Tag
This paper proposes a cloud-edge collaborative architecture for multimodal clinical screening in resource-constrained rural settings, using lightweight edge models to produce structured outputs that a cloud LLM synthesizes into clinical summaries. Evaluated on 100 multimodal cases, the hybrid system achieves high accuracy and factual grounding while transmitting orders of magnitude less data than cloud-only baselines.
DSTFView is a dual-input spatio-temporal-frequency multi-view framework for cloud-edge workload forecasting, jointly modeling closeness and period dependencies with an adaptive fusion mechanism to capture abrupt changes.
CoMIC is a cloud-edge framework for LLM agents that uses collaborative memory and insight circulation to improve long-horizon task performance without requiring parameter updates, achieving gains in progress rate and action grounding across multiple tasks.
INAR-VL proposes a lightweight routing system for edge-cloud vision-language inference that dynamically selects between edge and cloud models based on query complexity, achieving significant latency and energy reductions while preserving near-cloud accuracy.