## Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows: *PROS: handle irregularly sampled time series data. The paper is very well written and easy to understand. *CONS: paper confuses "Background" and "Related Work", lack of motivation for continuity. One reviewer recommend borderline rejection, but in my opinion the authors successfully addressed his concerns in the rebuttal. Recommendations: The authors are encouraged to clearly explain the reviewers' concern on potential similarities of the approach with the Kalman filter with nonlinear outputs. Also the issues related to background and related work and motivation for continuity.