2833 papers
This study empirically demonstrates that traditional deterministic security tools fail to detect context-dependent, syntactically valid vulnerabilities introduced by Generative AI in CI/CD pipelines, highlighting an urgent need for probabilistic, intent-aware verification frameworks.
This paper proposes GLFA-Net, a real-time UAV vehicle detection framework that integrates a bidirectional global-local feature aggregation network and a parallel hybrid attention module to overcome challenges like small target detection and scale variations, achieving state-of-the-art performance on multiple public benchmarks.
This paper proposes RLPF-YOLO, a lightweight and resolution-flexible object detector designed for edge devices that employs a "feature compensation" philosophy with novel modules like C2F-FCM, RMKPConv, and RCBAM to significantly reduce parameters while enhancing small-object detection accuracy on UAVs.
The paper proposes LSTA-KT, an interpretable knowledge tracing model that combines a dual-flow long-short term attention mechanism with geometric query alignment to effectively balance global learning trends and local fluctuations while filtering noise and providing transparent educational assessments.
This paper proposes a wireless sensor network-driven deep learning framework that integrates industrial field perception data with multimodal text analysis to enable low-latency, high-accuracy real-time assessment of cultural appropriateness in Chinese-English translations for Industry 4.0 applications.
This paper proposes a regularized channel-attentive adversarial framework that enhances unpaired image translation by integrating squeeze-and-excitation attention for feature recalibration, a deeper discriminator, and Total Variation regularization to improve perceptual quality, structural fidelity, and texture consistency across benchmark datasets.
This study demonstrates that the rise of Generative AI interrupts legitimate peripheral participation in online knowledge communities by substituting routine interactions, leading to structural closure characterized by increased modularity and a sharp decline in newcomer retention, particularly within algorithmic domains where procedural codifiability is high.
This study of the University of Hargeisa reveals that while multiple factors correlate with Management Information System implementation, only administrative commitment and IT staff capacity serve as significant independent predictors, highlighting that leadership and technical expertise are the primary drivers of digital transformation in resource-constrained, post-conflict higher education contexts.
This paper introduces AlloyGen, a physics-grounded, self-adaptive multi-agent framework that autonomously orchestrates knowledge retrieval, thermodynamic simulations, and dynamic team organization to streamline complex alloy design workflows for additive manufacturing.
The paper introduces FetMRIE, a novel unsupervised framework utilizing adaptive state-matching denoising diffusion to enhance fetal brain MRI by effectively suppressing motion-induced noise and artifacts while preserving critical anatomical and pathological details without requiring clean reference images.