Topic
edge computing
RAMS: Resource-Adaptive Model Switching for Embedded Edge Perception Under Load
Researchers present RAMS, a runtime controller that monitors device pressure and dynamically selects among three YOLOv8 tiers on embedded hardware, achieving up to 5.6x faster inference than a fixed medium model while retaining 74% of its accuracy. The system introduces a detection-conditioned switching policy and a new scalar metric, SWAS, for offline policy comparison.
New Hardware-Aware Neural Architecture Search Runs on Embedded Devices with Under 512MB RAM
Researchers propose a hardware-aware neural architecture search (HW NAS) method that runs on embedded devices with under 512MB of RAM. It produces tiny convolutional neural networks for low-end microcontrollers, enabling on-device AI without cloud dependence. The approach achieves state-of-the-art results on the Visual Wake Word dataset.
CogGuard: New Framework Reduces Profile Construction Time by 48% for Edge AI Warning Systems
Researchers propose CogGuard, a proactive-warning framework for edge intelligent services that decouples offline LLM-based profile construction from online SLM prediction. It reduces profile construction time by 48% and distributed fine-tuning time by 19% while achieving mean absolute errors of 13.4 and 5.9 on 100-point-scale tasks.
EdgeCitadel: Hybrid NATS-MQTT Orchestration Platform for Edge Multi-Agent Systems
EdgeCitadel is an edge multi-agent orchestration platform built around a single NATS 2.10 server with an MQTT adapter. It combines MQTT connectivity, JetStream-backed persistence, direct peer delegation, and a passive aggregator. A testbed spanning ARM64, x64, and Android clients demonstrates the hybrid architecture.