New agentic memory framework uses 118K tokens per query. LangMem burns through 3.26M.

NUS researchers' MRAgent framework reduces LLM agent memory retrieval to 118K tokens per query — vs. 3.26M for LangMem — ...
IEEE

Optimizing Query-by-Example Spoken Term Detection with Audio-to-Token Sequence Clustering and Query-Guided Retrieval

Abstract: Query-by-Example Spoken Term Detection (QbE-STD) retrieves relevant audio files corresponding to a spoken query, without relying on explicit word-level textual transcriptions. In ...
IEEE

Large Language Model Based Multi-Objective Optimization for Integrated Sensing and Communications in UAV Networks

Abstract: This letter investigates an un-crewed aerial vehicle (UAV) network with integrated sensing and communication (ISAC) systems, where multiple UAVs simultaneously sense the locations of ground ...