Z.-H. Tan*, Z.-C. Zhao*, H.-Y. Shi*, X.-Y. Zhang, P. Tan, Y. Yu, and Z.-H. Zhou.
Learnware of language models: Specialized small language models can do big.
arXiv preprint arXiv:2505.13425, 2025.
[paper]
2026
J.-D. Liu, Z.-C. Zhao, H. Sun, L.-X. Wu, H. Zhang, P. Wang, M. Zhao, X. Chu, S. Yan, Y. Zhu, W. Zhong, Z.-H. Tan, J. Shang, Y. Yu, and Z.-H. Zhou.
Constructive specification for plug-and-play learnware agents.
In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'26). 2026. [paper] (also presented at第十一届 CCF 中国数据挖掘会议 CCDM 2026 顶会顶刊论坛 byZi-Chen Zhao)
also accepted in ICLR 2026 Workshop on Lifelong Agents: Learning, Aligning, Evolving. 2026.
[paper]
P. Tan, Z.-H. Tan, H.-T. Liu, and Z.-H. Zhou. Handling learnwares from heterogeneous feature and label spaces with explicit label exploitation. In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2026. In press.
H.-T. Liu, P. Tan, J.-D. Liu, Z.-H. Tan, and Z.-H. Zhou.
Integrated learnware identification and reuse via reusability-aware metric learning.
In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'26). 2026. [paper]
H.-Y. Lei, Z.-H. Tan, and Z.-H. Zhou.
A statistical framework for analyzing specification resistance to learnware-inversion risks.
In Proceedings of the 43rd International Conference on Machine Learning (ICML'26). 2026. [paper]
H.-Y. Lei, J.-H. Wu, Z.-H. Tan, and Z.-H. Zhou.
PAVE specifications of learnwares yield intrinsic privacy-preserving capabilities.
In Proceedings of the 35th International Joint Conference on Artificial Intelligence (IJCAI'26). 2026. [paper]
H.-Y. Shi, Z.-H. Tan, Z.-C. Zhao, Y. Yu, and Z.-H. Zhou.
A study on PAVE specification for learnware.
In The 14th International Conference on Learning Representations (ICLR'26). 2026.
[paper]
P. Tan, F.-F. Yang, Z.-H. Tan, and Z.-H. Zhou.
Tabular learnwares can be repurposed for seemingly irrelevant new tasks.
In Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI'26), pages 25778–25786. 2026.
[paper]
2025
J.-D. Liu, Z.-H. Tan, and Z.-H. Zhou.
Dynamic learnware filtering for efficient learnware identification and system slimming.
In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'25), pages 1811–1822. 2025.
[paper]
J.-D. Liu, Z.-H. Tan, and Z.-H. Zhou.
Identifying and reusing learnwares across different label spaces.
In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI'25), pages 5734–5742. 2025.
[paper]
2024
Z.-H. Zhou and Z.-H. Tan.
Learnware: Small models do big.
Science China Information Sciences (SCIS), 67(1):112102, 2024.
[paper]
Z.-H. Tan*, J.-D. Liu*, X.-D. Bi, P. Tan, Q.-C. Zheng, H.-T. Liu, Y. Xie, X.-C. Zou, Y. Yu, and Z.-H. Zhou.
Beimingwu: A learnware dock system.
In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'24), pages 5773–5782. 2024.
[paper]
H.-Y. Lei, Z.-H. Tan, and Z.-H. Zhou.
On the ability of developers' training data preservation of learnware.
In Advances in Neural Information Processing Systems 37 (NeurIPS'24), pages 36471–36513. 2024.
[paper]
P. Tan, H.-T. Liu, Z.-H. Tan, and Z.-H. Zhou.
Handling learnwares from heterogeneous feature spaces with explicit label exploitation.
In Advances in Neural Information Processing Systems 37 (NeurIPS'24), pages 12767–12795. 2024.
[paper]
J.-D. Liu, Z.-H. Tan, and Z.-H. Zhou.
Towards making learnware specification and market evolvable.
In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI'24), pages 13909–13917. 2024.
[paper]
P. Tan, Z.-H. Tan, Y. Jiang, and Z.-H. Zhou.
Towards enabling learnware to handle heterogeneous feature spaces.
Machine Learning, 113(4):1839–1860, 2024.
[paper]
P. Tan, Z.-H. Tan, Y. Jiang, and Z.-H. Zhou.
Handling learnwares developed from heterogeneous feature spaces without auxiliary data.
In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI'23), pages 4235–4243. 2023.
[paper]
Y. Xie, Z.-H. Tan, Y. Jiang, and Z.-H. Zhou.
Identifying helpful learnwares without examining the whole market.
In Proceedings of the 26th European Conference on Artificial Intelligence (ECAI'23), pages 2752–2759. 2023.
[paper]
Z.-H. Tan, Y. Xie, Y. Jiang, and Z.-H. Zhou.
Real-valued backpropagation is unsuitable for complex-valued neural networks.
In Advances in Neural Information Processing Systems 35 (NeurIPS'22), pages 34052–34063. 2022.
[paper]
Z.-H. Tan, P. Tan, Y. Jiang, and Z.-H. Zhou.
Multi-label optimal margin distribution machine.
Machine Learning, 109(3):623–642, 2020.
[paper]
Z.-H. Tan, T. Zhang, and W. Wang.
Coreset stochastic variance-reduced gradient with application to optimal margin distribution machine.
In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI'19), pages 5083–5090. 2019.
[paper]