2931 papers
This study introduces an uncertainty-aware evaluation framework based on the Theory of Expertons to assess topic models in specialized tourism corpora, demonstrating that LLM-enhanced BERTopic outperforms traditional and neural approaches while revealing that decoding temperature significantly impacts interpretability.
This paper proposes a general, low-cost post-optimization meta-heuristic that enhances multi-start algorithms by iteratively generating and improving offspring from an elite set of solutions, successfully improving the best-known results for all 48 tested planar p-median instances within comparable run times.
This paper proposes a robust score-based generative modelling framework using Tsallis–Gaussian perturbations and a dual-head neural architecture to effectively mitigate the impact of heavy-tailed data and contamination while maintaining competitive generative performance.
This paper proposes a framework for industrial anomaly detection that combines a frozen DINOv3 backbone with a Multi-view Patch Inference strategy to overcome boundary information loss and a Multi-scale Reconstruction Fusion Transformer to model normal feature distributions, achieving state-of-the-art performance on multiple benchmark datasets.
This paper proposes LAR-Net, a lightweight adaptive receptive field network built on the LitePT backbone that dynamically adjusts to local geometric complexities to achieve high-precision point cloud segmentation of pharmaceutical deposits on reactor inner walls, thereby overcoming the limitations of conventional inspection methods and enabling automated intelligent cleaning.
This paper introduces KinderMM-Cap, a specialized multimedia captioning system for early childhood education that leverages the ECAC benchmark and a novel reward-conditional hybrid training framework (RSRS) to significantly improve the accuracy of generating educationally meaningful captions for complex classroom scenes and teaching toys.
This paper proposes and rigorously evaluates TW-DP-FedAvg, a privacy-preserving federated learning framework tailored for rural Tamil Nadu's medical insurance sector, demonstrating that while differential privacy incurs a measurable accuracy cost compared to centralized training, the approach remains statistically equivalent and viable under India's new data protection regulations.
This paper introduces a novel mothership and multi-drone routing problem for spatial marine management, proposing a metaheuristic solution that achieves near-optimal results with significantly reduced computation time compared to exact methods, thereby enabling practical-scale coordination for applications like coral reef restoration.
This paper introduces Meta-PPO, a lightweight meta-control framework that dynamically adjusts PPO hyperparameters online based on training statistics, demonstrating improved performance, efficiency, and robustness across multiple continuous-control benchmarks compared to standard PPO.
This paper presents HCLM-SmartTex, an explainable and frugal AI framework that distinguishes genuine physiological anomalies from smart-textile sensor degradation and artifacts by optimizing for human-centered decision costs rather than raw accuracy, utilizing a synthetic simulator for training and achieving high reliability with minimal computational footprint.