2833 papers
This paper presents a Retrieval-Augmented Generation (RAG) pipeline that significantly reduces hallucinations and improves factual accuracy in drug-related question answering by grounding LLM responses in a curated pharmaceutical knowledge base, thereby mitigating critical patient-safety risks.
This paper proposes a clinical metadata and semantic explanation-guided multimodal deep learning framework that integrates dermoscopic images with clinical and diagnostic attributes to significantly improve the accuracy and interpretability of skin lesion recognition compared to image-only methods.
This paper proposes Gnet_CAM, a novel human behavior recognition model that integrates visual, skeletal, and audio data via graph neural networks and a hierarchical cross-modal collaborative attention mechanism to achieve robust performance in complex scenarios like occlusion and varying lighting, as demonstrated by its superior accuracy on the NTU RGB+D120 dataset and a self-generated challenging environment dataset.
This paper introduces a self-verification model trained on a dataset that faithfully replicates the authentic format and scoring of the Japanese bar examination, demonstrating that it can exceed the official passing score and outperform complex multi-agent or decomposition-based strategies without altering the original exam structure.
This paper proposes the Evolutionary Kernel-based T-Spherical Fuzzy C-Means (EKTSFCM) algorithm, which integrates T-Spherical Fuzzy Sets and a dual-kernel distance metric optimized by evolutionary techniques to achieve superior clustering accuracy and noise robustness in complex datasets like EMG signals.
This study evaluates the ability of commercial LLMs to generate functional Verilog RTL from high-level specifications, finding that using HLS-C prompts significantly improves correctness over natural language while revealing persistent challenges with simulation errors and limited generalization across variable bit-widths.
This paper proposes the Principal Component Analysis Searched Binary Neural Network (PCA-SBNN), a multi-modal deep learning model that integrates CT image features extracted via TBConvL-Net and normalized clinical data to achieve highly accurate and sensitive early carcinoma detection.
This study demonstrates that large language models can serve as a scalable screening tool for automated reproducibility assessments in social and behavioral sciences, achieving qualitative conclusions comparable to human reanalysts while supporting, rather than replacing, expert judgment in systematic audits.
This paper proposes the Deep Twin-Stream Sparse Spatiotemporal Quantum Diffusion (STQD) framework, which integrates sparse twin-stream transformers, quantum encoding, and quantum diffusion models to effectively detect cyberattacks in smart grids, achieving superior generalization and high F1-scores on diverse benchmark datasets.
This paper introduces DRAgent, an agentic multidisciplinary framework that leverages a new large-scale dataset and a role-based multi-agent system to generate superior, individualized diabetic retinopathy treatment plans by effectively simulating collaboration between ophthalmology and endocrinology specialists.