谭志豪 Zhi-Hao Tan (Z.-H. Tan) Assistant researcher, LAMDA Group School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China Email: tanzh@lamda.nju.edu.cn Laboratory: Building of Computer Science and Technology, Xianlin Campus of Nanjing University

Biography

Currently I am an assistant researcher (Yuxiu Young Scholar) in School of Artificial Intelligence at Nanjing University, and I am also a member of LAMDA Group. I obtained my Ph.D. degree from Nanjing University in 2024, where I was very fortunate to be advised by Prof. Yuan Jiang and Prof. Zhi-Hua Zhou. I receive my B.Sc. degree from University of Science and Technology of China in 2017.

Research Interests

I focus on learnware paradigm in machine learning, which is a new field on AI capability representation for reuse, and building decentralized self-evolving intelligent system.

Preprints

• Learnware of Language Models: Specialized Small Language Models Can Do Big [arXiv]
  Zhi-Hao Tan*, Zi-Chen Zhao*, Hao-Yu Shi*, Xin-Yu Zhang, Peng Tan, Yang Yu, Zhi-Hua Zhou
  
  

Publications

• A Statistical Framework for Analyzing Specification Resistance to Learnware-Inversion Risks
  Hao-Yi Lei, Zhi-Hao Tan, Zhi-Hua Zhou.
  In: Proceedings of the 43rd International Conference on Machine Learning (ICML'26), Seoul, South Korea, 2026. (to appear)
  
  
• PAVE Specifications of Learnwares Yield Intrinsic Privacy-Preserving Capabilities
  Hao-Yi Lei, Jin-Hui Wu, Zhi-Hao Tan, Zhi-Hua Zhou.
  In: Proceedings of the 35th International Joint Conference on Artificial Intelligence (IJCAI'26), Bremen, Germany, 2026. (to appear)
  
  
• A Study on PAVE Specification for Learnware [PDF, Bibtex]
  Hao-Yu Shi, Zhi-Hao Tan, Zi-Chen Zhao, Yang Yu, Zhi-Hua Zhou.
  In: The 14th International Conference on Learning Representations (ICLR'26), Rio de Janeiro, Brazil, 2026.
  
  
• Constructive Specification for Plug-and-Play Learnware Agents [PDF, Bibtex]
  Jian-Dong Liu, Zi-Chen Zhao, Hao Sun, Lin-Xing Wu, Huan Zhang, Pengyuan Wang, Ming Zhao, Xinyu Chu, Shu Yan, Yongbei Zhu, Weijun Zhong, Zhi-Hao Tan, Jing Shang, Yang Yu, Zhi-Hua Zhou
  In: ICLR 2026 Workshop on Lifelong Agents: Learning, Aligning, Evolving. Rio de Janeiro, Brazil, 2026.
  
  
• Tabular Learnwares can be Repurposed for Seemingly Irrelevant New Tasks [PDF, Bibtex]
  Peng Tan, Fei-Fan Yang, Zhi-Hao Tan, Zhi-Hua Zhou.
  In: Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI'26), Changi, Singapore, 2026. Page: 25778-25786.
  
  
• Dynamic Learnware Filtering for Efficient Learnware Identification and System Slimming [PDF, Bibtex]
  Jian-Dong Liu, Zhi-Hao Tan and Zhi-Hua Zhou.
  In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'25), Toronto, Canada, 2025. Page: 1811-1822.
  
  
• Identifying and Reusing Learnwares across Different Label Spaces [PDF, Bibtex]
  Jian-Dong Liu, Zhi-Hao Tan and Zhi-Hua Zhou.
  In: Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI'25), Montreal, Canada, 2025. Page: 5734-5742.
  
  
• Learnware: Small Models Do Big [PDF, Bibtex]
  Zhi-Hua Zhou and Zhi-Hao Tan.
  Science China Information Sciences (SCIS), 2024, 67(1): 112102.
  
  
• Beimingwu: A Learnware Dock System [PDF, Bibtex, Homepage, Docs, GitLink, GitHub]
  Zhi-Hao Tan*, Jian-Dong Liu*, Xiao-Dong Bi, Peng Tan, Qin-Cheng Zheng, Hai-Tian Liu, Yi Xie, Xiao-Chuan Zou, Yang Yu and Zhi-Hua Zhou. (* indicates equal contribution)
  In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'24), Barcelona, Spain, 2024. Page: 5773-5782.
  
  
• On the Ability of Developers' Training Data Preservation of Learnware [PDF, Bibtex]
  Hao-Yi Lei, Zhi-Hao Tan and Zhi-Hua Zhou.
  In: Advances in Neural Information Processing Systems 37 (NeurIPS'24), Vancouver, Canada, 2024. Page: 36471-36513.
  
  
• Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation [PDF, Bibtex]
  Peng Tan, Hai-Tian Liu, Zhi-Hao Tan and Zhi-Hua Zhou.
  In: Advances in Neural Information Processing Systems 37 (NeurIPS'24), Vancouver, Canada, 2024. Page: 12767-12795.
  
  
• Towards Making Learnware Specification and Market Evolvable [PDF, Bibtex]
  Jian-Dong Liu, Zhi-Hao Tan and Zhi-Hua Zhou.
  In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI'24), Vancouver, Canada, 2024. Page: 13909-13917.
  
  
• Towards Enabling Learnware to Handle Heterogeneous Feature Spaces [PDF, Bibtex]
  Peng Tan, Zhi-Hao Tan, Yuan Jiang and Zhi-Hua Zhou.
  Machine Learning, 113(4): 1839–1860, 2024.
  
  
• Handling Learnwares Developed from Heterogeneous Feature Spaces without Auxiliary Data [PDF, Bibtex]
  Peng Tan, Zhi-Hao Tan, Yuan Jiang and Zhi-Hua Zhou.
  In: Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI'23), Macao, China, 2023. Page: 4235-4243.
  
  
• Identifying Helpful Learnwares without Examining the Whole Market [PDF, Bibtex]
  Yi Xie, Zhi-Hao Tan, Yuan Jiang and Zhi-Hua Zhou.
  In: Proceedings of the 26th European Conference on Artificial Intelligence (ECAI'23), Kraków, Poland, 2023. Page: 2752-2759.
  
  
• Real-Valued Backpropagation is Unsuitable for Complex-Valued Neural Networks [PDF, Poster, Bibtex]
  Zhi-Hao Tan, Yi Xie, Yuan Jiang and Zhi-Hua Zhou.
  In: Advances in Neural Information Processing Systems 35 (NeurIPS'22), New Orleans, Louisiana, 2022. Page: 34052-34063.
  
  
• Multi-label Optimal Margin Distribution Machine [PDF, Bibtex]
  Zhi-Hao Tan, Peng Tan, Yuan Jiang and Zhi-Hua Zhou.
  Machine Learning, 109(3): 623-642, 2020.
  
  
• Coreset Stochastic Variance-Reduced Gradient with Application to Optimal Margin Distribution Machine [PDF, Bibtex]
  Zhi-Hao Tan, Teng Zhang and Wei Wang.
  In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI'19), Honolulu, HI, 2019. Page: 5083-5090.
  
  
• 基于神经切线核的学件RKME规约 [PDF]
  谭志豪, 史浩宇, 陈梓轩, 姜远.
  计算机学报, 47(6): 1232-1243, 2024.

Academic Services

IJCAI 2021 Workflow Chair (May. 2020 - Aug. 2021) [Committee List][Certificate of Appreciation]

Conference Reviewers:

• ICML (2025, 2024, 2023, 2022), NeurIPS (2025, 2024, 2023, 2022), AAAI (2025, 2024, 2022, 2020), IJCAI (2020, 2019), AISTATS (2023, 2022), ICLR (2025, 2024), ECAI (2020), PAKDD (2022), PRICAI (2025, 2019)

Reviewer for Journals:

• Machine Learning (MLJ)
• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• International Journal of Data Science and Analytics (JDSA)
• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
• ACM Transactions on Knowledge Discovery from Data (TKDD)
• Frontiers of Computer Science (FCS)

Talks

• 第十四届江苏省计算机大会(JSCC 2025)·人工智能前沿论坛，2025.6.15

Awards & Honors

• 2024年华为“紫金学者”计划

• Nanjing University Yuxiu Scholar Program (2024年南京大学“毓秀青年学者”计划)

• CCFAI Best Paper Award (中国计算机学会人工智能会议最佳论文奖), 2023

• Nanjing University-Huawei Joint Laboratory Outstanding Contribution Award, 2023

• IJCAI 2021 Workflow Chair, 2021

Correspondence

Email: tanzh@lamda.nju.edu.cn

Address: National Key Laboratory for Novel Software Technology, Nanjing University, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China.

(南京市栖霞区仙林大道163号, 南京大学仙林校区, 软件新技术国家重点实验室, 210023.)