PPaperPicks

Wenjun Ke

Southeast University, College of Software Engineering, School of Computer Science and Engineering, Nanjing, China

22 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Balanced Knowledge Distillation for Large Language Models with Mix-of-Experts
  2. Benchmarking and Enhancing Rule Knowledge-Driven Reasoning of Large Language Models
  3. Capability Decomposition for Unified Information Extraction via Hierarchical Mixture-of-Experts
  4. Exploring Layer Activation Dynamic of CoT via Knowledge Probe
  5. From Outcome to Process: Optimizing MoE Load Balancing with MCTS
    ACL 2026 · Wenjun Ke
  6. Optimizing LoRA Allocation of MoE with the Alignment of Topic Correlation
  7. Unlearning of Knowledge Graph Embedding via Preference Optimization
  8. Acquisition and Application of Novel Knowledge in Large Language Models
  9. LLM-Guided Semantic-Aware Clustering for Topic Modeling
  10. On the Consistency of Commonsense in Large Language Models
  11. Boosting Textural NER with Synthetic Image and Instructive Alignment
  12. ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context
  13. Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification
  14. Fast and Continual Knowledge Graph Embedding via Incremental LoRA
  15. Incorporating Schema-Aware Description into Document-Level Event Extraction
  16. Learning Multi-Granularity and Adaptive Representation for Knowledge Graph Reasoning
  17. Making LLMs as Fine-Grained Relation Extraction Data Augmentor
  18. OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning
  19. Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction
  20. Towards Continual Knowledge Graph Embedding via Incremental Distillation
  21. Unify Named Entity Recognition Scenarios via Contrastive Real-Time Updating Prototype
  22. Unveiling LoRA Intrinsic Ranks via Salience Analysis
    NeurIPS 2024 · Wenjun Ke