2787 papers
This paper demonstrates that while outcome-aware reasoning allocation is theoretically valuable, its practical implementation in multi-robot systems is severely limited by the intrinsic sparsity of high-value opportunities, leading to classifier collapse in learned routers and failing to produce genuine emergent collective cognition through delegation or specialization.
This paper proposes a two-layer hybrid Imperialist Competitive Algorithm combined with local search to simultaneously optimize customer-to-depot assignments and vehicle routes for the Multi-Depot Vehicle Routing Problem, achieving competitive results with gaps within approximately 2% on standard benchmarks.
This paper empirically demonstrates that channel pruning enhances noise-robust pedestrian detection only in small-data, high-redundancy regimes by acting as a regularizer, while failing to generalize across diverse datasets and offering only modest computational savings.
This paper proposes a hybrid CNN–GRU deep learning framework enhanced by mRMR feature selection to effectively detect major depressive disorder from EEG signals, achieving a mean accuracy of 96.74% on the MODMA dataset while highlighting the need for further validation on diverse clinical data.
This paper introduces Mechanistic Circuit Tracking, a modular framework that combines direct logit attribution, causal activation patching, and ablation techniques to trace the emergence of attention circuits during pre-training and quantify their causal robustness via a new Circuit Stability Index for enhancing AI safety and alignment.
This study evaluates 14 large language models on smart contract vulnerability detection, revealing that model selection is more critical than prompting strategies or increased inference-time computation, as larger frontier models demonstrate superior reliability while smaller models and extended reasoning techniques can degrade performance.
This paper introduces Perceive AI, a novel end-to-end framework for automated short answer grading that leverages a dual-head parametric prototype architecture and adversarial consistency guardrails to achieve robust, prompt-aware scoring while effectively filtering off-topic submissions.
This paper introduces the Spectral Basis Interpretable Unit (SBIU), a classically inspired, quantum-mechanics-motivated neural module that uses learned orthogonal projections to achieve universal function approximation and unsupervised regime discovery with high interpretability and competitive performance on both synthetic and real-world clinical datasets.
This paper introduces Dictionary-KAN (DKAN), a machine-verified architecture that resolves the optimization paradox of Kolmogorov-Arnold Networks by employing complex-coefficient RBF dictionaries and discrete hierarchical refinement to achieve superior multivariate regression, PDE coefficient recovery, and hardware-efficient interpretability while avoiding the memory and convergence issues of continuous spline-based KANs.
CONCORDAT is a cross-silo federated learning framework that enables trustworthy, privacy-preserving multimodal autism research by integrating heterogeneous and incomplete health data across multiple sites while simultaneously addressing challenges in missingness, differential privacy, and subgroup equity.