2982 papers
This paper introduces Weak-Topological Neural Operators (WTNO), a framework that enhances neural operator selection for partial differential equations by coupling state predictors with geometric, topological, and weak-measure certificates to ensure robust physical predictions in scenarios involving interfaces, topological changes, and rare events.
This study provides empirical evidence that iterative language model self-refinement consistently converges toward stable semantic fixed points across diverse architectures and objectives, suggesting an underlying energy landscape where self-improvement acts as an implicit optimization process.
This study evaluates the educational usability of WEKA and Orange for beginner data mining learners through task-based comparisons and student feedback, concluding that Orange is more effective due to its intuitive visual workflow and user-friendly interface.
This paper introduces MLCompete, a scalable, multilingual web platform designed to evaluate machine-learning olympiads through an asynchronous, metric-agnostic pipeline and a secure, two-tier execution environment, demonstrating its robustness and reliability through successful deployment in Romania's National AI Olympiad and international participation.
This paper proposes a Dual-Guidance framework for semi-supervised semantic segmentation that combines an Uncertainty-Aware Dynamic Pseudo-Label Refinement module and a Class-Prototype Contrastive Guidance module to jointly refine predictions and regularize feature representations, achieving state-of-the-art performance on PASCAL VOC 2012 and Cityscapes benchmarks.
This systematic review of 108 studies (2010–2026) analyzes how AI reshapes marketing measurement by proposing a "Measure–Validate–Protect" framework that balances the enhanced predictive power of deep learning and neural media mix models against the causal limitations and accuracy costs imposed by privacy-preserving techniques.
This paper proposes a novel Beam Search-Driven Dual-Path Feature Selection with Weighted Merging (BSDPFS-WM) model that integrates advanced preprocessing, multi-strategy feature selection, and stacked generalization to achieve robust, generalizable, and explainable multi-cancer detection across diverse clinical datasets.
This paper presents a comprehensive benchmark of nine encoder-decoder architectures for automated fracture radiograph captioning on a clinically curated dataset, demonstrating that the vision-language pre-trained BLIP-Base model outperforms other combinations of visual encoders and GPT-2 decoders while providing critical insights into failure modes and architectural selection for low-resource medical imaging tasks.
This paper demonstrates that while the ForesightLM-v2 model successfully learns a stable sentence-level future prediction signal, this representation fails to directly control generation behavior, revealing that its apparent benefits stem primarily from semantic reranking rather than the learned future term itself and highlighting a critical gap between learned representations and calibrated behavioral outcomes in small language models.
This paper proposes a behavior-centric framework that reconstructs Sysmon events into GUID-correlated sequences to improve MITRE ATT&CK technique classification, demonstrating that preserving process-level context outperforms temporal grouping and that a baseline SecureBERT model achieves superior results without explicit class imbalance mitigation.