LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914291083378688 |
|---|---|
| author | Xiao, Qisong Chen, Xinhai Wang, Qinglin Guo, Xiaowei Wang, Binglin Chen, Weifeng Wang, Zhichao Liu, Yunfei Xia, Rui Zou, Hang Liu, Gencheng Li, Shuai Liu, Jie |
| author_facet | Xiao, Qisong Chen, Xinhai Wang, Qinglin Guo, Xiaowei Wang, Binglin Chen, Weifeng Wang, Zhichao Liu, Yunfei Xia, Rui Zou, Hang Liu, Gencheng Li, Shuai Liu, Jie |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21681 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics Xiao, Qisong Chen, Xinhai Wang, Qinglin Guo, Xiaowei Wang, Binglin Chen, Weifeng Wang, Zhichao Liu, Yunfei Xia, Rui Zou, Hang Liu, Gencheng Li, Shuai Liu, Jie Machine Learning Fluid Dynamics 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. |
| title | LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics |
| topic | Machine Learning Fluid Dynamics |
| url | https://arxiv.org/abs/2601.21681 |