3031 papers
This research proposes a machine learning framework that leverages ensemble methods and explainable AI to predict data warehouse failures up to 15 minutes in advance by analyzing system metrics, thereby reducing downtime through proactive anomaly detection and automated root cause analysis.
Through a comprehensive Monte Carlo investigation, this paper demonstrates that while training sample size is the primary driver of SHAP attribution fidelity, common class imbalance treatments often distort feature rankings and magnitudes, leading the authors to recommend avoiding rebalancing in favor of class weighting when SHAP interpretability is a priority.
This paper introduces CLHA, a cross-layer Hessian aggregation method for post-training quantization of weight-shared Mixture-of-Experts transformers that minimizes total reconstruction error by combining Hessian statistics across shared layers, significantly outperforming existing per-layer calibration approaches while also addressing critical implementation pitfalls in Hessian estimation.
This paper introduces the Agentic Annotation Language (AAL), a novel in-band annotation system that enables Just-In-Time context injection for autonomous agents, significantly reducing token consumption and context pollution compared to traditional global rule files while maintaining high compliance with domain-specific constraints.
This paper presents the first cross-dataset generalization study for Urdu fake news detection, revealing that a model trained on the Ax-to-Grind dataset fails catastrophically when applied to the Notri-Fact dataset due to a systematic length confound in the training data that induces shortcut learning, thereby highlighting critical flaws in current dataset construction and evaluation practices for low-resource NLP.
The paper introduces the Cascade Progressive Distilled Network (CPDN), a novel deep learning framework that leverages knowledge distillation from a CatBoost teacher to overcome optimization stagnation and non-differentiability issues, achieving state-of-the-art classification performance on heterogeneous tabular data.
This paper demonstrates that a centralized training with decentralized execution (CTDE) approach using QMIX significantly outperforms independent Q-learning (IQL) and non-RL baselines in coordinating electric vehicle charging within smart cities, achieving higher acceptance rates and success probabilities while effectively managing partial observability and traffic dynamics.
This systematic review of 445 recent studies (2024–2026) identifies CNN-Mamba hybrids as the most efficient architecture for medical imaging due to their linear computational complexity, while highlighting critical challenges like spatial information loss and memory consumption that must be addressed through native 3D blocks to enable clinical integration.
This paper proposes and evaluates a hybrid intrusion detection framework that combines supervised learning (Random Forest and XGBoost) with an LSTM Autoencoder-based anomaly detection model on aligned IoT and cloud datasets, demonstrating that while this approach significantly improves detection robustness and recall for unseen attacks, it necessitates a trade-off with increased false positives and reduced precision.
This paper proposes YOLOv10n-FBD, a lightweight cherry tomato maturity detection model that integrates CCFM feature fusion, PSA-BiFormer attention, and a C2f-Dual strategy to achieve high precision (94.3% mAP) and speed (369 FPS) while significantly reducing model size and computational complexity compared to existing methods.