Lo, Shao-YuShao-YuLoChang, Che-MingChe-MingChangChang, Yao-WenYao-WenChang2026-04-162026-04-162025-11-2010923152https://www.scopus.com/record/display.uri?eid=2-s2.0-105029378461&origin=resultslisthttps://scholars.lib.ntu.edu.tw/handle/123456789/737216Warpage caused by the manufacturing thermal process can significantly reduce product yield in advanced packaging. As a result, numerical simulations such as finite element methods (FEMs) are often used to analyze warpage effects. However, constrained by the mesh generation and large matrix-solving requirements in finite element methods, optimizing for warpage can be time-consuming. This paper presents a fundamental physical model, training framework, and methodology for a warpage surrogate model based on DeepONets, a physics-informed operator learning framework. Experimental results show that our warpage model achieves an average speedup of 435X compared to traditional solvers while maintaining a minimal average warpage error of just 1.9%.falseconference paper10.1109/iccad66269.2025.112408142-s2.0-105029378461