Susik Yoon

TimelyRAG is proposed, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents, and TimelyQABench is introduced, the first benchmark for regulation-heavy domains with overlapping-evolving challenges.

PEARL redefines multi-hop table retrieval by achieving up to 30% better accuracy without the need for real-time LLM inference.

BOAR reveals that addressing missing and unreliable auxiliary signals can lead to significant improvements in recommendation accuracy, especially for unseen items.

PGMem bridges the gap between user events and evolving personas, leading to more accurate and personalized dialogue interactions.