Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge and perception. Retrieval-augmented generation (RAG) addresses this by retrieving query-relevant contexts from knowledge bases to support LLM reasoning. Recent advances leverage pre-constructed graphs to capture the relational connections among distributed documents, showing remarkable performance in complex tasks. However, existing Graph-based RAG (GraphRAG) methods rely on a costly process to transform the corpus into a graph, introducing overwhelming token cost and update latency. Moreover, real-world queries vary in type and complexity, requiring different logic structures for accurate reasoning. The pre-built graph may not align with these required structures, resulting in ineffective knowledge retrieval. To this end, we propose a Logic-aware Retrieval Augmented Generation framework (LogicRAG) that dynamically extracts reasoning structures at inference time to guide adaptive retrieval without any pre-built graph. LogicRAG begins by decomposing the input query into a set of subproblems and constructing a directed acyclic graph (DAG) to model the logical dependencies among them. To support coherent multi-step reasoning, LogicRAG then linearizes the graph using topological sort, so that subproblems can be addressed in a logically consistent order. Besides, LogicRAG applies graph pruning to reduce redundant retrieval and uses context pruning to filter irrelevant context, significantly reducing the overall token cost. Extensive experiments demonstrate that LogicRAG achieves both superior performance and efficiency compared to state-of-the-art baselines.

Large language models (LLMs) have shown great success in content generation and intelligent intelligent decision making for IoT systems. Traditionally, LLMs are deployed on the cloud, incurring prolonged latency, high bandwidth costs, and privacy concerns. More recently, edge computing has been considered promising in addressing such concerns because the edge devices are closer to data sources. However, edge devices are cursed by their limited resources and can hardly afford LLMs. Existing studies address such a limitation by offloading heavy workloads from edge to cloud or compressing LLMs via model quantization. These methods either still rely heavily on the remote cloud or suffer substantial accuracy loss. This work is the first to deploy LLMs on a collaborative edge computing environment, in which edge devices and cloud servers share resources and collaborate to infer LLMs with high efficiency and no accuracy loss. We design EdgeShard, a novel approach to partition a computation-intensive LLM into affordable shards and deploy them on distributed devices. The partition and distribution are nontrivial, considering device heterogeneity, bandwidth limitations, and model complexity. To this end, we formulate an adaptive joint device selection and model partition problem and design an efficient dynamic programming algorithm to optimize the inference latency and throughput. Extensive experiments of the popular Llama2 serial models on a real-world testbed reveal that EdgeShard achieves up to 50% latency reduction and$2 \times $throughput improvement over the state-of-the-art.

Occupational stress has emerged as an undeniable concern. Fortunately, leveraging IoT and AI technologies allows us to gather vital sign data and assess cardiovascular health, individual stress levels, physiological resilience, and emotional states. This study highlights the potential of Heart Rate Variability (HRV) analysis in constructing stress prediction models, with a specific focus on developing an efficient model with minimal data requirements. Convolutional Neural Networks (CNN) have been employed to process raw waveform data for feature extraction. Simultaneously, R-R Interval (RRI) analysis was conducted to derive a set of statistical features. Various dimension reduction algorithms Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Random Projection (RP) were tested, and PCA demonstrated its significance in reducing dataset complexity, enabling swift model training without compromising accuracy excessively. This research aims to explore the feasibility of predicting an individual’s stress levels using minimal and simpler data. The objective is to pave the way for predictive models to be integrated onto lightweight platforms such as millimeter-wave chips. Our approach emphasizes non-contact monitoring of heartbeat variations, particularly beat-to-beat intervals (BBI), offering a novel method for non-invasive stress detection suitable for real-time applications on compact devices.