I joined the School of Artificial Intelligence at Beijing Normal University (BNU) as an Associate Professor and Ph.D. Supervisor in September 2024. Prior to this, I was a young senior researcher at the Institute of Information Engineering, Chinese Academy of Sciences, from September 2020 to September 2024. I received my Ph.D. from the University of Chinese Academy of Sciences in June 2020, under the supervision of Professor Yong Liu and Professor Weiping Wang.

Artificial intelligence methods represented by large language models (LLMs) are rapidly evolving from single-turn language systems into long-horizon, tool-using, and domain-specialized agents. My research focuses on information compression for large language models and efficient intelligent agents, aiming to build resource-aware LLM systems that preserve reasoning, memory, and tool-use capabilities under constrained computation, context, and deployment budgets. I am particularly interested in the fundamental mechanisms of compression, adaptation, and capability preservation, as well as their deployment in reliable and scalable educational AI systems. Specific research interests include, but are not limited to:

• Information compression for LLMs: Investigating model compression, context compression, memory compression, knowledge compression, and skill compression to understand how large-scale models and agents can retain essential information and capabilities with lower computational and contextual cost.

• Efficient and resource-aware agents: Studying cost-aware reasoning, budgeted memory, dynamic retrieval, tool-use scheduling, small-agent capability enhancement, and multi-agent coordination to improve the efficiency, robustness, and scalability of agentic LLM systems.

• Educational intelligent agents: Developing efficient, trustworthy, and deployable educational agents for interactive teaching-resource generation, question-generation agents, lesson-plan generation, intelligent tutoring, educational evaluation, and personalized learning support.

Career

Education

Selected Papers [Full List] [Google Scholar]

• Textual Stochastic Gradient Descent: Discrete Optimization of External Memory for Reasoning Language Agents.
  Jian Li, Hua Huang.
  International Conference on Machine Learning (ICML), 2026. CCF-A Conference.

• A Survey on Model Compression for Large Language Models. [pdf]
  Xunyu Zhu, Jian Li*, Yong Liu, Can Ma, Weiping Wang.
  Transactions of the Association for Computational Linguistics (TACL), 2024. CCF-B Journal / JCR Q1.
  

• Distilling mathematical reasoning capabilities into Small Language Models. [pdf]
  Xunyu Zhu, Jian Li*, Yong Liu, Can Ma, Weiping Wang.
  Neural Networks, 2024. CCF-B Journal / JCR Q1.

• Optimal Rates for Agnostic Distributed Learning. [pdf] [code]
  Jian Li, Yong Liu, Weiping Wang.
  IEEE Transactions on Information Theory (TIT), 2023. CCF-A Journal.
  

• Optimal Convergence Rates for Distributed Nyström Approximation. [pdf] [code]
  Jian Li, Yong Liu, Weiping Wang.
  Journal of Machine Learning Research (JMLR), 2023. CCF-A Journal.

• Convolutional Spectral Kernel Learning with Generalization Guarantees. [pdf] [code]
  Jian Li, Yong Liu, Weiping Wang.
  Artificial Intelligence (AI), 2022. CCF-A Journal.

• Optimal Convergence Rates for Agnostic Nyström Kernel Learning. [pdf]
  Jian Li, Yong Liu, Weiping Wang.
  International Conference on Machine Learning (ICML), 2023. CCF-A Conference.

• Multi-Class Learning: From Theory to Algorithm. [pdf] [poster] [slides] [3-minute video] [code]
  Jian Li, Yong Liu, Rong Yin, Hua Zhang, Lizhong Ding, Weiping Wang.
  Advances in Neural Information Processing Systems 31 (NeurIPS), 2018. CCF-A Conference.

• Federated learning for non-iid data: From theory to algorithm. [pdf] [presentation] [🏆Best Student Paper Award] (1/92)
  Bojian Wei, Jian Li*, Yong Liu, Weiping Wang.
  Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2021. CCF-C Conference.

Projects

• National Natural Science Foundation of China (No. 62576041), 2026.01 - 2029.12, ¥500,000.
  Information Compression of Large Language Models: Mathematical Mechanism Analysis and Algorithm Design.

• National Key R&D Program of China (2022YFB3105302.2), 2022.12 - 2025.11, ¥1,200,000.
  Aggregation and Collaborative Techniques for Cross-platforms Heterogeneous Data.

• National Natural Science Foundation of China (No. 62106257), 2022.01 - 2024.12, ¥300,000.
  Large Scale Structured Prediction with Automated Spectral Kernel Learning.

• China Postdoctoral Science Foundation (Special Support, No. 2023T160680), 2023.07 - 2024.03, ¥180,000.
  Research on Deep Differentiable Gaussian Processes for Structured Prediction.

• Special Research Assistant Project of CAS, 2020.09 - 2022.09, ¥800,000.
  Large-scale Few-shot Automated Machine Learning.

• Talent Program Class A of Institute of Information Engineering, CAS, Tenure-track Professor, 2023.10 - 2026.09.

• Talent Program Class B of Institute of Information Engineering, CAS, Tenure-track Young Professor, 2020.09 - 2023.10.

Patents

Granted

• Hailun Lin, Yong Liu, Jian Li, Weiping Wang. A Large-Scale Ontology Merging Method that Integrates Representation Learning and Divide-and-Conquer Strategy: China. Granted No.CN110059194A. Granted Date: April 8, 2022.

Pending

• Jian Li, Yong Liu, Liubin Wang, Yiguo Yang, Juhong Wang. Neural Network Architecture Search Method, Device, Computer Equipment, and Storage Medium. CN: 202011567991.3. App. Date: December 25, 2020.
• Jian Li, Jiaoyang Li, Bojian Wei, Yong Liu, Weiping Wang. A Federated Learning Method and System Based on Attention Mechanism. CN: 202311073645.3. App. Date: August 24, 2023
• Jian Li, Jiaoyang Li, Zheng Lin, Yong Liu, Weiping Wang. A Vertical Domain Large Model Method and System Based on Knowledge Distillation and Prompt Engineering. CN: 202311073641.5. App. Date: August 24, 2023.

Students

• Ph.D. students
  • 🎓Yilin Kang (2020.09 - 2023.06), Differential Privacy.
    Publications: Computers & Security, CIKM, ICCS.
    Post-graduation: Purple Mountain Laboratories; later joined Yuxi Normal University.
  • 🎓Xunyu Zhu (2020.09 - 2025.06), Efficient LLM Inference and LLM Compression.
    Publications: TACL, Neural Networks $\times$ 2, ICDM, IJCNN $\times$ 2.
    Post-graduation: State Power Investment Corporation Central Research Institute.
  • Boxuan Che (2022.09 - present), Efficient Graph Neural Networks.
• Master students
  • 🎓Bojian Wei (2020.09 - 2022.06), Federated Learning on Heterogeneous Data.
    Publications: PRICAI 2021 (best student paper award), TNNLS, ECML-PKDD, IJCNN.
    Post-graduation: Management Trainee in Bank of China Head Office.
  • 🎓Xuning Zhang (2023.09 - 2026.06), Federated Learning.
    Excellent Bachelor’s Thesis in Wuhan University in 2023.
    Publications: TNNLS.
    Post-graduation: ByteDance.
  • Zhenyu Wu (2024.09 - present), Interactive Teaching Resource Generation and Question-Generation Agents.
    In submissions: MM 2026, EMNLP 2026.
  • Mucun Xie (2025.09 - present), Efficient Agent Memory.
    Publications: ICCBR 2026.
  • Zongyou Tan (2025.09 - present), Educational Intelligent Agents.

Honors and Awards

• Microsoft Research Asia StarTrack Scholars Program, 2024
• Talent Plan Class A of IIE, CAS, 2023.
• PRICAI 2021 best student paper award, 2021.
• Special Research Assistant of Chinese Academy of Sciences, 2020.
• Talent Plan Class B of IIE, CAS, 2020.
• AIDU Talents of Baidu Research, 2020.
• Joint Ph.D. Program with Stanford University (Discontinued due to COVID-19), 2020.02 - 2021.02.
• Outstanding Graduates of Beijing, 2020.
• Outstanding Graduates of University of Chinese Academy of Sciences (UCAS), 2020.
• Outstanding Graduates of Institute of Information Engineering, CAS, 2020.
• National Scholarship for Doctoral students, 2019.
• ZhuLiYueHua Scholarship for Excellent Doctoral Student, 2019.
• CAS Presidential Scholarship, 2019.
• National Scholarship for Doctoral students, 2018.

Academic Service

• Mathematics Guest Editor
• Program committee of Conference: ICML, NeurIPS, ICLR, AAAI, IJCAI, ECAI, etc.
• Reviewers of Journals: TPAMI, JMLR, Pattern Recognition, etc.