Zhiling Chen

ScanBot is a novel dataset designed for instruction-conditioned, high-precision surface scanning in robotic systems.

A multi expert framework named MoXpert to enhance the capabilities of multimodal large language models (MLLMs) in indusrial anomaly detection.

An interpretable vision–language detection framework is proposed to enable reliable and real-time PPE compliance monitoring across heterogeneous workplace scenarios.

A multi expert framework named MoXpert to enhance the capabilities of multimodal large language models (MLLMs) in indusrial anomaly detection.

A multimodal RAG framework is proposed to automate anomaly detection in additive manufacturing (AM) without relying on task-specific training data.

A privacy-accountable and explainable decentralized federated learning framework is introduced by integrating HyperDimensional computing with an explicit differential privacy noise accountant.

We propose Echo, a novel multi-expert framework designed to enhance MLLM performance for industrial anomaly detection.

We introduce ScanBot, a novel dataset designed for instruction-conditioned, high-precision surface scanning in robotic systems.

A communication-efficient federated learning framework based on Hyperdimensional Computing is introduced for hierarchical and non-IID smart manufacturing data at the edge.