Skip to main content
Return to top

Jerry Liu

Headshot of Jerry Liu
Program Year:
4
University:
Stanford University
Field of Study:
Computational Math
Advisor:
Chris Re
Degree(s):
B.S. Mathematics, and B.S. Computer Science, Duke University, 2022
Personal URL:
https://jerrywliu.github.io/

Practicum Experience(s)

Lawrence Berkeley National Laboratory (2023)

Practicum Supervisor(s):
Michael
Mahoney
Practicum Title:
Does In-Context Operator Learning Generalize to Domain-Shifted Settings?

Summary of Research

Foundation models have revolutionized language and vision modeling, but so far they have shown limited effectiveness for regression-type tasks and continuous-valued data, such as time series and PDEs. I am broadly interested in understanding the fundamental shortcomings of existing machine learning techniques using tools from numerics, statistics, and complexity theory, towards developing proper foundation models for numerical tasks. Some questions from recent work:
- Do existing machine learning methods only perform pattern matching, or can they learn proper (numerical) algorithms directly from data?
- Why do existing architectures struggle to perform numerical operations precisely, and can we do better?
- What does generalization mean for continuous-valued regression tasks, e.g. for differential equations?

Annual Program Review Abstracts

Fellow Poster
: Can Transformers Solve Least Squares to High Precision? (
2024
)
Fellow Poster
: Consistency Flow Matching: Single-Step Generation With General Corruption Processes (
2023
)

Publications

Catherine Deng*, Junmiao Hu*, Milan Rohatgi, Jerry Weihong Liu, Christopher Re. Constructing Machine-Precision Neural Networks with Quasi-Interpolants. AI&PDE: ICLR 2026 Workshop on AI and Partial Differential Equations, 2026. Oral (8/113 accepted papers).

Owen Dugan*, Roberto Garcia*, Ronny Junkins*, Jerry Liu*, Dylan Zinsley, Sabri Eyuboglu, Atri Rudra, Christopher Re. Constructing Efficient Fact-Storing MLPs for Transformers. In review, 2025. arXiv: 2512.00207.

Xavier Gonzalez, E. Kelly Buchanan, Hyun Dong Lee, Jerry Weihong Liu, Ke Alexander Wang, David M. Zoltowski, Christopher Re, Scott W. Linderman. A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systems. TMLR, 2025. arXiv: 2509.21716.

Jerry Liu, Yasa Baig, Denise Hui Jean Lee, Rajat Vadiraj Dwaraknath, Atri Rudra, Christopher Re. BWLer: Barycentric Weight Layer Elucidates a Precision-Conditioning Tradeoff for PINNs. Workshop on the Theory of AI for Scientific Computing @ COLT, 2025. Best Paper Award. arXiv: 2506.23024.

Elliot L. Epstein*, Rajat Vadiraj Dwaraknath*, Thanawat Sornwanee*, John Winnicki*, Jerry Weihong Liu*. Score-Debiased Kernel Density Estimation. NeurIPS 2025. arXiv: 2504.19084.

Jerry Weihong Liu*, Jessica Grogan*, Owen Dugan, Ashish Rao, Simran Arora, Atri Rudra, Christopher Re. Towards Learning High-Precision Least Squares Algorithms with Sequence Models. ICLR 2025. arXiv: 2503.12295.

Roberto Garcia, Jerry Weihong Liu, Daniel Sorvisto, Sabri Eyuboglu. Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters. ICLR 2025. arXiv: 2503.18216.

Christopher Fifty, Ronald G. Junkins, Dennis Duan, Aniketh Iger, Jerry Weihong Liu, Ehsan Amid, Sebastian Thrun, Christopher Re. Restructuring Vector Quantization with the Rotation Trick. ICLR 2025. Oral (Top 1.82%). arXiv: 2410.06424.

Zhenshuo Zhang, Jerry Weihong Liu, Christopher Re, Hongyang R. Zhang. A Hessian View of Grokking in Mathematical Reasoning. The 4th Workshop on Mathematical Reasoning and AI @ NeurIPS, 2024.

Jerry Weihong Liu, Jessica Grogan, Owen M. Dugan, Simran Arora, Atri Rudra, Christopher Re. Can Transformers Solve Least Squares to High Precision? Workshop on Efficient Systems for Foundation Models II @ ICML, 2024.

Jerry Weihong Liu, N. Benjamin Erichson, Kush Bhatia, Michael W. Mahoney, Christopher Re. Does In-Context Operator Learning Generalize to Domain-Shifted Settings? The Symbiosis of Deep Learning and Differential Equations III @ NeurIPS, 2023.

Jerry Liu, Jin Yao. Non-Diffusive Volume Advection with a High Order Interface Reconstruction Method. USNCCM, 2021.

Liu, J. W., and Yao, J. Non-Diffusive Volume Advection with a High Order Interface Reconstruction Method. Lawrence Livermore National Laboratory, United States, 2021.

Jin Yao, Jerry Liu. Volume-of-Fluids Interface Reconstruction with Curvature and Corner Definition. WCCM-ECCOMAS, 2020.

Jerry Liu, Nathan O'Hara, Alexander Rubin, Rachel Draelos, Cynthia Rudin. Metaphor Detection Using Contextual Word Embeddings from Transformers. Proceedings of the Second Workshop on Figurative Language Processing @ ACL, 2020.

Awards

Alex Vasilos Award, Duke University: 2022.
NSF Graduate Research Fellowship: 2022 (declined).
CRA Outstanding Undergraduate Researcher, honorable mention: 2022.
Phi Beta Kappa (honor society): 2021.
Karl Menger Award, Duke University: 2019.
William Lowell Putnam Mathematical Competition (top 250 participants): 2018, 2019.