2608 papers
This paper advocates for adopting "diagrams-as-code" in scientific publications to eliminate interpretive ambiguity, thereby enabling reliable information handoffs between scientists, large language models, and autonomous AI agents for future scientific discovery.
This paper presents and evaluates a resource-aware eBPF/XDP architecture for mitigating DDoS attacks on IoT edge systems, demonstrating that while the approach effectively blocks malicious traffic and preserves service continuity, it requires careful platform-specific resource budgeting to manage the associated CPU and latency trade-offs.
This paper proposes a hybrid fuzzy swarm intelligence framework that integrates Adaptive Fuzzy Particle Swarm Optimization and a Fitness-Weighted Fuzzy Grey Wolf Optimizer to jointly address high-dimensional feature redundancy, graded veracity cues, and hyperparameter sensitivity, achieving superior fake news detection accuracy and efficiency across multiple datasets compared to existing baselines.
This review argues that while current AI systems demonstrate strong functional and behavioral task performance, they lack the mechanistic integration of memory, learning, context sensitivity, decision-making, and embodiment required for genuine human-like cognition, and it proposes a research agenda with measurable criteria to bridge this gap.
This paper proposes a WolverBear-Enhanced Evolution Transformer (WoBeOA + E-former) framework that optimizes image-based scene classification and integrates audio-derived contextual actions via a Visformer to construct comprehensive scene graphs, achieving high accuracy in multi-modal scene understanding.
This study addresses the inefficiencies of manual project allocation in the Computer Science Department of Adeyemi College of Education by designing and implementing an automated system to prevent duplicate topics and improve database management, while recommending enhanced student collaboration and infrastructure to support future development.
This paper evaluates the performance of Pthreads, OpenMP, and MPI in parallelizing a computationally intensive SIR epidemic simulation on a 2D grid, demonstrating that MPI achieves superior speedup and near-linear scaling for large grids compared to the moderate and limited scaling observed in OpenMP and Pthreads due to synchronization and memory contention overheads.
This paper presents a real-time, lightweight American Sign Language recognition system that utilizes Google MediaPipe for hand landmark detection and a deep neural network to achieve 98.49% accuracy in classifying static ASL alphabet gestures on consumer-grade devices.
This study demonstrates that machine learning models predicting pharmaceutical inspection outcomes primarily capture the FDA's own regulatory targeting processes rather than inherent manufacturing quality, resulting in unstable feature explanations and the risk that deploying such models would amplify existing inspection biases.
This paper introduces Profiled State Recovery, a practical framework that manages persistent adaptation states in streaming open-vocabulary test-time adaptation through a frozen, label-free lifecycle, demonstrating significant performance gains across diverse models and datasets while establishing state management as a critical design axis for streaming TTA.