Skip to content

Honghua Dong (董宏华) Your Image Description


About Me

I am currently a Ph.D. student at University of Toronto, adviced by Prof. Xujie Si, Prof. Chris J. Maddison and Prof. Jimmy Ba. I have graduated from IIIS, Tsinghua University (YaoClass) in 2019, major in computer science.

Research Interests

My Current research interest is in developing Language Model Agents.

I am broadly interested in artificial intelligence and have also worked on various topics including Reasoning, Graph Neural Networks, Reinforcement Learning and Computer Vision.

Selected Projects

  • Yangjun Ruan*, Honghua Dong*, Andrew Wang, Silviu Pitis, Yongchao Zhou, Jimmy Ba, Yann Dubois, Chris J Maddison, and Tatsunori Hashimoto. Identifying the risks of lm agents with an lm-emulated sandbox. In The Twelfth International Conference on Learning Representations, 2024. [Spotlight]

    Paper | Webpage | Code | Twitter

  • Honghua Dong*, Jiawei Xu*, Yu Yang*, Rui Zhao, Shiwen Wu, Chun Yuan, Xiu Li, Chris J Maddison, and Lei Han. Megraph: Capturing long-range interactions by alternating local and hierarchical aggregation on multi-scaled graph hierarchy. In The Thirty-seventh Advances in Neural Information Processing Systems 2023.

    Paper | Webpage | Code | Poster | OpenReview

  • Honghua Dong*, Jiayuan Mao*, Tian Lin, Chong Wang, Lihong Li, and Denny Zhou. Neural logic machines. In the 7th International Conference on Learning Representations (ICLR), 2019.

    Paper | Webpage | Code | OpenReview

  • Yuhuai Wu*, Honghua Dong*, Roger Grosse, and Jimmy Ba. The scattering compositional learner: Discovering objects, attributes, relationships in analogical reasoning. arXiv preprint arXiv:2007.04212, 2020.

    Paper | Code

See a full list



  • I have served as a reviewer for conferences including NeurIPS, ICLR and ICML.


Last updated April 2024.