Tag
This paper formulates context distillation as a latent memory management problem, proposing a framework that stores distilled contexts as independent LoRA adapters with retrieval, routing, and self-gating to improve robustness and efficiency.
MeMo introduces a modular memory model that augments any LLM to store, retrieve, and integrate new knowledge without retraining or catastrophic forgetting. It outperforms RAG-based methods on benchmarks like BrowseComp-Plus, NarrativeQA, and MuSiQue.