AI RESEARCH
Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods
arXiv CS.AI
•
ArXi:2603.16413v1 Announce Type: cross Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a \textbf{proof-of-concept pilot study} showing that persistent memory in the \emph{continuous latent space} of a frozen LLM is feasible -- even under severe resource constraints (a single frozen Flan-T5-XL backbone, small trainable adapters, a single dataset