Large Language Models (LLMs) remain highly susceptible to jailbreak attacks that bypass safety alignments through sophisticated prompt manipulation. While multi-agent defense systems have emerged as a promising countermeasure, existing frameworks pre...
Large language models (LLMs), built upon Transformer architectures, have demonstrated remarkable performance in a wide range of natural language processing tasks. However, their practical deployment—especially in long-context scenarios—is...
The exponential growth of AI applications has intensified the demand for efficient inference hardware capable of delivering low-latency, high-throughput, and energy-efficient performance. This study presents a systematic, empirical comparison of GPU-...
LLM-based language services (e.g., summarization, translation, and question answering) require low-latency and cost-effective inference, yet GPU resources may be costly, unavailable, or difficult to integrate in many deployments. Many-core CPUs provi...
Nanofiber-based structures have shown considerable potential in semiconductor-related applications, including ultra-thin dielectric layers and flexible electronic devices, owing to their tunable micro-/nanoscale morphology. However, the manufacturing...
Large language model (LLM) serving has emerged as a major source of energy consumption in modern AI infrastructure. In current deployments, graphics processing units (GPUs) are typically operated at default high-frequency settings to maximize perform...
Deploying Large Language Models (LLMs) in edge environments faces two major challenges: (i) the conflict between limited device resources and high computational demands, and (ii) the dynamic impact of user mobility on model partitioning and task offl...
Large language model (LLM) inference is an increasing component of AI energy demand, while the energy effects of weight quantization depend on workload phase and implementation. We benchmarked four LLM families—Gemma 4 E4B IT, Qwen3.5 4B, Nemot...
With the increasing computational demands of large language models (LLMs), there is a pressing need for more specialized hardware architectures capable of supporting their dynamic and memory-intensive workloads. This paper examines recent studies on...
Large language models (LLMs) exhibit strong semantic reasoning capabilities for autonomous driving decision-making; however, their substantial inference latency poses a critical challenge for real-time closed-loop vehicle control. This study proposes...
Unmanned aerial vehicle (UAV) swarms generate massive multi-modal sensor data streams from onboard payloads such as RGB cameras, LiDAR, and thermal sensors. Large language models (LLMs) can interpret these data for natural language-based swarm coordi...
The intersection of edge computing, Large Language Models (LLMs), and the Transformer architecture is a very active and fascinating area of research. The core tension is that LLMs, which are built on the Transformer architecture, are massive and comp...
2 November 2026
Large language model (LLM) accelerators are commonly optimized for fixed model structures and isolated inference workloads, whereas emerging artificial-intelligence operating systems (AI OSs) primarily virtualize agents, memory, and tools in software...
Temporal Knowledge Graph Inference (TKGI) is a cornerstone for intelligent decision-making in dynamic scenarios, but existing models face critical bottlenecks, including inadequate complex-context modeling, a lack of entity importance quantification,...
As large language models (LLMs) increasingly enter specialized domains, inference without external resources often leads to knowledge gaps, opaque reasoning, and hallucinations. To address these challenges in power equipment defect grading, we propos...
Object detection is a critical technology for smart city development. As request volumes surge, inference is increasingly offloaded from centralized clouds to user-proximal edge sites to reduce latency and backhaul traffic. However, heterogeneous wor...
Nowadays, more enterprises are rapidly transitioning to cloud computing as it has become an ideal platform to perform the development and deployment of software systems. Because of its growing popularity, around ninety percent of enterprise applicati...
Low-power NPUs enable on-device LLM inference through efficient integer and fixed-point algebra, yet their lack of native exponential support makes Transformer softmax a critical performance bottleneck. Existing NPU kernels approximate
Deep learning-based flow field prediction for microclimate pollutant dispersion represents an emerging and promising methodology, where effectively integrating meteorological, spatial, and temporal information remains a critical challenge. To address...
The convergence of Artificial Intelligence (AI) and the Internet of Things (IoT) is enabling a new class of intelligent applications. Specifically, Large Language Models (LLMs) are emerging as powerful tools not only for natural language understandin...
Query–service matching in customer service systems faces a critical challenge of accurately aligning user queries expressed in colloquial language with formally defined services while balancing business objectives. Traditional keyword-based and...
Conventional approaches to building energy retrofit decision-making struggle to generalize across diverse building characteristics, climate conditions, and occupant behaviors, and often lack interpretability. Generative AI, particularly Large Languag...
Under the “Dual Carbon” goal, public opinion analysis is crucial for optimizing policy implementation and enhancing social consensus, yet it faces challenges such as insufficient multi-source data integration, limited causal modeling, and...
Recent research has explored combining large language models (LLMs) with speech recognition for various services, but such applications require a strong network environment for quality service delivery. For on-device services, which do not rely on ne...
Large language models (LLMs) built upon the Transformer architecture have achieved remarkable performance in natural language understanding, text generation and logical reasoning, while their internal working mechanisms remain poorly interpreted. Thi...
The integration of unmanned aerial vehicles (UAVs), autonomous vehicles, and advanced satellite systems in sixth-generation (6G) networks is poised to redefine next-generation communications as well as next-generation intelligent transportation syste...
Deep learning models for power quality (PQ) disturbance classification remain critically vulnerable to adversarial perturbations, with classification performance degrading severely under white-box attacks. Existing defenses address individual models...
Auditability and regulatory compliance are increasingly required for deploying large language models (LLMs). Prior work typically targets isolated stages such as training or unlearning and lacks a unified mechanism for verifiable accountability acros...
The rapid advancement of large language models (LLMs) and vision-language models (VLMs) holds enormous promise across industries, including healthcare but hospitals face unique barriers, such as stringent privacy regulations, heterogeneous IT infrast...
Large language models (LLMs) are increasingly applied to software vulnerability detection, but evaluations report accuracy while ignoring inference cost and energy and under-represent open-weight models relative to proprietary systems. We benchmark e...
This study develops an integrated LLM–fuzzy decision-support and digital twin framework for adaptive agricultural robotics, combining semantic reasoning, fuzzy inference, multi-objective optimization, and feedback-driven state updating. Numeric...
Document-level Event Extraction (DEE) requires identifying complex event records and arguments dispersed across unstructured texts. However, applying general Large Language Models (LLMs) to DEE is intrinsically hindered by their lack of inductive bia...
Large Language Models (LLMs) offer state-of-the-art performance in natural language understanding and generation tasks. However, the deployment of leading commercial models for specialized tasks, such as e-commerce, is often hindered by high computat...
The rapid deployment of Large Language Models (LLMs) in multilingual, production-scale systems has made inference-time energy consumption a critical yet systematically under-evaluated dimension of model quality. While accuracy-centric benchmarks domi...
The integration of natural language understanding into conversational commerce requires robustly extracting structured intents from idiomatic text. While cloud-based models are highly capable, their latency, privacy risks, and operational costs neces...
Large Language Models (LLMs) combined with visual foundation models have demonstrated significant advancements, achieving intelligence levels comparable to human capabilities. This study analyzes the latest Multimodal LLMs (MLLMs), including Multimod...
Urban expressway projects are critical components of modern transportation infrastructure, yet their construction quality is often threatened by multi-source, latent, and dynamic risks. Traditional expert-driven risk identification methods frequently...
Facility layout design (FLD) is critical for optimizing manufacturing efficiency, yet traditional approaches struggle with complexity, dynamic constraints, and fragmented data integration. This study proposes a generative-AI-enabled facility layout d...
Large Language Models (LLMs), based on transformer architecture, have demonstrated remarkable capabilities in natural language processing tasks, enabling machines to generate human-like text and engage in meaningful dialogues. However, the exponentia...
Retrieval-Augmented Generation (RAG) mitigates hallucination and knowledge staleness in large language models (LLMs) by injecting external knowledge into the context window, yet its effectiveness is rigidly constrained by attention dilution and infer...
This paper proposes the Continuous Operational Feedback Loop (COFL) architecture, a fully localized, event-driven operational monitoring and response system for Direct-to-Consumer (D2C) commerce. The architecture integrates the n8n workflow engine wi...
Inference now dominates the lifecycle footprint of large language models, yet published estimates often use inconsistent boundaries and optimize carbon while ignoring water. We present a provider-agnostic framework that unifies scope-transparent meas...
With the rapid advancement of Transformer-based large language models (LLMs), these models have found widespread applications in industrial domains such as code generation and non-functional requirement (NFR) classification in software engineering. H...
The rapid spread of climate change misinformation across digital platforms undermines scientific literacy, public trust, and evidence-based policy action. Advances in Natural Language Processing (NLP) and Large Language Models (LLMs) create new oppor...
As UAVs are increasingly deployed in complex scenarios such as disaster monitoring, emergency rescue, and power-line inspection, traditional command and control systems face severe challenges in intelligent decision-making, resource allocation, and e...
Recent advances in land system research depend heavily on efficient access to large-scale, multi-source remote sensing spatiotemporal databases. Although Text-to-SQL provides natural language interfaces, the scale and spatial complexity of remote sen...
Real-time video anomaly detection (VAD) under realistic edge constraints—sub-second latency, ≤25 W power, no cloud dependency, and human-interpretable output—remains an open problem. Existing lightweight video convolutional neural netw...
We propose QwenMoE-SC, a semantic communication framework that integrates a Mixture-of-Experts (MoE) Large Language Model with three complementary modules: (1) a Graph Neural Network (GNN)-based Unequal Error Protection (UEP) plug-in that assigns sem...
Secure Shell (SSH) intrusions against Linux servers remain a dominant vector of opportunistic and targeted cyber incidents, yet operational honeypots treat attacker commands either as isolated lookup keys for static templates or as input to a single...
Conventional web analytics treats the human user as its fundamental unit of analysis, assuming stable preferences, identifiable intentions, and behavioral patterns that unfold over time. That assumption is under strain. Crawlers and traditional bots...
of 2