11 papers
Extending Fourier Neural Operators for Modeling Parameterized and Coupled PDEs
Cheng Jing, Uvini Balasuriya Mudiyanselage, Abhishek Verma +3
Parameterized and coupled partial differential equations (PDEs) are central to modeling phenomena in science and engineering, yet neural operator methods that address both aspects…
Meta-learning Structure-Preserving Dynamics
Cheng Jing, Uvini Balasuriya Mudiyanselage, Woojin Cho +3
Structure-preserving approaches to dynamics discovery have demonstrated great potential for modeling physical systems due to their use of strong inductive biases, which enforce key…
Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation
Junghwan Park, Woojin Cho, Junhyuk Heo +2
Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they…
Learning Low Rank Neural Representations of Hyperbolic Wave Dynamics from Data
Woojin Cho, Kookjin Lee, Noseong Park +2
We present a data-driven dimensionality reduction method that is well-suited for physics-based data representing hyperbolic wave propagation. The method utilizes a specialized neur…
Disaggregated Health Data in LLMs: Evaluating Data Equity in the Context of Asian American Representation
Uvini Balasuriya Mudiyanselage, Bharat Jayprakash, Kookjin Lee +1
Large language models (LLMs), such as ChatGPT and Claude, have emerged as essential tools for information retrieval, often serving as alternatives to traditional search engines. Ho…
Modeling Neural Networks with Privacy Using Neural Stochastic Differential Equations
Sanghyun Hong, Fan Wu, Anthony Gruber +1
In this work, we study the feasibility of using neural ordinary differential equations (NODEs) to model systems with intrinsic privacy properties. Unlike conventional feedforward n…