2787 papers
This survey explores the potential of Diffusion Language Models as a non-autoregressive alternative for mobile edge agentic AI, analyzing their foundations, resource-efficient applications, and system-level challenges to enable flexible quality-latency trade-offs and robust performance under edge constraints.
This paper introduces QiboAgent, an open-source framework that combines Retrieval-Augmented Generation and autonomous agentic workflows to enable lightweight Large Language Models to outperform proprietary baselines in generating high-precision Quantum Computing code, reducing hallucinations and automating complex software engineering tasks for the Qibo middleware.
This paper introduces SAGE, a self-adaptive multi-agent framework that significantly improves the reliability of generating runnable multi-file projects by employing a closed-loop MAPE-K control cycle to iteratively execute code, analyze runtime errors, and perform self-repair, thereby achieving a statistically significant increase in success rates compared to single-pass generation.
The paper introduces MedMamba3D, a novel hybrid architecture that integrates a linear-complexity 3D Mamba encoder, a deterministic U-Net branch, and a conditional diffusion model guided by uncertainty estimation to achieve state-of-the-art 3D medical image reconstruction with superior anatomical consistency, robustness to missing data, and improved downstream segmentation performance.
This paper presents a confidence-guided neuromorphic framework that leverages training-induced diversity in memristive nanowire networks to dynamically route inputs through a cascaded reservoir cascade, achieving significant energy and resource savings while maintaining high classification accuracy.
This paper proposes DOA-EDS, a two-stage framework combining an Obstacle-Aware Adaptive Large-Neighborhood Search for edge server placement and a feasibility-masked Proximal Policy Optimization for dynamic task scheduling, to significantly enhance network throughput and reduce latency in Industrial IoT environments plagued by severe signal blockages from metallic obstacles.
This paper presents DKSE, a Rust-based tool that leverages large language models to automatically convert unstructured software requirement documents from the Chinese banking sector into machine-readable, provenance-tracked ontologies, demonstrating high accuracy and practical utility for downstream tasks like test generation and knowledge graph construction.
This paper empirically demonstrates that while federated unlearning methods are computationally efficient, they often induce significant stability and fairness side-effects for remaining clients under non-IID data, revealing a critical trade-off between cost, forgetting completeness, and equitable model performance that aggregate metrics fail to capture.
This paper introduces the Multi-Level Regulation Engine (MLRE), a socially adaptive Intelligent Tutoring System architecture designed to regulate learning across individual, dyadic, and group levels in heterogeneous collaborative settings, which has been partially validated through offline modeling and simulations to improve participation equity while proposing a future field study for comprehensive evaluation.
This paper introduces BSPAL, a transactional prequential adaptation framework for visual anomaly localization that ensures causal integrity and bounded state under unknown stream contamination, while explicitly disclaiming benchmark performance improvements due to a post-seal audit revealing data leakage in the underlying VisA dataset.