Papers
1
Total Citations
11
H-Index
1
About
Lile Cai is a researcher at the forefront of applying deep learning to industrial and materials science challenges, with a particular focus on 3D defect detection and metrology. Their work bridges the gap between cutting-edge computer vision techniques and practical manufacturing quality control, especially for high-bandwidth memory (HBM) components. Cai’s most cited paper, "3D Defect Detection and Metrology of HBMs using Semi-Supervised Deep Learning" (2023, 11 citations), demonstrates a novel approach that leverages recent advances in 3D semi-supervised learning to identify and segment structural anomalies with minimal labeled data—a critical innovation for industries where annotated 3D datasets are scarce and expensive. This contribution not only enhances automated inspection in semiconductor manufacturing but also showcases how deep learning can be adapted from fields like medical imaging and autonomous driving to solve real-world engineering problems. Cai’s work is notable for its practical impact, offering scalable solutions that improve both accuracy and efficiency in defect analysis, making them a key figure in the intersection of AI and advanced manufacturing.
Research Focus
Key Achievements
Top Papers
- 1