Linhai Ma

I am currently a postdoc at Yale University, focusing on information extraction from medical text through the use of pretrained language models and large language models (LLMs)

I obtained my Ph.D. in Computer Science from the University of Miami under the supervision of Dr. Liang Liang. During my Ph.D., my research focused on improving the robustness of deep neural networks against adversarial noise. I proposed various methods to achieve this goal, including regularization techniques and adversarial training. In addition to conducting experiments on standard natural image classification tasks, I developed approaches to enhance model robustness for more complex applications in the medical imaging domain, such as ECG signal automatic diagnosis, MRI image segmentation, cephalometric landmark detection, and blood cell detection.

I received my master’s degree from the State Key Laboratory of Computer Science (SKLCS) at the Institute of Software, Chinese Academy of Sciences (ISCAS), under the supervision of Dr. Peng Wu. During my master’s studies, my primary research focus was on software testing and concurrency. I proposed an adaptive algorithm for testing C++ concurrent data structures based on a coverage criterion.