Xian-Sheng Hua

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning

CARE: Contextual Affinity Exploration with Twin Concordance for Graph Out-Of-Distribution Detection

PURE: Prototypical Mutual Prompting Enhancement for Zero-shot Text-attributed Graph Learning

Towards Efficient Fairness Image Retrieval with Disentangled Information Suppression

Prototypical Environment-aware Proxy with Coordinated Optimization for Multi-agent Dynamics Modeling

LIGHT: LLM-guided Graph Expert Routing for Semi-supervised Domain Generalization

EIBench: Assessing the Emotion Interpretation ability of Vision Large Language Models