Shilong Zong
Shilong Zong is a Ph.D. student in the Department of Computer Science. He is advised by Hoda Eldardiry.
His research focuses on Liquid Neural Networks (LNNs), a class of continuous-time neural models inspired by dynamical systems theory. He studies their theoretical properties, including stability, memory efficiency, and multi-time-scale dynamics, and compares them with traditional recurrent neural networks and modern architectures.
Zong also develops structured LNN variants—such as multi-time-scale and mixture-of-experts frameworks—for applications in robotics, control, and time-series prediction, with an emphasis on interpretability and efficient real-time deployment.