Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep Learning
该研究提出一种基于深度学习的直接局部到全局学习框架，用于从衍射测量中重建全视野相位图，无需迭代优化，解决了传统方法计算成本高的问题。
0 citationsRead paper
Selected work
Representative Papers
Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning
This study addresses data heterogeneity, label imbalance, and communication bottlenecks in federated ECG classification by proposing a novel Hybrid Quantum-Inspired Kolmogorov-Arnold Network (QIKAN) integrated with the FedAvg framework. This approach effectively enhances robustness and parameter efficiency for cross-client arrhythmia classification while preserving privacy. Experimental results demonstrate that, compared to traditional MLPs, QIKAN reduces model parameters by 44.81% and communication overhead by 36.41%, while significantly improving classification metrics across most categories. Consequently, this work achieves efficient and precise distributed biosignal learning under strict privacy constraints, offering a promising solution for resource-constrained federated healthcare applications.
0 citationsRead paper
An Intelligent AI glasses System with Multi-Agent Architecture for Real-Time Voice Processing and Task Execution
This work addresses the challenges of achieving low-latency, multilingual voice interaction and cross-platform task automation for smart glasses in real-world scenarios. The authors propose an edge-oriented dual-agent collaborative architecture: Agent 01 handles multilingual speech recognition, while Agent 02 leverages a local large language model integrated with the MCP protocol, retrieval-augmented generation (RAG), and external tools to perform task reasoning and execution. The system supports RTSP audio-video streaming, eye-tracking data acquisition, and RabbitMQ-based remote communication, enabling end-to-end real-time voice command understanding and cross-platform task orchestration. Experimental results demonstrate the feasibility of deploying such a sophisticated AI agent system on resource-constrained wearable devices, significantly enhancing both interactive efficiency and multilingual adaptability.
0 citationsRead paper
Intelligent Singularity Avoidance in UR10 Robotic Arm Path Planning Using Hybrid Fuzzy Logic and Reinforcement Learning
This study addresses the issue of instability or potential damage in UR10 robotic arms caused by kinematic singularities during path planning. To mitigate this, the authors propose an adaptive obstacle-avoidance method that integrates fuzzy logic with reinforcement learning. Singular configurations are detected in real time using manipulability measures and condition numbers, and a fuzzy decision mechanism combined with a stable reinforcement learning policy dynamically generates safe trajectories. Notably, this work is the first to embed a fuzzy logic–based safety mechanism within a reinforcement learning framework, enabling efficient avoidance of singular postures. Experiments conducted via PyBullet simulation and the URSim interface demonstrate a 90% success rate in reaching target positions while consistently maintaining a safe distance from singular configurations.
0 citationsRead paper
Recent publications
Latest Papers
Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep Learning
该研究提出一种基于深度学习的直接局部到全局学习框架，用于从衍射测量中重建全视野相位图，无需迭代优化，解决了传统方法计算成本高的问题。
0 citationsRead paper
Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning
This study addresses data heterogeneity, label imbalance, and communication bottlenecks in federated ECG classification by proposing a novel Hybrid Quantum-Inspired Kolmogorov-Arnold Network (QIKAN) integrated with the FedAvg framework. This approach effectively enhances robustness and parameter efficiency for cross-client arrhythmia classification while preserving privacy. Experimental results demonstrate that, compared to traditional MLPs, QIKAN reduces model parameters by 44.81% and communication overhead by 36.41%, while significantly improving classification metrics across most categories. Consequently, this work achieves efficient and precise distributed biosignal learning under strict privacy constraints, offering a promising solution for resource-constrained federated healthcare applications.
0 citationsRead paper
An Intelligent AI glasses System with Multi-Agent Architecture for Real-Time Voice Processing and Task Execution
This work addresses the challenges of achieving low-latency, multilingual voice interaction and cross-platform task automation for smart glasses in real-world scenarios. The authors propose an edge-oriented dual-agent collaborative architecture: Agent 01 handles multilingual speech recognition, while Agent 02 leverages a local large language model integrated with the MCP protocol, retrieval-augmented generation (RAG), and external tools to perform task reasoning and execution. The system supports RTSP audio-video streaming, eye-tracking data acquisition, and RabbitMQ-based remote communication, enabling end-to-end real-time voice command understanding and cross-platform task orchestration. Experimental results demonstrate the feasibility of deploying such a sophisticated AI agent system on resource-constrained wearable devices, significantly enhancing both interactive efficiency and multilingual adaptability.
0 citationsRead paper
Intelligent Singularity Avoidance in UR10 Robotic Arm Path Planning Using Hybrid Fuzzy Logic and Reinforcement Learning
This study addresses the issue of instability or potential damage in UR10 robotic arms caused by kinematic singularities during path planning. To mitigate this, the authors propose an adaptive obstacle-avoidance method that integrates fuzzy logic with reinforcement learning. Singular configurations are detected in real time using manipulability measures and condition numbers, and a fuzzy decision mechanism combined with a stable reinforcement learning policy dynamically generates safe trajectories. Notably, this work is the first to embed a fuzzy logic–based safety mechanism within a reinforcement learning framework, enabling efficient avoidance of singular postures. Experiments conducted via PyBullet simulation and the URSim interface demonstrate a 90% success rate in reaching target positions while consistently maintaining a safe distance from singular configurations.
0 citationsRead paper