Context Distillation as Latent Memory Management

ArXi:2605.28889v1 Announce Type: cross Context distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent memories should be d, retrieved, and safely activated in non-oracle settings. We formulate context distillation as a latent memory management problem. We distill each context into an independent LoRA adapter, forming a modular memory bank that enables explicit memory selection.