Tag
This paper introduces CRAWO, a framework for adaptive workload orchestration of AI pipelines across heterogeneous edge infrastructures. It uses a control-loop model and Kubernetes-based implementation to improve workload distribution and reduce reliance on centralized cloud processing, demonstrated in a vehicle surveillance scenario.
FedOPAL proposes a framework that adapts visual prompts as feature rectifiers for one-shot federated learning, achieving efficient gradient-free aggregation via analytic methods while outperforming existing analytical approaches and matching iterative methods with zero server-side training costs.
AI is enabling the collection and processing of previously inaccessible data from the physical world through cheaper sensors, robotics, and multimodal models, creating new data flywheels in infrastructure, healthcare, and industrial automation.
CBD introduces an API-only black-box unlearning framework for LLMs that uses two auxiliary models to create controlled behavioral divergence between retained and target data, achieving a better unlearning-utility trade-off compared to existing methods.
CogGuard is a proactive-warning framework for edge intelligent services that decouples offline LLM-based profile construction from online SLM-based score prediction, reducing construction time by 48% and fine-tuning time by 19% while achieving lower prediction errors on education and operation datasets.
This paper introduces SPIN, a framework for decentralized multi-agent swarm control that uses tensor network factorization to reduce computational complexity from exponential to linear, enabling low-power edge deployment. It validates the approach in simulation for tracking, coverage, and coordination tasks.
This paper presents a comprehensive survey and taxonomy of federated learning over human-body communication for on-body edge intelligence, including a scheduling vignette called BODYFED-HBC.
This paper proposes MODIAD, a framework for multimodal online distributed industrial anomaly detection, addressing resource constraints with a Multi-class Intelligent Scheduling problem and a Resource Efficient Class-Wise Low Rank Adaptation (REC-LoRA) strategy. Experiments on MVTec 3D-AD and Eyecandies datasets demonstrate superior performance and efficiency.
This paper presents an AI-driven framework for energy-efficient environmental monitoring in smart cities using edge intelligence and TinyML, which dynamically activates sensors based on spatiotemporal conditions to reduce energy consumption and extend sensor lifespan.
FusionSense introduces a tri-stage near-sensor learning framework for multimodal edge intelligence that jointly reduces compute and communication by using fusion-aware filtering, achieving up to 33× energy savings and significant data-reduction gains on RGB-Depth/LiDAR tasks.
AutoMCU is a multi-agent system leveraging LLMs to automate neural network design for microcontroller units, significantly reducing customization time while ensuring feasibility under hardware constraints.