3020 papers
This paper introduces "Quantum LEGO Learning," a modular hybrid AI framework that decouples a frozen classical feature extractor from a trainable variational quantum circuit to achieve stable optimization, noise resilience, and improved performance on NISQ hardware by separating representation learning from adaptive adaptation.
Edge-XReal is a distributed, hardware-agnostic software pipeline designed to overcome the computational limitations of standalone XR devices by enabling efficient, low-latency 3D Holistic Scene Understanding on edge hardware without sacrificing accuracy.
This paper proposes Attention-guided Local Dynamic Alignment (ALDA), a training-free method that enhances zero-shot vision-language classification by employing attention-driven adaptive multi-scale sampling to reduce background noise and bidirectional iterative propagation on a region-description bipartite graph to model mutual semantic correlations, thereby achieving significant accuracy improvements across diverse benchmarks.
This paper proposes SOAGAN, a second-order attention generative adversarial network that integrates re-identification mechanisms and a U-Net-based covariance attention discriminator to provide both global and pixel-level feedback, thereby significantly enhancing the subjective visual quality of single image super-resolution results.
This paper proposes a hybrid deep learning framework that achieves high accuracy in anemia detection and severity classification by combining DenseNet121-based analysis of RBC smear images with a stacked ensemble model for processing CBC data.
This quantitative study of Indian engineering students and faculty reveals that while Generative AI tools like ChatGPT are increasingly adopted to enhance industry readiness, students utilize a more limited range of tools and report lower satisfaction levels compared to their instructors, highlighting a critical need for improved AI literacy and personalized learning strategies in higher education.
This paper addresses the fragmentation and lack of comparability in empirical studies on LLM-based code generation by synthesizing a review of 35 recent studies into a comprehensive reference framework comprising six core components to enable more systematic, transparent, and reproducible evaluations.
This paper proposes a hybrid deep learning framework that integrates transfer learning, CNNs, and attention mechanisms to overcome the limitations of traditional emotion detection systems, achieving superior accuracy, robustness, and cross-domain adaptability for real-world human-computer interaction applications.
This paper proposes a multimodal AI framework that integrates a custom Mask R-CNN for CTPA clot segmentation, a hybrid LSTM-GRU model for ICU time-series analysis, and an artificial neural network for clinical risk assessment, achieving a Dice Score of 0.88 and 91.81% overall accuracy to improve pulmonary embolism diagnosis and patient risk prediction.
The paper proposes UAMG-RAG, a framework that dynamically adjusts retrieval depth and document granularity based on question complexity and employs uncertainty-guided re-retrieval to enhance reasoning performance and reduce hallucinations, achieving significant improvements on HotpotQA and WikiHow benchmarks.