2661 papers
This paper introduces AMODD, an ML-augmented pipeline that leverages lightweight semantic embeddings to deduplicate redundant document sections and cluster graph entities, significantly reducing LLM token consumption and latency for knowledge graph construction while maintaining high retrieval quality.
This paper presents the development and pilot validation of an AI-assisted self-practice system for the erhu that integrates optical music recognition, pitch tracking, and dynamic time warping to provide score-aligned feedback, demonstrating strong correlation with expert ratings and high usability among conservatory students.
This paper introduces "Possibility Ethics," a conceptual-computational framework that evaluates sociotechnical systems by quantifying their impact on ethically admissible future opportunities through a novel metric called Option Entropy, implemented in the Omega-PE toolkit to reveal distributional opportunity losses often missed by aggregate measures.
This paper proposes a novel Reinforcement Learning-assisted A-Teams hyper-heuristic framework that significantly accelerates real-time route optimization for collaborative UAV-UGV systems, delivering near-optimal solutions 30–70% faster than existing methods while effectively adapting to dynamic environmental changes.
The paper proposes JK-DHGNN, a dual-view framework integrating a Top- dynamic hypergraph generator, Jacobi spectral filtering, and a Jacobi polynomial-based classifier to effectively detect financial and e-commerce fraud by modeling both pairwise relations and higher-order affiliations, achieving superior performance on YelpChi and Amazon datasets while demonstrating dataset-dependent component efficacy.
This paper introduces a lightweight, post-hoc Boundary-Refinement Module (BRM) that significantly improves biomedical named entity recognition accuracy by correcting boundary errors without degrading existing correct predictions, thereby enhancing downstream relation extraction stability while requiring minimal computational resources.
This paper introduces ChaosEntropyGate v2 (CEG-2), a bounded, learnable uncertainty gating mechanism paired with a feature augmentor that, while modestly improving deep learning-based malware detection in specific regimes and correcting previous instability issues, ultimately confirms that tuned tree ensembles remain the most robust and cost-effective solution for the task.
This paper evaluates and compares the performance of Random Forest, XGBoost, and Temporal Convolutional Network models for predicting the remaining useful life of lithium-ion batteries, demonstrating their practical deployment and effectiveness on the Coral Dev Board for predictive maintenance in electric vehicles.
The paper introduces APOSM, an active-learning framework that enhances small-molecule design by training a graph neural network surrogate on pairwise molecular comparisons rather than absolute scores, thereby significantly improving target attainment and sampling efficiency in noisy screening regimes.
This paper introduces InterGRACE, an Integrated Gradient-guided adversarial framework that generates clinically meaningful counterfactual explanations for 12-lead ECGs by targeting decision-relevant features like the ST segment and T wave, thereby enhancing the interpretability of AI models for myocardial infarction detection.