Zhitong Xu

I'm a third year PhD student at University of Utah, advised by Prof. Shandian Zhe. My research is on Gaussian processes and kernel methods, with a focus on structure-exploiting scalable inference, Bayesian optimization and sequential decision making under uncertainty, and uncertainty quantification.

Google Scholar GitHub
Education
  • University of Utah
    University of Utah
    Kahlert School of Computing
    Ph.D. Student
    Aug. 2024 - present
  • New York University
    New York University
    M.S. in Computer Science
    Aug. 2021 - May. 2023
  • Rensselaer Polytechnic Institute
    Rensselaer Polytechnic Institute
    B.S. in Computer Science dual Mathematics
    Aug. 2016 - May. 2020
Experience
  • Origami Robotics
    San Francisco, CA
    Research Scientist, Robotics
    June. 2026 - Aug. 2026
  • Microsoft (STCA)
    Microsoft (STCA)
    SE Intern
    June. 2023 - Aug. 2023
Selected Publications (view all )
Kronecker-Structured Nonparametric Spatiotemporal Point Processes

Zhitong Xu, Qiwei Yuan, Yinghao Chen, Sun Yan, Bin Shen, Shandian Zhe

The 42nd Conference on Uncertainty in Artificial Intelligence (UAI) 2026

[Code] [Paper]

Kronecker-Structured Nonparametric Spatiotemporal Point Processes

Zhitong Xu, Qiwei Yuan, Yinghao Chen, Sun Yan, Bin Shen, Shandian Zhe

The 42nd Conference on Uncertainty in Artificial Intelligence (UAI) 2026

[Code] [Paper]

Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs

Qiwei Yuan, Zhitong Xu, Yinghao Chen, Yiming Xu, Houman Owhadi, Shandian Zhe

The 29th International Conference on Artificial Intelligence and Statistics (AISTATS) 2026

[Code] [Paper]

Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs

Qiwei Yuan, Zhitong Xu, Yinghao Chen, Yiming Xu, Houman Owhadi, Shandian Zhe

The 29th International Conference on Artificial Intelligence and Statistics (AISTATS) 2026

[Code] [Paper]

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

Long Da, Zhitong Xu, Guang Yang, Akil Narayan, Shandian Zhe

Forty-second International Conference on Machine Learning (ICML) 2025

[Paper]

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

Long Da, Zhitong Xu, Guang Yang, Akil Narayan, Shandian Zhe

Forty-second International Conference on Machine Learning (ICML) 2025

[Paper]

Toward Efficient Kernel-Based Solvers for Nonlinear PDEs
Toward Efficient Kernel-Based Solvers for Nonlinear PDEs

Zhitong Xu*, Da Long*, Yiming Xu, Guang Yang, Shandian Zhe, Houman Owhadi (* equal contribution)

Forty-second International Conference on Machine Learning (ICML) 2025

[Paper]

Toward Efficient Kernel-Based Solvers for Nonlinear PDEs

Zhitong Xu*, Da Long*, Yiming Xu, Guang Yang, Shandian Zhe, Houman Owhadi (* equal contribution)

Forty-second International Conference on Machine Learning (ICML) 2025

[Paper]

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

Zhitong Xu, Haitao Wang, Jeff M. Phillips, Shandian Zhe

The Thirteenth International Conference on Learning Representations (ICLR) 2025 Oral

[Code] [Paper]

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

Zhitong Xu, Haitao Wang, Jeff M. Phillips, Shandian Zhe

The Thirteenth International Conference on Learning Representations (ICLR) 2025 Oral

[Code] [Paper]

Invertible Fourier Neural Operators for Tackling Both Forward and Inverse Problems

Long Da, Zhitong Xu, Qiwei Yuan, Yin Yang, Shandian Zhe

The 28th International Conference on Artificial Intelligence and Statistics (AISTATS) 2025

[Code] [Paper]

Invertible Fourier Neural Operators for Tackling Both Forward and Inverse Problems

Long Da, Zhitong Xu, Qiwei Yuan, Yin Yang, Shandian Zhe

The 28th International Conference on Artificial Intelligence and Statistics (AISTATS) 2025

[Code] [Paper]

All publications