863 papers
This study proposes an Artificial Intelligence-Driven Adaptive Learning Ecosystem (AIALE) that integrates adaptive learning, multilingual support, blockchain credential verification, and community mentoring to holistically overcome legal, financial, and technological barriers to higher education for refugee and displaced populations.
This literature review synthesizes 103 records to categorize AI-based 3D radiological image reconstruction methods into four representation families—discrete grids, explicit basis expansions, explicit primitives, and implicit neural representations—while evaluating their respective strengths, limitations, available resources, and critical clinical challenges.
The paper proposes SWCB-YOLO, a lightweight real-time detector for wind turbine blade defects that integrates a Curvature-Aware Shape IoU loss, an Asymmetric Strip Swin-TransformerV2 module, and a Frequency-Spatial Dual-Domain Attention mechanism to achieve robust detection in unstructured environments with 89.0% mAP@50 on a field dataset while running at 35 FPS on edge hardware.
This paper presents TLAS-YHCT, a generative AI assistant for traditional-medicine education that achieves 100% safety against domain-specific attacks through a defense-in-depth architecture, demonstrating that clinically calibrated safety standards and a minimum safety stack combining RAG, standardized prompting, and LLM-as-judge verification are essential for safe deployment in clinical education.
This paper proposes a collaborative optimization method based on the multi-objective marine predator algorithm (MOMPA) and constraint programming to generate area air traffic controller schedules that effectively balance operational efficiency, fatigue risk, and working time fairness, demonstrating superior performance and engineering feasibility through validation with real-world data.
This paper proposes an improved APF-RRT algorithm that integrates power-law decay repulsive gains, a three-level escape mechanism, and adaptive strategies to significantly enhance path planning efficiency, smoothness, and obstacle avoidance for basket-carrying robotic arms in complex agricultural environments.
This paper demonstrates that training a Small Language Model (Gemma 2B) with RLVR and GRPO to enforce calibrated abstention significantly improves clinical safety by doubling the deferral rate for ambiguous cases, despite a trade-off in raw benchmark accuracy.
This paper systematically demonstrates that in chest X-ray AI, correct predictions are frequently accompanied by inaccurate saliency map explanations, revealing a critical decoupling between prediction accuracy and localization fidelity that necessitates mandatory validation thresholds before clinical deployment.
This paper proposes a multi-agent LLM framework featuring distinct planner, executor, and verifier roles operating on a dependency-aware task graph with calibrated parameters and shared-memory mechanisms, which significantly outperforms single-agent baselines in complex task solving by improving completion rates, accuracy, and factual consistency while reducing tool errors.
The paper introduces Stratum-eval, a normative-first evaluation framework for clinical machine learning that mandates a validated Normative Specification Document defining use cases, fairness trade-offs, and stakeholder boundaries before computing any performance metrics, thereby ensuring ethical and regulatory alignment is established prior to model deployment.