Yifan Wang

Assistant Professor@University of International Business and Economics·中国·OpenReview

研究方向

Deep Learning · Data Mining · Graph Representation Learning · Graph Neural Networks · Disentangled Representation Learning · Recommender Systems · Natural Language Processing (especially text generation) · Large Language Models

Yifan Wang

Compactness and Consistency: A Conjoint Framework for Deep Graph Clustering

Automatic Instance Selection with Genetic Updating for Few-shot LLM Jailbreak

LANO: Large Language Models as Active Annotation Agents for Open-World Node Classification

ETA: Dual Evidence-Aware Uncertainty Learning for Open-Set Graph Domain Adaptation

Dynamic Multi-sample Mixup with Gradient Exploration for Open-set Graph Anomaly Detection

Conformalized Hierarchical Calibration for Uncertainty-Aware Adaptive Hashing

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

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

Reward-guided Meta-Prompt Evolving with Reflection for LLM Jailbreaking

stUAI: Uncertainty-Aware Clustering of Spatially Resolved Transcriptomics Data

Towards Efficient Fairness Image Retrieval with Disentangled Information Suppression

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

Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction

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

GREAT: GROUP-ACQUIRED BIPARTITE ALIGNMENT FOR GRAPH FAIRNESS ADAPTATION

Test-Time Safety Alignment with Dynamic Intervention for Jailbreak Defense in LLMs

DANCE: Dual Unbiased Expansion with Group-acquired Alignment for Out-of-distribution Graph Fairness Learning

Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation