柯文俊 (Wenjun Ke)

southeast university教授

H指数:2

被引数:14

个人简介

"柯文俊，副教授，博士生导师，紫金青年学者，小米青年学者，就职于东南大学计算机科学与工程学院、软件学院、人工智能学院。博士毕业于中国科学院计算技术研究所（导师为程学旗研究员），加入东南大学KGCode实验室（实验室负责人为汪鹏教授）。研究方向为：人工智能、自然语言处理、大语言模型、知识图谱，先后主持7项国家级科研项目，并参与4项国家级科研项目。先后获得省部级/市厅级等荣誉7项，任中国仿真学会会刊、CCF-T2中文核心期刊《系统仿真学报》青年编委，CCF-T3中文核心期刊《计算机工程与设计》编委。在WSDM、NeurIPS、ACL、IJCAI、AAAI、ISWC、TOIS、TKDE、KBS、ESWA、EMNLP、IPM、中文信息学报等重要国内外重要期刊和会议发表论文60余篇，申请发明专利10余项，获授权发明专利7项。作为研究生导师，指导/协助指导博士/硕士研究生10余名，其中5人获得国家奖学金，1人获得博士新生奖学金，2人获得全国研究生数学建模比赛二等奖，2人获得全国研究生数学建模比赛三等奖。同时，担任本科人工智能专业主干课《自然语言处理》的主讲教师，以理论教学与实践操作相结合的方式开展综合性教学。每年招收1-2名博士生、5-6名硕士生（可以在计算机学院、软件学院、人工智能学院招生），2027年秋季入学的保研硕士生还有名额，欢迎对自然语言处理（NLP）、大语言模型（LLMs）、知识图谱（Knowledge Graph）感兴趣的同学与我联系（kewenjun@seu.edu.cn），将与汪鹏教授共同指导。论文（Selected）1. Y. Lou, W. Ke, Y. He, P. Wang, Q. Liu, H Xu. Boosting multimodal CoT reasoning through DPO with Error-prone Sample Synthesis. IPM 2026 (CCF B)2.Y. Guo, B. Wang, X. Fan, W. Ke, H. Luo. On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective. ICML 2026 (CCF-A)3. Z. Yang, W. Ke, Y. Li, Y. Liu, J. Xu, P. Wang, H. Xu. Mitigating Tool Overuse for LLMs via Active Knowledge Boundary Probing. IJCAI 2026 (CCF-B)4. T. Hong, P. Wang, W. Ke, Y. He, H. Wang. Benchmarking and Enhancing Relational Diagrams Reasoning for Multimodal Large Language Models. IJCAI 2026 (CCF-B)5. C. Zhang, J. Liu, Y. He, W. Ke, P. Wang, Y. Le, S. Liu, Z. Yang. Exploring Layer Activation Dynamic of CoT via Knowledge Probe. ACL 2026 Main Conference Oral (CCF-A)6. J. Zhou, P. Wang, W. Ke, J. Liu, Y. He. Capability Decomposition for Unified Information Extraction via Hierarchical Mixture-of-Experts. ACL 2026 Main Conference Oral (CCF-A)7. W. Ke, H. Xu, Z. Shang, Y. He, J. Wang, Z. Xu, P. Wang, Y. Lou, J. Liu. From Outcome to Process: Optimizing MoE Load Balancing with MCTS. ACL 2026 Findings (CCF-A)8. Y. He, J. Liu, W. Wen, Y. Guo, H. Chen, Y. Ma, W. Ke. LogicICL: Towards Instructive Logical-Aware Demonstrations for Stimulating LLMs Mathematical Reasoning Ability. IEEE Trans. on Emerging Topics in Computational Intelligence 2026 (SCI JCR Q1)9. Z. Xu, W. Ke, P. Wang, et al. Benchmarking and Enhancing Rule Knowledge-Driven Reasoning of Large Language Models. AAAI 2026 (CCF-A)10. H. Xu, W. Ke, Y. He, et al. Optimizing LoRA Allocation of MoE with the Alignment of Topic Correlation. AAAI 2026 (CCF-A)11. J. Liu, Y. He, W. Ke, et al. Balanced Knowledge Distillation for Large Language Models with Mix-of-Experts. AAAI 2026 (CCF-A)12. W. Ke, Y. Zheng, Y. Li, et al. Large Language Models in Document Intelligence:A Comprehensive Survey, Recent Advances, Challenges andFuture Trends. TOIS 2025 (CCF-A)13. Y. Li, W. Ke, J. Liu, et al. Towards Evidence-Aware RAG via Self-Corrective Chain-of-Thought. Information Processing and Management 2025 (CCF-B)14. Z. Shang, P. Wang, J. Liu, J. Liu, G. Li, Z. Xu, Z. Luo, X. Chen, W. Ke. Learning Multi-Granularity and AdaptiveRepresentation for Knowledge Graph Reasoning. TKDE 2025 (CCF-A)15. J. Liu, Z. Shang, W. Ke, et al. LLM-Guided Semantic-Aware Clustering for Topic Modeling. ACL 2025 (CCF-A)16. Z. Shang, J. Liu, Z. Luo, P. Wang, W. Ke, et al. Acquisition and Application of Novel Knowledge in Large Language Models. ACL 2025 (CCF-A)17. G. Li, P. Wang, W. Ke, et al. On the Consistency of Commonsense in Large Language Models. ACL Findings 2025 (CCF-A)19. Y. He, J. Liu, W. Ke, et al. Exploring Meta Evidence for Prompt Optimization. ICASSP 2025 (CCF-B)20. W. Ke, J. Wang, P. Wang, et al. Unveiling LoRA Intrinsic Ranks via Salience Analysis. NeurIPS 2024 (CCF-A)21. W. Ke, Z. Shang, et al. Unveiling Factuality and Injecting Knowledge for LLMs via Reinforcement Learning and Data Proportion.SCIENCE CHINA Information Sciences 2024(CCF-A)22. J. Wang, W. Ke, P. Wang, et al. InstructNER: Boosting Textural NER with Synthetic Image and Instructive Alignment. ACL Findings 2024 (CCF-A)23. Y. Zheng, W. Ke, Q. Liu, et al. Making LLMs as Fine-Grained Relation Extraction Data Augmentor. IJCAI 2024 (CCF-A)24. K. Ji, P. Wang, W. Ke, et al. Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification. IJCAI 2024 (CCF-A)25. G. Li, P. Wang, W. Ke, et al. Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction. IJCAI 2024 (CCF-A)26. Z. Xu, P. Wang, W. Ke, et al. Incorporating Schema-Aware Description into Document-Level Event Extraction. IJCAI 2024 (CCF-A)27. J. Liu, W. Ke, P. Wang, et al. Fast and Continual Knowledge Graph Embedding via Incremental LoRA. IJCAI 2024 (CCF-A)28. Z. Shang, P. Wang, W. Ke, et al. Learning Multi-Granularity and Adaptive Representation for Knowledge Graph Reasoning. IJCAI 2024 (CCF-A)29. Q. Liu, W. Ke, X. Yuan, et al. AdaptiveUKE: Towards Adaptive Unsupervised Keyphrase Extraction with Gated Topic Modeling. ESWA 2024（SCI JCR 一区）30. G. Li, W. Ke, P. Wang, et al. Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction. COLING 2024（CCF-B）31. Z. Luo, Y. Wang, W. Ke, et al. BOOSTING LLMS WITH ONTOLOGY-AWARE PROMPT FOR NER DATA AUGMENTATION. ICASSP 2024. (CCF-B)32. Z. Shang, W. Ke, P. Wang, et al. OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning. AAAI 2024.(CCF-A)33. C. Wu, W. Ke, P. Wang, et al.ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context. AAAI 2024.(CCF-A)34. J. Liu, W. Ke, P. Wang, et al. Towards Continual Knowledge Graph Embedding via Incremental Distillation. AAAI 2024. (CCF-A)35. Y. Liu, P. Wang, W. Ke, et al.Unify Named Entity Recognition Scenarios via Contrastive Real-time Updating Prototype. AAAI 2024. (CCF-A)36. W. Ke,Y. Guo,Q. Liu,W. Chen,P. Wang,H. Luo,Z. Luo. MDM: Meta Diffusion Model for Hard-constrained Text Generation. KBS 2023. (SCI JCR 一区)37. W. Ke, Z. Tian, Q. Liu, P. Wang, J. Gao, R. Qi. Towards Incremental NER Data Augmentation via Syntactic-aware Insertion Transformer. IJCAI 2023. (CCF-A)38. H. Zhang, W. Ke, J. Zhang, Z. Luo, H. Ma, Z. Luan, P. Wang. Prompt-based Ev"