The field of information retrieval is moving towards more efficient and scalable solutions, with a focus on vector search and retrieval-augmented generation. Recent advancements have led to the development of innovative techniques, such as hierarchical patch compression and hybrid-based retrieval methods, which enhance the efficiency of multi-vector document retrieval systems while preserving their retrieval accuracy. Additionally, there is a growing interest in unifying text-to-SQL and vector search to support more diverse and holistic natural language queries. The integration of these technologies has the potential to revolutionize the way we interact with databases and retrieve information. Noteworthy papers include: HPC-ColPali, which achieves significant storage reduction and latency improvement through hierarchical patch compression and attention-guided dynamic pruning. HyReC, which introduces an end-to-end optimization method tailored specifically for hybrid-based retrieval in Chinese. JointRank, which proposes a model-agnostic method for fast reranking large sets that exceed model input limits. Text2VectorSQL, which bridges text-to-SQL and vector search for unified natural language queries. NaviX, which presents a native vector index for graph DBMSs with robust predicate-agnostic search performance.