Tianshi Zheng 郑天石 Stone
Bibliography
Hello there!
I’m a Ph.D. student in Computer Science at the Hong Kong University of Science and Technology (HKUST) starting from 2024, advised by Prof. Yangqiu Song. I’m also a research intern at NVIDIA AI Technology Center. Prior to that, I obtained two bachelor’s degrees in Computer Science and General Business Management from the Dual Degree Program at the same institution with the highest distinction.
News
- Aug 2025: Two research papers accepted to EMNLP 2025 Main Conference!
- May 2025: Our survey paper on Large Language Models in Scientific Discovery has been published, with an awesome github repository: Awesome-LLM-Scientific-Discovery . We welcome community contributions through pull requests!
- May 2025: Four research papers accepted to ACL 2025!
Research Interests
I am generally interested in Machine Learning and Natural Language Processing.
RI1. Logical Inference Towards Explanatory Hypothesis from Observations.
It naturally bridges:
- Abductive Reasoning: Explanatory Hypothesis Generation (LogiDynamics, AbductiveKGR, Controllable AKGR)
- Inductive Reasoning: Learning from Contextual Instances (The Curse of CoT, Robust Rule Induction, Legal Rule Induction)
- Deductive Reasoning: Entailment Verification with Uncertainty (FOL-Entailment)
RI2. AI-Driven Autonomous Scientific Discovery and Research [LLM-SD Survey].
My focus is on accelerating the autonomy of AI agents, in tasks ranging from general scientific discovery to machine learning research.
- Self-Improving / Self-Evolving Optimization for Autonomous R&D
- Interactive Environments for Generalizable Scientific Discovery with LLM Agents
I’ve been also working on complex logical reasoning under diverse modalities and scenarios (SQE, CLR-Fact, KnowShiftQA).
Awards
- Hong Kong PhD Fellowship 2024
- HKUST RedBird PhD Scholarship 2024
- HKUST Academic Achievement Medal (~top 1% graduate)
- HKUST Dean's Lists (7 semesters)
Academic Service
Conference Reviewer: ACL Rolling Review (2023, 2024, 2025), EMNLP 2023, KDD 2024, NLPCC 2024, ICLR 2025, COLM 2025