The field of recommender systems is shifting towards incorporating sequential information to improve prediction accuracy. Researchers are exploring various techniques to model temporal and sequential patterns in user behavior, such as using graph neural networks and contrastive learning methods. These approaches aim to capture the complex relationships between users and items, including repeat consumption and complementary product recommendations. Noteworthy papers include: Heterogeneous Sequel-Aware Graph Neural Networks for Sequential Learning, which proposes a novel graph neural network architecture that incorporates temporal item sequence information to enhance recommendation performance. TSRec: Enhancing Repeat-Aware Recommendation from a Temporal-Sequential Perspective, which introduces a model that utilizes temporal and sequential patterns to improve repeat-aware recommendation. Revisiting Graph Projections for Effective Complementary Product Recommendation, which presents a simple yet effective method for predicting complementary products based on the structure of a directed weighted graph. Contrastive Matrix Completion with Denoising and Augmented Graph Views for Robust Recommendation, which proposes a novel method that uses contrastive learning to improve the robustness of matrix completion-based recommender systems.