2890 papers
This paper proposes a task-aware graph reinforcement learning framework that compresses reusable reasoning contexts in black-box LLMs by training a lightweight policy to make extractive keep-or-drop decisions on graph-structured reasoning units, achieving significant input-cost savings while preserving reasoning accuracy.
The paper introduces EquiEwald, a novel SO(3)-equivariant neural interatomic potential that extends Ewald summation to reciprocal space to effectively capture long-range electrostatic and polarization interactions while preserving orientation-dependent information, thereby significantly improving accuracy and data efficiency in machine-learning models for periodic and aperiodic systems.
This paper proposes a stochastic multiscale theory grounded in nonequilibrium physics to explain the mechanistic origin of language model scaling laws, modeling training as a scale-dependent biased random walk that yields analytically derived power laws for loss versus data and model size while identifying a bifurcated two-phase dynamics of context compression and frontier absorption.
This paper introduces the Knowledge-Constrained Reasoner, a novel approach that employs a single alignment phase to internalize essential reasoning capabilities into Large Language Models, thereby ensuring the rigorous and correct utilization of external knowledge for question answering and bridging the reliability of traditional expert systems with the flexibility of non-parametric continuous learning.
This study presents an explainable, Weighted Mixture of Experts-based decision-support system optimized by dual metaheuristics that achieves high accuracy in predicting mental health severity among engineering and medical students in low-and-middle-income countries while revealing distinct risk factors across disciplines.
This paper identifies and addresses the "regularization-monitoring dilemma," a fundamental conflict where the marginal Gaussianization required for stable training of self-supervised world models (like JEPAs) inadvertently suppresses the discriminative geometric structures necessary for reliable inference-time anomaly detection.
This paper presents a systematic review of deep convolutional neural network architectures, datasets, and preprocessing strategies for automated melanoma detection, highlighting their high accuracy, current challenges like class imbalance and interpretability, and future directions such as federated learning and hybrid models.
This paper introduces SciCFM, a causal foundation model framework that demonstrates intervention-rich cross-task pretraining significantly improves treatment-effect estimation in extremely small-data, complex causal regimes, though it remains less effective than direct regularized estimators in low-dimensional settings.
This review article argues that while Large Language Models demonstrate impressive cognitive capabilities, the future advancement of AI requires bridging the gap to multimodal intelligence through embodied experiences, hierarchical modulation, and autonomous reinforcement to overcome the inherent limitations of language-only systems.
This paper proposes a Front Propagation–Based Clustering framework that unifies adaptive and arrival-time algorithms to form clusters through competitive propagation dynamics on a neighborhood graph, effectively handling nonconvex structures, varying densities, and noise without relying on global optimization or sensitive thresholds.