2931 papers
This paper evaluates the feasibility of NVIDIA's RTX Neural Shaders for real-time fluid rendering, demonstrating that while neural networks successfully approximate pixel-level BSDFs at high frame rates, significant framework limitations currently prevent their effective deployment for vertex displacement tasks.
This study proposes and validates a partial-correctness and progress-aware formulation for early success prediction in programming practice, demonstrating that it significantly outperforms traditional binary and ordinal approaches by more effectively capturing learner progression and enabling targeted instructional support.
This systematic review of 122 studies (2015–2025) demonstrates that machine learning models, particularly ensemble and hybrid approaches integrated with non-destructive sensing technologies, significantly enhance post-harvest management of perishable fruits by improving quality assessment and loss reduction across the entire supply chain, while highlighting the need for standardized datasets and real-world validation to overcome current deployment challenges.
This paper introduces Validation-Aligned Coreset Selection (VACS), a method that selects the optimal class-balanced subset selector by evaluating a portfolio on internal validation splits, demonstrating that repeated validation can significantly improve few-shot classification accuracy under extreme budget constraints, though it does not universally surpass the best static selection rules.
This paper proposes a lightweight two-stage framework utilizing YOLO11s-seg for instance-level candidate generation and YOLOv8n-cls for hard-negative and occlusion-aware classification, achieving high harvesting decision accuracy and zero false harvest rates in complex oil palm plantation environments.
This paper proposes a neuro-symbolic fuzzy rule-based framework that integrates deep learning-based dermoscopic attribute estimation with automatically extracted clinical rules to improve melanoma classification accuracy and interpretability compared to image-only deep learning approaches.
This study demonstrates that analyzing the structural characteristics of a paper's reference list at the time of publication—specifically self-citation rates, the spread of reference years, and the recency of cited literature—can significantly improve the early detection of future retraction risks before any post-publication evidence emerges.
This paper proposes an Explainable TabNet Framework that leverages attention-based deep learning and SHAP values to accurately, robustly, and fairly predict remote employee performance using a large-scale dataset, outperforming traditional baseline models while ensuring transparent and equitable human resource decision-making.
This study demonstrates that advanced Large Language Models, specifically BioClinicalBERT and BioGPT, achieve high accuracy (98% F1 score and accuracy) in automatically identifying causative drugs for adverse events from social media and drug review datasets, offering a promising real-time solution for drug safety monitoring.
This paper proposes a Distributed Consent Based Sociocracy 3.0 governance framework that integrates S3 principles with ROS 2 architecture to enhance ethical, transparent, and scalable coordination in autonomous multi-robot systems, demonstrating significant improvements in conflict reduction, debuggability, and consent success rates through evaluation on the DROID 100 dataset.