Shandian Zhe

Associate Professor@, University of Utah·美国·OpenReview

研究方向

Bayesian methods · tensor/matrix factorization · Probabilsitic machine learning · Computational physics · deep learning/neural networks · Diffusion Modeling · AI for Science · Operator learning/neural operators · physics informed machine learning · Scientific Machine learning · Surrogate models · emulation

Shandian Zhe

Deep Gaussian Processes for Functional Maps

SIFBench: An Extensive Benchmark for 3D Fatigue Analysis

Diffusion-Based Symbolic Regression

Multi-Operator Few-Shot Learning for Generalization Across PDE Families

Graph-Based Operator Learning from Limited Data on Irregular Domains

Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization

Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation

Toward Efficient Kernel-Based Solvers for Nonlinear PDEs

Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients

HyResPINNs: Adaptive Hybrid Residual Networks for Learning Optimal Combinations of Neural and RBF Components for Physics-Informed Modeling

Kernel Neural Operators (KNOs) for Scalable, Memory-efficient, Geometrically-flexible Operator Learning

ElastoGen: 4D Generaetive Elastodynamics

Pseudo Physics-Informed Neural Operators

Toward Efficient Kernel-Based Solvers for Nonlinear PDEs

Efficient Fatigue Modeling: Applying Operator Networks for Stress Intensity Factor Prediction and Analysis