![]() |
田 时 雨 |
Currently I am a first-year graduate student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by professor Zhi-Hua Zhou. I got my B.Sc. degree in College of Computer Science in June 2024 from Chongqing University, where I work closely with Prof. Lei Feng. In the same year, I was admitted to pursue for a Ph.D. degree in Nanjing University without entrance examination.
My long-term goal is to develop robust and trustworthy AI systems. Currently, my research centers on Neuro-Symbolic AI, with a particular focus on enhancing the reasoning capabilities of LLMs through the integration of symbolic tools and knowledge—especially in the area of spatial reasoning. Previously, I worked on learning under limited supervision, including settings with label noise and partial labels.
LawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLM
[arxiv]
Zhi Zhou, Kun-Yang Yu, Shi-Yu Tian, Xiao-Wen Yang, Jiang-Xin Shi, Peng-Xiao Song, Yi-Xuan Jin, Lan-Zhe Guo, Yu-Feng Li.
Proceedings of the 13th International Conference on Learning Representations, Open Science for Foundation Models Workshop
(ICLR 2025 SCI-FM Workshop)
CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning
[pdf]
[code]
[poster]
Shi-Yu Tian, Hong-Xin Wei, Yi-Qun Wang, Lei Feng.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024)
Rethinking Evaluation for Multi-Label Drug-Drug Interaction Prediction
[paper]
Shi-Yu Tian, Zhi Zhou, Xin Su, Yu-Feng Li.
Frontiers of Computer Science (FCS)
Automated Text-to-Table for Reasoning-Intensive Table QA: Pipeline Design and Benchmarking Insights
[arxiv]
[benchmark]
[code]
Shi-Yu Tian*, Zhi Zhou*, Wei Dong, Ming Yang, Kun-Yang Yu, Zi-Jian Cheng, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2025.
VC Search: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning
[arxiv]
[dataset]
Shi-Yu Tian*, Zhi Zhou*, Kun-Yang Yu, Ming Yang, Lin-Han Jia, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2025.
Email:
tiansy@lamda.nju.edu.cn