Discrete Prototypical Memories for Federated Time Series Foundation Models

ArXi:2604.04475v1 Announce Type: cross Leveraging Large Language Models (LLMs) as federated learning (FL)-based time series foundation models offers a promising way to transfer the generalization capabilities of LLMs to time series data while preserving access to private data. However, the semantic misalignment between time-series data and the text-centric latent space of existing LLMs often leads to degraded performance.