2661 papers
This paper presents an Edge-AI shared-control framework for teleoperated assistive robots that utilizes a Hailo-8L NPU to concurrently execute an Adaptive Neuro-Fuzzy Inference System and a YOLOX-S detector, fusing their outputs to significantly reduce collision rates and emergency interventions while maintaining full local operation.
This paper proposes AdaHet-Clust, a lightweight distributed clustering algorithm that utilizes adaptive thresholding to dynamically select cluster heads based on local energy conditions in heterogeneous IoT networks, thereby significantly extending network lifetime and reducing control overhead compared to existing methods.
This paper presents an organizational transformation framework and narrative synthesis that identifies five interdependent domains and six measurable dimensions to guide the sustainable implementation of embodied AI agents in urban healthcare systems, moving beyond simple technology adoption toward deep sociotechnical integration and institutional capability building.
Tessera is a vendor-free, lossless-first session compression proxy that reduces token costs and latency for long-horizon LLM agents by employing a three-tier memory system to deterministically rewrite conversation history while preserving verifiable access to original data via the Model Context Protocol.
This paper presents a human-verified, AI-assisted workflow for interpreting static and dynamic analysis of WhiteSnake, Donex, and Emotet malware samples within an isolated FLARE VM environment, using archived undergraduate project data to identify specific behavioral indicators while explicitly noting the limitations regarding unconfirmed exfiltration, encryption, and stable process capture.
This study demonstrates that the composition of candidate sentence pools in chest X-ray retrieval systems significantly impacts both finding-level retrieval performance and cross-model agreement on difficulty, suggesting that observed consensus on retrieval challenges may be driven more by evaluation pool bias than by intrinsic model capabilities.
This paper introduces LDIF, a novel PyTorch-based neural architecture that models hidden state evolution using symmetric and skew-symmetric interaction fields combined via a response-conditioned gating mechanism and adaptive low-rank spectrum, demonstrating superior performance on both static and sequential datasets compared to traditional machine learning and deep learning baselines.
This study presents a machine learning system that utilizes public Unaccompanied Alien Children records to forecast HHS care placement demand, achieving a MAE of 15.22 with a Gradient Boosting model and deploying a 30-step projection via Streamlit.
This survey provides a comprehensive review of quantum and quantum-inspired image segmentation methods, contextualizing them within the broader evolution of segmentation research by categorizing existing approaches, analyzing their computational principles and challenges, and identifying current trends and future directions in the field.
This study presents a secondary analysis of public datasets to investigate how cross-subject variability impacts the generalization of EEG-EMG fusion models for motor intention decoding, aiming to quantify performance degradation across different fusion strategies and evaluate the potential of transfer learning to mitigate these inter-individual differences.