Tiansi Dong

About

Dr Tiansi Dong is a researcher in the Department of Computer Science and Technology at the University of Cambridge. His research focuses on machine reasoning, aiming to innovate neural networks that achieve symbolic-level logical reasoning while preserving predictive power and ensuring explainability and reliability in real applications.

Selected publications

• Tiansi Dong, Mateja Jamnik, Pietro Liò (2026). Non-Zero Radius: The Missing Component of Neural Networks. ACM AI Leadership Summit. 2026.
• Tiansi Dong, Shizhu He, Yunfei Long (eds.) (2026). Proceedings of the Third Workshop on Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning@AAAI. Springer LNAI series as Volume 16779.
• Tiansi Dong, Mateja Jamnik, Pietro Liò (2025). Neural Reasoning for Sure Through Constructing Explainable Models. AAAI.
• Tiansi Dong, Writwick Das, Rafet Sifa (2025). Bridging Language and Scenes through Explicit 3-D Model Construction. NeusymBridge@COLING. (best paper award)
• Tiansi Dong, et. al., (2024). Word Sense Disambiguation as a Game of Neurosymbolic Darts. NeusyBridge@LREC-COLING.
• Tiansi Dong (2021). A Geometric Approach to the Unification of Symbolic Structures and Neural Networks. Springer-Nature.
• Tiansi Dong, et. al. (2019). Triple Classification Using Regions and Fine-Grained Entity Typing. AAAI.
• Tiansi Dong, et. al. (2019). Imposing Category Trees Onto Word-Embeddings Using A Geometric Construction, ICLR.
• Tiansi Dong (2012). Recognizing Variable Environment -- The Theory of Cognitive Prism, Spinger.
• Tiansi Dong (2008). A Comment on RCC: from RCC to RCC++, Journal of Philosophical Logic 37(4): 319-352.