This document summarizes a research paper on personalizing session-based recommendations with hierarchical recurrent neural networks (HRNNs). The paper proposes using HRNNs to decouple user and session representations, with a user RNN that evolves the user's latent state across sessions and a session RNN that generates personalized recommendations for each session. Experiments on job posting and online video datasets show the HRNN approach outperforms baselines and other RNN methods, particularly for users with longer histories, by up to 28% in recall and 41% in MRR. The HRNN approach effectively transfers cross-session knowledge to improve session-based recommendations.