publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. BWLer: Barycentric Weight Layer Elucidates a Precision-Conditioning Tradeoff for PINNs
    Jerry Weihong Liu, Yasa Baig, Denise Hui Jean Lee, Rajat Vadiraj Dwaraknath, Atri Rudra, and Christopher Re
    In Workshop on the Theory of AI for Scientific Computing @ COLT, 2025
    Best Paper Award
  2. Score-Debiased Kernel Density Estimation
    Elliot L Epstein, Rajat Vadiraj Dwaraknath, Thanawat Sornwanee, John Winnicki, and Jerry Weihong Liu
    In Frontiers in Probabilistic Inference: Learning meets Sampling @ ICLR, 2025
  3. Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters
    Roberto Garcia, Jerry Weihong Liu, Daniel Sorvisto, and Sabri Eyuboglu
    ICLR, 2025
  4. Towards Learning High-Precision Least Squares Algorithms with Sequence Models
    Jerry Weihong Liu, Jessica Grogan, Owen Dugan, Ashish Rao, Simran Arora, Atri Rudra, and Christopher Ré
    ICLR, 2025
  5. Restructuring Vector Quantization with the Rotation Trick.
    Christopher Fifty, Ronald G Junkins, Dennis Duan, Aniketh Iger, Jerry Weihong Liu, Ehsan Amid, Sebastian Thrun, and Christopher Ré
    ICLR, 2025
    Oral (Top 1.82%)

2024

  1. A Hessian View of Grokking in Mathematical Reasoning
    Zhenshuo Zhang, Jerry Weihong Liu, Christopher Ré, and Hongyang R Zhang
    In The 4th Workshop on Mathematical Reasoning and AI @ NeurIPS, 2024
  2. Can Transformers Solve Least Squares to High Precision?
    Jerry Weihong Liu, Jessica Grogan, Owen M Dugan, Simran Arora, Atri Rudra, and Christopher Ré
    In Workshop on Efficient Systems for Foundation Models II @ ICML, 2024

2023

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

2021

  1. Non-Diffusive Volume Advection with a High Order Interface Reconstruction Method
    Jerry Weihong Liu and Jin Yao
    2021
    10th International Conference on Numerical Methods for Multi-Material Fluid Flow, August 2022.

2020

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