898 papers
This paper introduces a scenario-driven evaluation methodology to compare GenAI-generated test suites against human-written ones, revealing that while direct prompts recover more expected behaviors, ideate-then-implement strategies yield more efficient suites with fewer duplicates, and ideate-only approaches effectively uncover additional test scenarios.
This paper introduces QUAMET, a novel approach that combines structural and semantic analysis to establish software metrics and detect six types of code smells in quantum programs, validated on a refined dataset of 4,102 real-world Qiskit projects.
This paper proposes a Conscious Infrastructure Neural Systems (CINS) framework that utilizes household-burden data rather than traditional infrastructure metrics to significantly improve the fairness and accuracy of AI-driven detection of water insecurity in Hyderabad's informal settlements, thereby bridging the gap between lived experiences and institutional decision-making.
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.