Yun-Bo Zhao

This survey develops a unified, concept-driven view of major CT machine learning branches through a taxonomy that organizes families according to their underlying base mathematical formulations, and presents a canonical mathematical formulation that relates these families through different architectural choices of vector-field parameterization, stochasticity, memory mechanisms, and discretization.

Users can now intuitively grasp a robot's inferred goals through its motion, reducing control effort and enhancing collaboration.

By reformulating attention as a stochastic differential equation modulated by biologically-inspired neuronal circuits, this work offers a new path to interpretable and well-calibrated uncertainty estimates in continuous-time representation learning.