Heng Tao Shen

Factually consistent prompting with LLMs for cross-lingual dialogue summarization

A2VAD: Attribute-augmented prompt learning for weakly supervised video anomaly detection

Geometric Gradient Divergence Modulation for Imbalanced Multimodal Learning

VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization

Resisting Noise in Pseudo Labels: Audible Video Event Parsing With Evidential Learning