4157 papers
This exploratory review identifies and consolidates the unclaimed problem of "Design Grounding"—the critical lack of mechanisms to verify that LLM-generated designs correspond to real-world constraints before fabrication—by screening thousands of papers to reveal that only a handful address this structural challenge, which remains fragmented across adjacent fields.
This paper introduces Sovereign-Mohawk, a formally verified hierarchical federated learning architecture that disproves the assumption of deterministic Byzantine resilience, proposes a probabilistic repair using machine-checked Chernoff bounds, and implements a secure, high-performance system with zero-knowledge proofs and differential privacy that maintains accuracy under significant adversarial conditions.
This paper proposes a hybrid deep learning and sparse representation framework that combines YOLOv8 feature extraction with Lasso-based classification to achieve highly accurate, efficient, and interpretable recognition of nine apple leaf diseases, offering a scalable solution for precision agriculture.
This study demonstrates that a reusable, task-free lesion-grounded content-based retrieval system for CT scans can be effectively constructed using patch embeddings from a frozen volumetric foundation model, significantly outperforming chance and descriptor-only baselines in retrieving relevant educational cases without requiring fine-tuning.
This paper proposes the Shell-based Structural-Propagation Influence (SSPI) method, which enhances node ranking in directed complex networks by introducing a new KSOutIn K-shell representation and integrating it with topologically significant features identified through machine learning analysis to achieve superior accuracy and efficiency.
This exploratory study of Qwen2.5-1.5B reveals that the intrinsic dimensionality of internal representations varies non-uniformly across task categories and transformer layers, with reasoning tasks exhibiting lower dimensionality than factual recall in middle layers but converging toward similar levels in the final layers.
This paper presents a hybrid Swin Transformer–ConvNeXt deep learning model, integrated with a Flask-based web interface, that achieves 75.35% accuracy in classifying gastric histopathology images into eight distinct tissue types to assist pathologists in gastric cancer diagnosis.
This paper proposes the MO-AIWOA-XAI framework, which integrates multi-objective adaptive improved whale optimization for feature selection, an Optuna-optimized Extra Trees classifier, and explainable AI techniques to deliver a robust, accurate, and clinically interpretable diabetes risk prediction model validated across multiple datasets.
This paper proposes a residual-guided Boosted-LLL refinement method for GNSS integer ambiguity resolution that strategically selects coordinates with large rounding residuals to improve solution quality and computational efficiency, demonstrating significant gains in objective-gap satisfaction and reduced conversion costs across diverse simulation settings.
This paper presents a real-time, GPU-based procedural framework that uses a shared spatial damage field to drive spatially correlated geometric and optical changes for the interactive appearance modeling of severely damaged hair without requiring dense auxiliary geometry or high-resolution textures.