Da Long

Da Long

Ph.D. Student in Computer Science

Kahlert School of Computing, the University of Utah

About Me

I am a Ph.D. student in computer science at the Kahlert School of Computing, University of Utah. I earned my Bachelor of Science degree from the University of Arizona in computer science and mathematics.

My PhD research focuses on developing surrogate-based AI models that learn to emulate and reason about complex processes, including both physical systems and human expertise:

  • Surrogates for human experts: I align large language models to act as intelligent surrogates for personalized healthcare coaching and recommendations, using customized techniques such as supervised fine-tuning, reinforcement learning, and chain-of-thought reasoning.
  • Surrogates for physical dynamical systems: I develop probabilistic and generative surrogates for complex physical dynamics such as climate evolution, plasma dynamics, and turbulent fluid flows, to enable efficient simulation, forecasting, and uncertainty quantification.

I am advised by Dr. Shandian Zhe.

My research interest includes: Surrogate Modeling, LLM Alignment, Reinforcement Learning

I am on job market for a full-time role starting in summer/fall 2026. Please feel free to reach out to me if you are hiring.

Publications

(2025). Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation. ICML.

PDF

(2025). Toward Efficient Kernel-Based Solvers for Nonlinear PDEs. ICML.

PDF

(2025). Pseudo-Physics-Informed Neural Operators: Enhancing Operator Learning from Limited Data. TMLR.

PDF

(2025). Invertible Fourier Neural Operators for Tackling Both Forward and Inverse Problems. AISTATS.

PDF

(2024). Equation Discovery with Bayesian Spike-and-Slab Priors and Efficient Kernels. AISTATS.

PDF

(2024). A kernel approach for pde discovery and operator learning. Physica D: Nonlinear Phenomena.

PDF

(2023). Solving High Frequency and Multi-Scale PDEs with Gaussian Processes. ICLR.

PDF

(2022). AutoIP: A united framework to integrate physics into Gaussian processes. ICML.

PDF

Preprint

(2024). Spatio-temporal Fourier Transformer (StFT) for Long-term Dynamics Prediction. Preprint.

PDF

Teaching

Teaching Mentorships

  • CS 6190 Probabilistic Machine Learning (Spring 2023)
  • CS 6350 Machine Learning (Fall 2022)