4157 papers
This study evaluates the ChromaPose-MIL architecture for autism classification using public skeleton videos from 160 children, finding that while the model is computationally feasible and achieves modest performance (AUC 0.605), the limitations of small participant cohorts and the need for independent replication preclude its current use for clinical screening.
FORGE is a principled framework that enhances Retrieval-Augmented Generation by integrating an uncertainty-driven adaptive retrieval controller, a reliability-weighted evidence fusion network, and a token-level grounding verification module to significantly reduce hallucinations and computational costs while achieving state-of-the-art performance across multiple benchmarks.
This paper demonstrates that leveraging morphological lexicons as weak supervision during subword vocabulary learning improves morpheme-boundary alignment in tokenizers while simultaneously enabling a bias-aware evaluation protocol to validate these gains.
This study proposes an automated banana ripeness classification system using deep learning models, specifically demonstrating that the Swin Transformer Tiny architecture achieves high accuracy (86.78%) in categorizing Moira bananas into five stages while utilizing Explainable AI techniques to ensure prediction interpretability.
This paper presents a compact, 5.01M-parameter CNN enhanced with Squeeze-and-Excitation channel attention that achieves 88.55% accuracy on a balanced 24-class clinical skin disease dataset, demonstrating significant performance gains over baseline models while acknowledging specific evaluation limitations prior to clinical deployment.
This paper establishes a controlled empirical benchmark on the OBWX dataset to evaluate 14 vision architectures for high-cardinality ancient Chinese ideograph recognition, revealing that EfficientNetV2-S achieves the highest accuracy while demonstrating that model size does not correlate with performance, tail classes drive the majority of errors, and MaxViT-T exhibits superior robustness against noise.
This paper reconciles contradictory findings on hallucination propagation in multi-agent LLM systems by demonstrating that six distinct formalizations are projections of a single process governed by error correlation and independent verification channels, revealing that propagation depends on structural metrics rather than topology alone and that increasing initial agent diversity can paradoxically amplify false claims.
This paper proposes an auditable, multi-LLM evidence synthesis framework that resolves the contested origins of Turpan's Karez system by quantitatively evaluating competing hypotheses, ultimately identifying the Central Asia Introduced hypothesis as the most supported explanation based on a comprehensive analysis of fragmented multilingual literature.
This paper proposes and validates an online calibration procedure that dynamically adjusts account-specific risk sensitivity parameters based on local behavioural distances in streaming banking transactions, demonstrating that this adaptive approach effectively tailors risk evaluation to individual account regularity without requiring parametric assumptions or increased memory.
The paper introduces LungColonCancerPred-NN, a compact triple-branch neural network that achieves state-of-the-art 99.25% accuracy in five-class lung and colon histopathology classification by addressing data leakage in the LC25000 benchmark through a rigorous augmentation-family-based evaluation protocol.