2731 papers
The paper proposes MARS-Agent, a retrieval-augmented multi-agent framework featuring a Dual-Triggered RAG mechanism and a Verify-Adapt-Replan Loop to enable closed-loop, self-correcting deliberation for enhancing cross-border e-commerce supply chain resilience against heterogeneous disruptions.
This paper introduces a memory-efficient contrastive learning framework that eliminates the quadratic memory bottleneck of dense similarity matrices by streaming computations and dynamically selecting a fixed budget of hard negatives, enabling significantly larger batch sizes on constrained hardware while maintaining optimization effectiveness.
This paper presents a concern-centric empirical evaluation of JNI code smells using LLM-assisted analysis of 8,207 commits across 15 open-source projects, revealing that existing smell definitions cover only 36.5% of developer maintenance concerns and proposing three new smell definitions to address the identified gaps.
This study demonstrates that while controlled schema and representation drift in Android forensic parsers like ALEAPP frequently lead to incomplete or misinterpreted evidence, the tools fail to provide examiner-visible diagnostics of these failures, highlighting the critical need for validation frameworks that prioritize failure transparency alongside recovery accuracy.
This paper demonstrates that the short causal depthwise convolution in linear-attention and state-space models imposes a hard, non-degradable limit on which parts of a query can condition retrieval, causing the model to confidently generate wrong answers when critical information falls outside this narrow window, a failure that persists in shallow layers but can be mitigated by deeper architectures or larger kernels.
This paper proposes a robust visual relocalization framework for humanoid robots that integrates a Mixture-of-Experts architecture with hierarchical knowledge distillation to achieve accurate, stable, and efficient 6-DoF pose estimation under challenging conditions like abrupt viewpoint changes and self-occlusion.
This paper investigates how modeling choices in Deep Reinforcement Learning affect scheduling policies for the Flexible Job-shop Scheduling Problem, demonstrating that integrating Constraint Programming-derived optimality bounds and expert demonstrations into a multi-agent framework significantly improves reward design and accelerates convergence to achieve superior, real-time scheduling performance.
This study proposes a hierarchical network with word-level attention and ratio-based weighting for Arabic aspect-based sentiment analysis, demonstrating that using CamelTools embeddings significantly outperforms Word2Vec across multiple datasets in terms of accuracy and F1-score.
This paper presents a systematic empirical study demonstrating that fine-tuning the Wav2Vec2-XLSR-53 pretrained Transformer model on a 870-hour Quranic dataset with Arabic text without diacritics significantly reduces Word Error Rates and improves training efficiency compared to baseline systems.
This paper employs bibliometric and knowledge mapping analyses of Web of Science data (2000–2025) to trace the evolution of AI-enabled accessible design from engineering feasibility to contextual usability, identifying core research pillars, emerging hotspots like generative AI and XR standardization, and proposing a comprehensive User–Scenario–Technology framework for future sustainable governance.