Feature-Foundation Model Evolution for Low-Latency Semantic Communication

In response to the escalating communication demand, transceivers are transforming from a data-oriented to an artificial intelligence (AI)-driven semantic-aware paradigm. However, current semantic-aware transceivers fail to simultaneously adapt to unseen data without labels and guarantee low data processing latency because strong generalization ability requires large-scale models with robust semantic understanding, while low latency leads to small model size and simple structure. To this end, we propose a feature-foundation model evolution framework deployed at cloud, edge, and users, where models with different scales can cooperate to address these issues. Specifically, the transmitter at edge sends images to the users by performing real-time semantic feature extraction and data encoding, and the small feature model is evolved with the aid of a large foundation model at cloud when unseen data occurs. To simultaneously update the feature model and avoid loss of previously acquired semantic understanding, we design a feature-foundation model evolution scheme where outputs of both foundation and feature models are leveraged. Additionally, to tackle coupled communication-computation resources for evolution, we formulate the resource scheduling problem and design algorithms to minimize the evolution latency. We conduct rigorously-designed simulation to validate the effectiveness of our framework.