4157 papers
This paper demonstrates that entropy-based detection of malicious PE files is severely compromised by data duplicates, size confounding, and adversarial padding, revealing that such models largely memorize known sections and can be easily evaded by appending benign-looking bytes, thereby necessitating more robust detection strategies.
GenEdXR is a novel closed-loop framework that synergistically integrates generative AI and extended reality through transformer-based knowledge tracing, LLM-driven content synthesis, and adaptive orchestration to significantly enhance learning gains, engagement, and flow in educational entertainment ecosystems.
This paper presents a comprehensive survey of fifty-one computer vision-based studies from the last decade on automatic student engagement detection in online classrooms, highlighting the high accuracy of existing machine learning methods while identifying critical gaps in handling occluded or low-light images and the need for deeper research into the link between emotion and engagement.
This paper presents JFilterLocalizationCNN, a lightweight dual-head convolutional neural network that enables real-time joint classification of thermal scenes and heat-source localization on native 8×8 infrared frames, achieving high accuracy and efficient deployment on resource-constrained microcontrollers while preserving user privacy.
This paper proposes a token-based concurrency control algorithm utilizing a circulating token ring topology to serialize refresh transactions and ensure data consistency in replicated database systems operating over decentralized peer-to-peer networks.
This paper develops an evolutionary game model to demonstrate that jointly weakening governance channels in generative AI ecosystems significantly increases risk and reduces trust, while showing that the timing of system dynamics critically determines local stability boundaries.
This paper proposes STFA-Net, a lightweight and robust dynamic object recognition framework that integrates spatio-temporal feature fusion with an adaptive attention mechanism to effectively handle rapid motion, occlusion, and illumination changes, achieving state-of-the-art performance on both ImageNet-Vid and a custom warehouse benchmark while utilizing significantly fewer parameters and computational resources than existing baselines.
This paper proposes a decomposition-based approach with a closed-loop feedback mechanism to efficiently solve the joint mapping and scheduling problem of dependent imprecise computation tasks on heterogeneous multicore systems, achieving near-optimal quality-of-service with significantly reduced computational time compared to commercial solvers.
The paper proposes RIBGCL, a graph contrastive learning framework for social recommendation that mitigates noisy social ties and popularity bias by jointly employing an interest-consistency gate for confidence-weighted social propagation and a bounded, similarity-controlled item-representation correction.
This paper establishes the nonconvex geometry of the regularized Dirichlet likelihood in Evidential Deep Learning by proving the equivalence of second-order conditions to derivative positivity, deriving exact comparative statics, and introducing a certified finite-convergence face-enumeration algorithm that explains the Evidence Ceiling effect and sparsification of active sets.