activity
20242026
collaborators

6 papers

cs.LG2026

GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning

Liyan Tan, Yequan Zhao, Yifan Yang +3

Zeroth-order (ZO) optimization is a memory-efficient alternative to backpropagation for fine-tuning large language models, but its deployment is limited by the high variance of gra…

cs.LG2026

KANO: Kolmogorov-Arnold Neural Operator

Jin Lee, Ziming Liu, Xinling Yu +4

We introduce Kolmogorov--Arnold Neural Operator (KANO), a dual-domain neural operator jointly parameterized by both spectral and spatial bases with intrinsic symbolic interpretabil…

cs.LG2026

Scalable Back-Propagation-Free Training of Optical Physics-Informed Neural Networks

Yequan Zhao, Xinling Yu, Xian Xiao +6

Physics intelligence and digital twins often require rapid and repeated performance evaluation of various engineering systems (e.g. robots, autonomous vehicles, semiconductor chips…

cs.LG2025

DeepOHeat-v1: Efficient Operator Learning for Fast and Trustworthy Thermal Simulation and Optimization in 3D-IC Design

Xinling Yu, Ziyue Liu, Hai Li +5

Thermal analysis is crucial in 3D-IC design due to increased power density and complex heat dissipation paths. Although operator learning frameworks such as DeepOHeat~\cite{liu2023…

cs.LG2025

Experimental Demonstration of an Optical Neural PDE Solver via On-Chip PINN Training

Yequan Zhao, Xian Xiao, Antoine Descos +6

Partial differential equation (PDE) is an important math tool in science and engineering. This paper experimentally demonstrates an optical neural PDE solver by leveraging the back…

cs.LG2024

Separable Operator Networks

Xinling Yu, Sean Hooten, Ziyue Liu +4

Operator learning has become a powerful tool in machine learning for modeling complex physical systems governed by partial differential equations (PDEs). Although Deep Operator Net…