining, demonstrating strong generalization and zero-shot capabilities.

Contribution

The paper presents a new approach integrating LLMs with physics-informed reduced-order modeling for generalizable fluid dynamics prediction without retraining.

Findings

Achieves state-of-the-art accuracy in fluid prediction tasks.

Demonstrates robust zero-shot and in-context learning capabilities.

Provides a modality alignment strategy to improve long-term prediction stability.

Abstract

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.