4158 papers
This study demonstrates that integrating source credibility, inspired by Qur'anic principles, with deep learning models—specifically a highly efficient CNN architecture—achieves near-perfect accuracy in detecting fake news in the low-resource Kurdish language, significantly outperforming content-only approaches.
This study evaluates five boundary-aware loss functions within 2D and 3D U-KAN pipelines for BraTS 2023 brain tumor segmentation and concludes that while Staged Boundary Loss showed some pipeline-dependent improvements, boundary-aware training generally fails to provide consistent or reproducible advantages over standard region-based objectives.
This paper presents a wearable non-visual guidance system that integrates smart glasses, an edge computing unit, and a haptic wristband to convert spatial perception into actionable cues, demonstrating significantly reduced collision rates for blind users and equivalent performance for low-vision users compared to traditional white canes.
This paper presents the first systematic red-team evaluation of African-language Large Language Models, revealing that despite varying sizes and alignment techniques, models across Hausa, Swahili, Yoruba, and Igbo exhibit significant safety vulnerabilities to culturally grounded adversarial attacks, particularly in propaganda and harm generation categories.
This paper proposes ITS-D3QN, a deep reinforcement learning scheduler utilizing a two-stage architecture and Pareto optimization strategy to effectively balance task response time, energy consumption, and resource utilization in dynamic cloud environments, achieving significant performance improvements over existing methods.
This paper presents an explainable AutoML framework that integrates MFCC-based acoustic features, optimized ensemble learning, and SHAP analysis to achieve high-accuracy traditional music genre classification and support AI-assisted composition through learnable genre-specific acoustic prototypes.
This paper proposes a Collaborative Deep Q-Network (CD-DQN) framework that leverages a multi-head attention mechanism and dynamic region allocation to enable multi-robot teams to efficiently cover unknown complex environments with high adaptability to varying team sizes and map layouts while minimizing redundancy and motion conflicts.
This paper proposes PARRY, a two-layer defense method combining an adversarially trained deep detector with a far-bus witness to effectively detect and bound physically consistent false data injection attacks in power systems, significantly outperforming standard deep learning approaches in detecting substantial load changes.
This paper introduces EdgeRefine, a lightweight residual logit correction module for DeepLabV3 and SegFormer that improves semantic boundary refinement in traffic salient object segmentation by explicitly defining supervised boundaries as morphological mask edges, yielding modest but measurable gains in overlap and boundary metrics while revealing specific limitations in geometric consistency and cross-domain transfer.
Evolver is an experience-driven framework that transforms transient agent exploration into persistent, reusable capabilities without updating foundation model parameters, thereby improving task success rates and execution efficiency across multiple benchmarks.