Welcome!

Hi, nice to meet you! I’m Xu Jundong, an incoming PhD Student at the National University of Singapore (NUS) CTIC lab, working under the supervision of Prof. Mong-Li Lee and Prof. Wynne Hsu. I am also mentored by Dr. Hao Fei. Previously, I earned a Master of Computing from NUS and a BSc from University College London (UCL).

My work focuses on enhancing the symbolic reasoning capabilities of AI systems. I aim to develop methods that enable AI to perform systematic, reliable, and deterministic inference, bridging the gap between data-driven learning and structured logical reasoning.

I actively seek interdisciplinary collaborations and welcome discussions with researchers who share an interest in AI, logic, and cognitive systems. Feel free to reach out via email to exchange ideas!

πŸ”₯ News

  • 2025.06: Β πŸŽ‰πŸŽ‰ The paper Aristotle has been selected as an oral presentation (8% of the accepted paper).
  • 2025.05: Β πŸŽ‰πŸŽ‰ The paper Aristotle has been accepted to ACL 2025 main conference.
  • 2025.04: Β πŸŽ‰πŸŽ‰ I got a PhD offer from NUS!
  • 2025.01: Β πŸŽ‰πŸŽ‰ I started working as a research assistant at NUS CTIC.
  • 2025.01: Β πŸŽ‰πŸŽ‰ I officially received my master’s degree.
  • 2024.12: Β πŸŽ‰πŸŽ‰ Our new paper Aristotle is released on Arxiv.
  • 2024.10: Β πŸŽ‰πŸŽ‰ One paper was accepted at the ACM MM Workshop on Multi-modal Misinformation Governance in the Era of Foundation Models.
  • 2024.05: Β πŸŽ‰πŸŽ‰ The paper SymbCoT has been accepted to the ACL 2024 main conference.

πŸ“ Publications

ACL 2025 Oral
sym

Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework

Jundong Xu, Hao Fei (Corresponding Author), Meng Luo, Qian Liu, Liangming Pan, William Yang Wang, Preslav Nakov, Mong-Li Lee, Wynne Hsu.

Project

  • This paper is about integrating a decompose-search-resolve framework based on symbolic logic to improve the reasoning chain using LLM.
ACL 2024 Main
sym

Faithful Logical Reasoning via Symbolic Chain-of-Thought

Jundong Xu, Hao Fei (Corresponding Author), Liangming Pan, Qian Liu, Mong-Li Lee, Wynne Hsu.

Project

  • This paper is about combining symbolic logical rules in the reasoning chain to improve logical reasoning in LLM.
ACM MM Workshop 2024
sym

Fine-grained Structural Hallucination Detection for Unified Visual Comprehension and Generation in Multimodal LLM

Hao Fei, Meng Luo, Jundong Xu, Shengqiong Wu, Wei Ji, Mong-Li Lee, Wynne Hsu.

πŸ“– Educations

  • 2025.08 - Present, PhD in Computer Science, National University of Singapore
  • 2023.01 - 2025.01, Master of Computing, National University of Singapore
  • 2019.09 - 2022.07, BSc Information Management, University College London

πŸ’¬ Invited Talks

  • 2025.05, Inviated to NICE (NLP Academic Exchange) to introduce ACL 2025 paper Aristotle. | [video]
  • 2024.06, Inviated to NICE (NLP Academic Exchange) to introduce ACL 2024 paper SymbCoT. | [video]

πŸ’» Academic Services

  • Reviewer: ACL (2025), ICLR (2025), EMNLP (2025), ACM MM (2024, 2025), Neurocomputing (2024, 2025), NLPCC 2024
  • Volunteer: ACL 2024

Miscellaneous

I love sports, especially basketball, tennis, and skiing. I’m a big fan of the Golden State Warriors and Stephen Curry, and I also admire Roger Federer. I enjoy reading books, especially science fiction and psychology. And some of my favorites include Narcissus and Goldmund and The Three-Body. I also love watching movies. Some of my favorites are Fight Club by David Fincher and A Confucian Confusion by Edward Yang.