3020 papers
This paper proposes a novel (n, n) threshold visual secret sharing scheme that utilizes color QR codes as meaningful shares to securely encrypt and losslessly recover privacy images by leveraging color redundancy and XOR operations.
This paper presents an empirical study demonstrating that problem difficulty in code generation benchmarks is a stable, transferable metric driven by specification features (like examples and prompt length) on HumanEval and solution complexity on MBPP, offering critical insights for improving benchmarking, autograding, and educational tool design as aggregate model scores saturate.
This paper presents a pioneering machine learning model that detects ovarian endometriomas from ultrasound images using vision transformers and cross-modality transfer learning, achieving high performance despite data scarcity and imbalance while demonstrating the transferability of low-level features across medical imaging modalities.
Despite the theoretical appeal of viewing hallucinations as dynamical instabilities in large language models, this paper demonstrates that static representations are far more effective for detection, as adding dynamical features provides no statistically significant improvement over simple linear probes.
This paper presents an intelligent root cause analysis framework for Microsoft Fabric and Power BI that utilizes multi-layer telemetry correlation and Kusto Query Language-driven inference to significantly improve incident diagnosis accuracy and speed compared to traditional manual methods.
This study employs design-based research to demonstrate that a customised GPT coding assistant, when integrated with structured prompts and a collaborative human-first workflow, effectively supports deductive coding of classroom dialogue while highlighting that successful human–AI collaboration depends on the dynamic interplay between prompt architecture, workflow sequencing, and the researcher's stance toward AI.
This paper systematically analyzes contextual conditioning in vision-language models across diverse architectures and datasets, revealing that while domain-level prompting is consistently beneficial, full per-image contextual conditioning carries high variance and overfitting risks, with its utility primarily driven by model scale and baseline accuracy.
This paper presents the first production-scale study of AI-assisted course design by mining a privacy-preserving dataset from CourseFactory to extract four workflow surfaces, demonstrating that structural-quality triage and item-to-assignment routing models significantly improve review efficiency and accuracy while confirming that withheld prompt text adds no measurable signal.
This study demonstrates that while successful and failed trajectories in a disrupted world model exhibit distinct recovery dynamics—such as lower path entropy and fewer structural excursions—these full-trajectory patterns cannot be reliably predicted from early prefixes, thereby distinguishing the challenges of regime detection, recovery monitoring, and individual rollout prediction.
This paper introduces H. Dilpriya's Momentum (HDM), a novel multi-strategy optimizer that combines adaptive per-parameter corrections with cosine-annealed scheduling to achieve rigorous convergence guarantees and state-of-the-art gradient alignment, demonstrating superior performance on both ill-conditioned synthetic problems and deep learning benchmarks like MNIST and CIFAR-10.