2786 papers
This study demonstrates that the choice of large language model rater significantly influences measured fidelity and safety compliance in AI-generated biomedical summaries, with different models producing error rates that vary by a factor of four and leading to divergent conclusions about summary quality.
This paper introduces Dec-GRPO, a Byzantine-robust decentralized Group Relative Policy Optimization framework that defends against domain poisoning and reasoning-inflation attacks by integrating reference-logit filtering, reputation-weighted selection, Multi-Krum aggregation, and adaptive length-penalized advantages.
This paper demonstrates that persistent shared state in modular recurrent systems is selectively advantageous rather than universally superior, becoming critically necessary specifically when task-relevant information must both cross modular boundaries and persist after its external availability has ended.
This paper introduces X-CoLA, the first post-hoc explainability framework for contrastive graph anomaly detection, which integrates Gradient Attention Maps into the CoLA model to identify the specific structural connections and feature dimensions driving anomaly decisions without compromising detection performance.
This paper proposes a hierarchical deep reinforcement learning framework that integrates an improved artificial potential field-based dense reward function with the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm to achieve efficient and optimal 3D path planning for multiple UAVs in unknown environments with complex obstacles.
This experimental study demonstrates that differential fuzzing is a practical, language-agnostic approach for efficiently identifying and suppressing equivalent mutants across diverse real-world software projects, achieving near-perfect mutation scores while generating actionable inputs to strengthen traditional test suites.
This paper proposes the Hybrid Copula Bayesian Network (HCBN), a novel algorithm that learns Bayesian network structures from mixed-type data without transformation by integrating Laplacian spectral analysis with a Regular Vine copula framework to achieve superior log-likelihood and model complexity control compared to existing methods.
This paper proposes CWMAN-EEG, a conditionally weighted multi-source adversarial network that addresses cross-subject EEG emotion recognition challenges by separating shared and individualized features and adaptively weighting source domains based on distribution similarity to achieve state-of-the-art performance on the SEED and SEED-IV datasets.
This study demonstrates that the Gated Recurrent Unit (GRU) significantly outperforms both machine learning models and other deep learning architectures in forecasting Vietnam's Robusta coffee export prices during a period of severe structural breaks, while transparently addressing methodological limitations and providing actionable risk parameters for forward contracts.
This paper presents a novel robotic-inspired tri-metaheuristic framework integrated with neuromorphic edge intelligence that optimizes real-time multi-modal biomedical signal processing to achieve high diagnostic accuracy and ultra-low power consumption, enabling continuous 72-hour wearable monitoring and significantly improving clinical decision support for early disease detection.