基本信息

个人简介

梁浩锋（Ho-fung Leung），华南理工大学软件学院教授、博士生导师。香港中文大学计算机科学与工程学系荣休教授、前系主任、前社会学系教授（礼任）；香港工程师学会（HKIE）资深会员（Fellow）、英国电脑学会（BCS）特许会士（Chartered Fellow）、英国工程委员会特许工程师 (CEng)。研究聚焦于人工智能，包括智能体（intelligent agents）、多智能体系统（multi-agent systems）、智能体协作、规范涌现、强化学习、计算本体论（computational ontologies）、复杂系统与社会计算等。已在IEEE TCAD, IEEE TKDE, IEEE TMM, IEEE TPDS, VLDBJ, AAMAS, Comput J, Cybersecurity, Inf Sci, KAIS, Neural Netw, ACM TAAS, IEEE TAC, IEEE TASLP, TCS, IEEE THMS, IEEE TSMC, WWW等期刊和AAAI, ACL, ICLR, ICML, IJCAI, NeurIPS, SIGKDD, AAMAS, DASFAA, ECAI, EMNLP, LREC/COLING, NAACL, PerCom, WISE等会议发表学术论文300余篇，并在施普林格、高等教育出版社等出版研究专著及编著10部。

学历

1985 香港中文大学电子计算学理学士（荣誉）

1988 香港中文大学电子计算学哲学硕士

1992 伦敦大学计算机科学哲学博士（获帝国理工学院文凭 DIC）

教学经历

从事博弈论、多智能体系统、语义网、人工智能编程语言、数据结构等课程的教学和建设。

工作经历

1992-1997 香港中文大学计算机科学与工程学系助理教授

1997-2006 香港中文大学计算机科学与工程学系副教授

2006-2023 香港中文大学计算机科学与工程学系教授

2019-2023 香港中文大学社会学系教授（礼任）

研究方向

多智能体系统、强化学习、知识图谱。

近三年发表论文

2026

LI, M. Z., QI, J. H., WU, Y.H., ZHAO, M. H., MA, L. H., LI, Y. F., WANG, X. Y., TAI, Z. H., SONG, Z. X., ZHANG, Y. X., LEUNG, H. F., KING, I., 2026. From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development. In: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2026, Jeju, Korea, 9 – 13 August 2026. ACM.

WU, Y. H., MA L. H., LI, M. Z., ZHOU, J. M., DING, L., HAO, J. Y., LEUNG, H. F., KING, I., ZHANG, Y. X., NIE, J. Y., 2026. Advancing Multi-Agent RAG system with Minimalist Reinforcement Learning. In: Proceedings of the 25th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’26, Paphos, Cyprus, 25 – 29 May 2026. IFAAMAS.  doi:10.65109/QCQC1144

2025

LI, M. Z., QI, J. H., WU, Y. H., ZHAO, M. H., MA, L. H., LI, Y. F., WANG, X. Y., ZHANG, Y. X., LEUNG, H. F., and KING, I., 2025. From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development. In: NeurIPS 2025 Workshop on Efficient Reasoning. San Diego, U.S.A., 6 December 2025.  https://openreview.net/forum?id=wt5EF9bAqb

WU, X., BU, Y. Q., CAI, Y., CHEN, Y. F. and LEUNG, H. F., 2025. Type-Agnostic and Form-Oriented Deductive Conclusion Generation. Neural Netw., 192. Elsevier, 107968.  doi:10.1016/j.neunet.2025.107968

HU, X. Y., LEUNG, H. F. and FARNIA, F., 2025. PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-based Selection of Generative Models and LLMs. In: A. SINGH, M. FAZEL, D. HSU, S. LACOSTE-JULIEN, F. BERKENKAMP, T. MAHARAJ, K. WAGSTAFF and J. ZHU, Eds., Proceedings of the 42^nd International Conference on Machine Learning, ICML 2025, PMLR, Vol. 267. Vancouver, Canada, 13 – 19 July 2025. PMLR, 24447–24481.  https://proceedings.mlr.press/v267/hu25m.html

WU, Y. H., MA, L. H., LI, M. Z., ZHOU, J. M., LEUNG, H. F., HAO, J. Y., KING, I., ZHANG, Y. X. and NIE, J. Y., 2025. Reinforcing Question Answering Agents with Minimalist Policy Gradient Optimization. In: Multi-Agent Systems in the Era of Foundation Models: Opportunities, Challenges and Futures. ICML 2025 Workshop, Vancouver, Canada, 18 July 2025.  https://icml.cc/virtual/2025/49315

AHMAD, N., LEUNG, H. F. and FARNIA, F., 2025. VirtualHAR: Virtual Sensing Device and Correlation-Based Learning Approach for Multi-Wearable Sensing Device-Based Human Activity Recognition. IEEE Internet Things J., 12(13). IEEE, 23577–23597.  doi:10.1109/JIOT.2025.3555799

GUO, Y. J., JI, S. J., FANG, X. W., CHIU, D. K. W., CAO, N. and LEUNG, H. F., 2025. An Unsupervised Fake News Detection Framework Based on Structural Contrastive Learning. Cybersecurity, 8(41). SpringerOpen, 13 Pages.  doi:10.1186/s42400-024-00342-5

HU, X. Y., LEUNG, H. F. and FARNIA, F., 2025. A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models. In: Y. LI, S. MANDT, S. AGRAWAL, and E. KHAN, Eds., Proceedings of the 28^th International Conference on Artificial Intelligence and Statistics, AISTATS 2025, PMLR, Vol. 258. Phuket, Thailand, 3–5 May 2025. PMLR, 1864–1872. https://proceedings.mlr.press/v258/hu25a.html

LI, M. Z., YANG, C. H., XU, C. J., JIANG, X. H., QI, Y. Y., GUO, J., LEUNG, H. F. and KING, I., 2025. Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion. In L. CHIRUZZO, A. RITTER and L. WANG, Eds: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2025, Albuquerque, USA, 29 April – 4 May 2025. ACL, 4349–4363. doi:10.18653/v1/2025.naacl-long.221

LI, M. Z., YANG, C. H., XU, C. J., SONG, Z. X., JIANG, X. H., GUO, J., LEUNG, H. F. and KING, I., 2025. Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 39(11). Philadelphia, USA, 25 February – 4 March 2025. AAAI Press, 12102–12111.  doi:10.1609/aaai.v39i11.33318

2024

HU, X. Y., FARNIA, F. and LEUNG, H. F., 2024. An Information Theoretic Approach to Interaction-Grounded Learning. In: R. SALAKHUTDINOV, Z. KOLTER, K. HELLER, A. WELLER, N. OLIVER, J. SCARLETT and F. BERKENKAMP, Eds., Proceedings of the 41^st International Conference on Machine Learning, ICML 2024, Proceedings of Machine Learning Research, Vol. 235. Vienna, Austria, 21 – 27 July 2024. PMLR, Volume 235, 19198–19215.  https://proceedings.mlr.press/v235/hu24e.html

LI, M. Z., HU, M. D., KING, I. and LEUNG, H. F., 2024. The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing. In: K. DUH, H. GOMEZ and S. BETHARD, Eds, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, 16 – 21 June 2024. ACL, 6625–6638.  doi:10.18653/v1/2024.naacl-long.369

WU, X., CAI, Y. and LEUNG, H. F., 2024. Abstract-level Deductive Reasoning for Pre-trained Language Models. In: N. CALZOLARI, M. KAN, V. HOSTE, A. LENCI, S. SAKTI and N. XUE, Eds., Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024, Torino, Italy, 20 – 25 May 2024. ELRA and ICCL, 70–76.  https://aclanthology.org/2024.lrec-main.6/

ZHAO, Y. L., ZHAN, W. H., HU, X. Y., LEUNG, H. F., FARNIA, F., SUN, W. and LEE, J., 2024. Provably Efficient CVaR RL in Low-rank MDPs. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, 7 – 11 May 2024. OpenReview.net.  https://openreview.net/forum?id=9x6yrFAPnx.  Also appears in NeurIPS2023 Workshop on Mathematics of Modern Machine Learning (M3L). New Orleans, USA, 16December,2023.  https://openreview.net/forum?id=Vg6oMb7fbh

LEUNG, C. W., HU, S. Y. and LEUNG, H. F., 2024. The Stochastic Evolutionary Dynamics of Softmax Policy Gradient in Games. In: N. ALECHINA, V. DIGNUM, M. DASTANI and J.S. SICHMAN, Eds., Proceedings of the 23rd International Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’24, Auckland, New Zealand, 6 – 10 May 2024. IFAAMAS, 1101–1109.  https://dl.acm.org/doi/10.5555/3635637.3662966

ZENG, Y. S., WANG, G. H., REN, H. P., CAI, Y., LEUNG, H. F., LI, Q. and HUANG, Q. B., 2024. A Knowledge-Enhanced and Topic-Guided Domain Adaptation Model for Aspect-based Sentiment Analysis. IEEE Trans. Affect. Comput., 15(2). IEEE, 709–721.  doi:10.1109/TAFFC.2023.3292213

AHMAD, N. and LEUNG, H. F., 2024. HyperHAR: Inter-sensing Device Bilateral Correlations and Hyper-correlations Learning Approach for Wearable Sensing Device Based Human Activity Recognition. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 8(1). ACM, 1–29.  doi:10.1145/3643511

XU, J. Y., XIE, J. Y., CAI, Y., LIN, Z. H., LEUNG, H. F., LI, Q. and CHUA, T. S., 2024. Context-Aware Dynamic Word Embeddings for Aspect Term Extraction. IEEE Trans. Affect. Comput., 15(1). IEEE, 144–156.  doi:10.1109/TAFFC.2023.3262941

2023

HU, X. Y. and LEUNG, H. F., 2023. Provably (More) Sample-Efficient Offline RL with Options. In: A. OH, T. NEUMANN, A. GLOBERSON, K. SAENKO, M. HARDT and S. LEVINE, Eds., Advances in Neural Information Processing Systems, volume 36 (NeurIPS2023),New Orleans, USA, 10–16December,2023. Curran Associates, 68784–68797.  Electronic version provided by NeurIPS

HU, X. Y. and LEUNG, H. F., 2023. Provably Efficient Offline RL with Options (Extended Abstract). In: Proceedings of the 22nd International Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’23, London, United Kingdom, 29 May–2 June 2023. IFAAMS, 2592–2594.  Online article provided by ACM

REN, H. P., CAI, Y., LAU, R., LEUNG, H. F. and LI, Q., 2023. Granularity-aware Area Prototypical Network with Bimargin Loss for Few Shot Relation Classification. IEEE Trans. Knowl. Data Eng., 35(5). IEEE, 4852–4866.  doi:10.1109/TKDE.2022.3147455

HU, X. Y. and LEUNG, H. F., 2023. A Tighter Problem-Dependent Regret Bound for Risk-Sensitive Reinforcement Learning. In: F. RUIZ, J. DY, and J. van de MEENT, Eds., Proceedings of the 26^th International Conference on Artificial Intelligence and Statistics, AISTATS 2023, Proceedings of Machine Learning Research, volume 206. Valencia, Spain, 25–27 April 2023. PMLR, Volume 206, 5411–5437.  Online article provided by PMLR

WU, X., CAI, Y., LIAN, Z. T., LEUNG, H. F. and WANG, T., 2023. Generating Natural Language from Logic Expressions with Structural Representation. IEEE/ACM Trans. Audio Speech Lang. Process., 31. IEEE, 1499–1510.  doi:10.1109/TASLP.2023.3263784

AHMAD, N. and LEUNG, H. F., 2023. ALAE-TAE-CutMix⁺: Beyond the State-of-the-Art for Human Activity Recognition Using Wearable Sensors. In: 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom), Atlanta, USA, 13–17 March 2023. IEEE, 222–231.  doi:10.1109/PERCOM56429.2023.10099138