833 papers
The paper introduces GRACE, a novel large-language-model framework that iteratively refines hypotheses and evidence to automatically discover the optimal number of clinical subgroups in heterogeneous, multimodal data without requiring prior specification of cluster counts, as validated across Long COVID and Parkinson's disease cohorts.
This survey systematizes the fragmented landscape of autonomous research by introducing a multi-axis framework for 56 systems and their evidence reliability, revealing a critical gap between the ability to generate research artifacts and the lack of robust verification mechanisms to defend them before release.
This paper introduces MOGA-NAS, a multi-objective evolutionary algorithm that effectively balances predictive performance and model compactness for clinical tabular classification by simultaneously maximizing F1-scores and minimizing parameter counts, resulting in significantly smaller models with superior or comparable accuracy across five public benchmarks.
This paper proposes a federated learning security scheme that combines threshold Paillier homomorphic encryption with a data quality-based selective decryption mechanism and ECDSA signatures to effectively defend against inference and tampering attacks while improving training efficiency by approximately 10%.
This paper presents a hybrid deep learning framework that integrates CNN, Transformer, and BiLSTM layers with multi-feature fusion to achieve state-of-the-art speech emotion recognition performance across five benchmark datasets, demonstrating robust generalization and significant accuracy improvements over existing baselines.
This study proposes the StackPip Framework, a hybrid ensemble learning approach utilizing a Stacking Classifier on the SDSS DR-17 dataset, which achieved a 98% accuracy in classifying celestial objects into galaxies, stars, and quasars, outperforming various individual machine learning models.
The paper proposes BayesMem-CD, a Bayesian memory-based framework that integrates probabilistic inference with temporal regularization to achieve uncertainty-aware dynamic community detection, effectively balancing stability against noise with sensitivity to genuine structural changes.
The paper introduces AraCoT-Agent, a framework that distills structured reasoning capabilities into Arabic models using a high-quality, filtered dataset (AraCoT) and a reward-weighted training objective, achieving a 55.7% relative improvement on the new AraAgent-Bench and significantly narrowing the reasoning gap between Arabic and English LLMs.
The paper proposes CoDeR, a continuous degradation representation learning framework that integrates a Dual-axis Coupled Transformer Encoder and a Time-Aware Contrastive Learning module to overcome the limitations of fragmented representations in existing deep learning models, thereby achieving more accurate Remaining Useful Life predictions for aero-engines.
This systematic review evaluates the suitability of Kolmogorov-Arnold Networks (KANs) for time series analysis, concluding that while they excel in interpretable, short-horizon forecasting with smooth patterns across various domains, their current application is limited by heterogeneous evidence, challenges in handling long-range dependencies and regime shifts, and a need for standardized benchmarks and rigorous interpretability validation.