Kun Zhang, Ph.D., Associate Professor and Doctoral Supervisor of Hefei University of Technology. His main research interests include research in the fields of text semantic understanding, semantic matching, semantic reasoning, text-based recommender systems, etc. He has published more than 20 papers in top conferences such as SIGIR, WWW, ACL, AAAI, and ICDM, as well as top journals including TSMC-S, TNNLS, and TKDE. He was selected for the 2021 Microsoft Research Asia Cast Star Scholars Programme, won the KDD2018 Best Student Paper Award, and served as a program committee member of international conferences such as SIGIR, ACL, AAAI, EMNLP, and so on. 

For his research, he has proposed a dynamic attention mechanism incorporating a priori knowledge of users' reading habits, which achieves dynamic attention to text focus content during semantic reasoning, significantly better than existing attention mechanism methods. The results were published in AAAI [1], the top academic conference in the field of Artificial Intelligence; He has proposed a multimodal graph modeling method incorporating user attribute information (age, occupation, etc.), which achieves the modelling of user preferences using attribute information, and better solves the cold-start problem in the recommendation system under the premise of guaranteeing the recommendation effect. The results were published in SIGIR [2], the top academic conference in the field of information retrieval.

【Opening Position】I am looking forward Ph.D. students for Large Language Models research.

I am looking forward self-motivated students to join us. If you are interested in my research, feel free to contact me.

For more information, please visit the individual academic homepage：https://zhangkunzk.github.io/

1. [ACL2025 Findings] Dacao Zhang, Kun Zhang*, Shimao Chu, Le Wu, Xin Li, Si Wei,  MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning

2. [CCL 2025] (Featured Paper) Jinglong Li, Kun Zhang*, Chenyu Zou, Wei Shi, Xin Li, Si Wei, EDGE: Enhanced Debiased Gradient Extraction for Robust Fine‑tuning

3. [ACM TOIS 2025] Shulan Ruan, Huijie Liu, Zhao Chen, Bin Feng, Kun Zhang, Caleb Chen Cao, Enhong Chen, Lei Chen, CPWS: Confident Programmatic Weak Supervision for High-Quality Data Labeling.

4. [KDD 2025] Pengyang Shao, Yonghui Yang, Chen Gao, Lei Chen, Kun Zhang, Chenyi Zhuang, Le Wu, Yong Li, Meng Wang, Exploring Heterogeneity and Uncertainty for Graph-based Cognitive Diagnosis Models in Intelligent Education. 

5. [FCS 2025] Pengyang Shao, Kun Zhang*, Chen Gao*, Lei Chen, Miaomiao Cai, Le Wu, Yong Li, Meng Wang, Breaking Student-Concept Sparsity Barrier for Cognitive Diagnosis

6. [KDD2024] Dacao Zhang, Kun Zhang*, Le Wu, Mi Tian, Richang Hong, Meng Wang, Path-Specific Causal Reasoning for Fairness-aware Cognitive Diagnosis.

7. [ACM TOIS2024] Pengyang Shao, Le Wu*, Kun Zhang, Defu Lian, Richang Hong, Yong Li, Meng Wang. Average User-side Counterfactual Fairness for Collaborative Filtering. 

8. [AI Open2024] Kun Zhang*, Dacao Zhang, Le Wu, Richang Hong, Ye Zhao, Meng Wang. Label-aware Debiased Causal Reasoning for Natural Language Inference.

9. [IEEE TCSS2024] Kun Zhang*, Guangyi Lv, Le Wu, Richang Hong, Meng Wang. EMCRL: EM-enhanced Negative Sampling Strategy for Contrastive Representation Learning

10. [FCS 2024] Dacao Zhang, Fan Yang, Kun Zhang*, Richang Hong. Optimizing Low-Rank Adaptation with Decomposed Matrices and Adaptive Rank Allocation.

11. [IEEE TNNLS2023] Kun Zhang, Le Wu, Guangyi Lv, Enhong Chen, Shulan Ruan, Jing Liu, Zhiqiang Zhang, Jun Zhou, Meng Wang. Description-Enhanced Label Embedding Contrastive Learning for Text Classification.