papers

Publications (12)

physics.comp-ph2025

Stable spectral neural operator for learning stiff PDE systems from limited data

Rui Zhang, Han Wan, Yang Liu +1

Accurate modeling of spatiotemporal dynamics is crucial to understanding complex phenomena across science and engineering. However, this task faces a fundamental challenge when the…

cs.LG2025

PeSANet: Physics-encoded Spectral Attention Network for Simulating PDE-Governed Complex Systems

Han Wan, Rui Zhang, Qi Wang +2

Accurately modeling and forecasting complex systems governed by partial differential equations (PDEs) is crucial in various scientific and engineering domains. However, traditional…

physics.flu-dyn2025

OmniFluids: Physics Pre-trained Modeling of Fluid Dynamics

Rui Zhang, Qi Meng, Han Wan +3

Computational fluid dynamics (CFD) drives progress in numerous scientific and engineering fields, yet high-fidelity simulations remain computationally prohibitive. While machine le…

cs.LG2026

Spectral-inspired Operator Learning with Limited Data and Unknown Physics

Han Wan, Rui Zhang, Hao Sun

Learning PDE dynamics from limited data with unknown physics is challenging. Existing neural PDE solvers either require large datasets or rely on known physics (e.g., PDE residuals…

cs.LG2026

PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics

Hao Zhou, Rui Zhang, Han Wan +1

Reconstructing PDE-governed fields from sparse and irregular measurements is challenging due to their ill-posed nature. Deterministic surrogates are trained on dense fields that st…

cs.LG2026

Geometry-Aware Neural Optimizer for Shape Optimization and Inversion

Guoze Sun, Tianya Miao, Haoyang Huang +4

Geometry is central to PDE-governed systems, motivating shape optimization and inversion. Classical pipelines conduct costly forward simulation with geometry processing, requiring…

cs.LG2025

TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices

Jianlei Yang, Jiacheng Liao, Fanding Lei +6

Developing deep learning models on tiny devices (e.g. Microcontroller units, MCUs) has attracted much attention in various embedded IoT applications. However, it is challenging to…

cs.CL2026

L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention

Yuliang Zhan, Xinyu Tang, Han Wan +3

Recently, Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs), but Vision-Language Models (VLMs) still struggle with multi-…

cs.LG2025

PIMRL: Physics-Informed Multi-Scale Recurrent Learning for Burst-Sampled Spatiotemporal Dynamics

Han Wan, Qi Wang, Yuan Mi +2

Deep learning has shown strong potential in modeling complex spatiotemporal dynamics. However, most existing methods depend on densely and uniformly sampled data, which is often un…

cs.DC2025

Towards Affordable, Adaptive and Automatic GNN Training on CPU-GPU Heterogeneous Platforms

Tong Qiao, Ao Zhou, Yingjie Qi +4

Graph Neural Networks (GNNs) have been widely adopted due to their strong performance. However, GNN training often relies on expensive, high-performance computing platforms, limiti…

cs.AI2026

Large language models for partial differential equation workflows

Han Wan, Rui Zhang, Hao Sun

Partial differential equations (PDEs) become actionable in science and engineering not as isolated formulae, but as executable workflows that connect modelling assumptions, governi…

math.OC2026

Fast and Effective Computation of Generalized Symmetric Matrix Factorization

Lei Yang, Han Wan, Min Zhang +1

In this paper, we study a nonconvex, nonsmooth, and non-Lipschitz generalized symmetric matrix factorization model that unifies a broad class of matrix factorization formulations a…