Dongcai Lu — accepted AI-conference papers

2026

Mathesis: Towards Formal Theorem Proving from Natural Languages

Yu Xuejun, Jianyuan Zhong, Zijin Feng, Pengyi Zhai, Roozbeh Yousefzadeh, Wei Chong Ng +14

ICLR 2026poster

Recent advances in large language models (LLMs) show strong promise for formal reasoning. However, most LLM-based theorem provers remain constrained by the need for expert-written formal statements as inputs, limiting their applicability to real-world problems expressed in natural language. We addre…

Cited by 0 Source ↗code ↗Scholar ↗

2017

Leveraging commonsense reasoning and multimodal perception for robot spoken dialog systems

Dongcai Lu, Shiqi Zhang, Peter Stone, Xiaoping Chen

IROS 2017poster

Probabilistic graphical models, such as partially observable Markov decision processes (POMDPs), have been used in stochastic spoken dialog systems to handle the inherent uncertainty in speech recognition and language understanding. Such dialog systems suffer from the fact that only a relatively sma…

Cited by 19 Source ↗Scholar ↗