About me
I am currently a Researcher at Token Foundry (formerly Tongyi Lab), Alibaba Token Hub, Alibaba Group. I obtained my Ph.D. from the Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University (PolyU), under the supervision of Prof. Xiao-Ming Wu, during which I was remotely visiting the University of Illinois at Chicago (UIC) and honored to work with Prof. Philip S. Yu.
Prior to that, I obtained my Master degree from Peking University (PKU) under the supervision of Prof. Yasha Wang and Bachelor degree from Harbin Institute of Technology, Weihai (HIT).
Research Interests
My research focuses on Natural Language Processing (NLP) and Large Language Models (LLMs), with an emphasis on continual adaptation and capability evolution.
My Ph.D. work studied how to efficiently adapt and evolve LLMs in dynamic environments, where new tasks, domains, and knowledge continuously emerge. This includes topics such as continual learning, model editing, and memory-based adaptation.
More recently, I am interested in the self-evolution of LLM-based agents, including recursive self-improvement: how agents autonomously improve from their own experience and interaction, as well as the co-evolution between an agent’s harness (e.g., its skill bank) and its policy model.
📢 We are recruiting research interns on agent self-evolution and memory. The position is onsite (Beijing or Hangzhou), and a long-term commitment is preferred. Please feel free to reach out if you are interested!
🔥 News
- 2026.10: 🎉 One paper has been accepted to IEEE Transactions on Mobile Computing!
- 2026.08: 🎉 One paper has been accepted to EMNLP 2026 Findings!
- 2026.07: 🥳 Organized the Continual Learning in the Era of Foundation Models and Embodied Agents Workshop at NeurIPS 2026.
- 2026.04: 🎉 One paper has been accepted to ACL 2026!
- 2026.01: 🎉 Two papers have been accepted to ICLR 2026!
- 2025.08: 🎉 Two papers have been accepted to EMNLP 2025!
- 2025.07: 🎉 One paper has been accepted to COLM 2025!
- 2025.05: 🎉 Two papers have been accepted to ACL 2025!
- 2024.12: 🎉 One paper has been accepted to AAAI 2025!
- 2024.09: 🎉 One paper has been accepted to EMNLP 2024!
- 2024.08: 🥳 One paper about continual learning is online!
- 2024.05: 🎉 Two papers have been accepted to ACL 2024 (1 Main + 1 Findings)!
- 2024.02: 🎉 One paper has been accepted to COLING 2024!
- 2023.10: 🎉 One paper has been accepted by EMNLP 2023!
Preprint
- TaSL: Task Skill Localization and Consolidation for Language Model Continual Learning.
Yujie Feng, Xu Chu, Yongxin Xu, Zexin Lu, Bo LIU, Philip S. Yu, Xiao-Ming Wu.
[arXiv] (Extension of the ACL 2024 paper)
Selected Publications
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning. [PDF] [Code]
Yujie Feng, Hao Wang, Jian Li, Xu Chu, Zhaolu Kang, Yiran Liu, Yasha Wang, Philip S. Yu, Xiao-Ming Wu.
The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026).Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models. [PDF] [Code]
Yujie Feng, Jian Li, Zhihan Zhou, Pengfei Xu, Yujia Zhang, Xiaoyu Li, Xiaohui Zhou, Alan Zhao, Xi Chen, Xiao-Ming Wu.
The Fourteenth International Conference on Learning Representations (ICLR 2026).AIMMerging: Leveraging Training Trajectories for Adaptive Iterative Model Merging in Language Model Continual Learning. [PDF] [Code]
Yujie Feng, Jian Li, Xiaoyu Dong, Pengfei Xu, Xiaohui Zhou, Yujia Zhang, Zexin Lu, Yasha Wang, Alan Zhao, Xu Chu, Xiao-Ming Wu.
Conference on Empirical Methods in Natural Language Processing (EMNLP 2025).GeoEdit: Geometric Knowledge Editing for Large Language Models. [PDF] [Code]
Yujie Feng, Liming Zhan, Zexin Lu, Yongxin Xu, Xu Chu, Yasha Wang, Jiannong Cao, Philip S. Yu, Xiao-Ming Wu.
Conference on Empirical Methods in Natural Language Processing (EMNLP 2025).Recurrent Knowledge Identification and Fusion for Language Model Continual Learning. [PDF] [Code]
Yujie Feng, Xujia Wang, Zexin Lu, Shenghong Fu, Guangyuan Shi, Yongxin Xu, Yasha Wang, Philip S. Yu, Xu Chu, Xiao-Ming Wu.
The 63nd Annual Meeting of the Association for Computational Linguistics (ACL 2025).TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation. [PDF] [Code]
Yujie Feng, Xu Chu, Yongxin Xu, Guangyuan SHI, Bo LIU, Xiao-Ming Wu.
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).Towards LLM-driven Dialogue State Tracking. [PDF] [Code]
Yujie Feng, Zexin Lu, Bo Liu, Liming Zhan, Xiao-Ming Wu.
Conference on Empirical Methods in Natural Language Processing (EMNLP 2023).Completing missing prevalence rates for multiple chronic diseases by jointly leveraging both intra-and inter-disease population health data correlations. [PDF] [Code]
Yujie Feng, Jiangtao Wang, Yasha Wang, Sumi Helal.
Proceedings of the Web Conference 2021 (WWW 2021).
Honors and Awards
- PolyU Research Student Attachment Program (RSAP) 2024
- PolyU Research Postgraduate Scholarship 2022
- Excellent Graduation Thesis of Peking University 2022
- Merit student of Peking University 2020
- Outstanding Graduates of Shandong Province 2019
- Excellent Graduation Thesis of Harbin Institute of Technology 2019
- Merit student of Harbin Institute of Technology 2016, 2017, 2018
Internships
- 2025/04 - 2025/10, Tencent (Qingyun Project), Shenzhen.
- 2018/11 - 2019/06, Tsinghua University, Beijing.
Activity and Service
- Teaching Assistant
COMP 2421: Computer Organization, Spring 2024 | 2023, PolyU
COMP 6704: Advanced Topics in Optimization, Fall 2024 | 2023, PolyU
COMP 5523: Computer Vision and Image Processing, Spring 2023 | 2022, PolyU
COMP 2021: Data Structures, Fall 2023 | 2022, PolyU
C Language, Fall 2017 | 2016, HITwh - Reviewer of ACL/EMNLP/NAACL/ICLR/NeurIPS/ICML/KDD/TNNLS
- Workshop Organizer / Program Co-Chair NeurIPS 2026 Workshop on Continual Learning in the Era of Foundation Models and Embodied Agents (CL4FMAgents), Sydney, Australia
