About Me
Currently, I am a second-year graduate student of School of Artificial Intelligence in Nanjing University advised by Professor Yu-Feng Li and a member of LAMDA Group, led by professor Zhi-Hua Zhou.
I got my B.Sc. degree in Department of Computer Science and Technology in June 2023 from Nanjing University. In the same year, I was admitted to pursue a Ph.D. degree in Nanjing University without entrance examination.
Research Interests
My research interests include Machine Learning and Artificial General Intelligence (AGI). Currently, I am focusing on the subfields:
- AI4Math: applying AI techniques to mathematical problem solving and research
- Reasoning in LLMs: improving the reasoning capability of large language models
- Neural Symbolic Integration: integrating the power of machine learning and logical reasoning to boost the reasoning and planning capabilities of the AI system
News
🤖 [Feb 2025] Our paper “Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models” is available on arXiv! We have released our code and dataset!
🎉 [Jan 2025] CARTS is accepted by ICLR2025.
Publication
(* denotes the co-first authors)
Conference Papers
CARTS: Advancing Neural Theorem Proving with Diversified Tactic Calibration and Bias-Resistant Tree Search. [PDF] [Webpage]
Xiao-Wen Yang, Zhi Zhou, Haiming Wang, Aoxue Li, Wen-Da Wei, Hui Jin, Zhenguo Li, Yu-Feng Li.
The 13th International Conference on Learning Representations (ICLR 2025).Abductive Learning for Neuro-Symbolic Grounded Imitation. [PDF] [Webpage]
Jie-Jing Shao*, Hao-Ran Hao*, Xiao-Wen Yang, Yu-Feng Li.
The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD’25).Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts. [PDF] [Webpage]
Xiao-Wen Yang, Wen-Da Wei, Jie-Jing Shao, Yu-Feng Li, Zhi-Hua Zhou.
The 41st International Conference on Machine Learning (ICML 2024).Safe Abductive Learning in the Presence of Inaccurate Rules. [PDF]
Xiao-Wen Yang, Jie-Jing Shao, Wei-Wei Tu, Yu-Feng Li, Wang-Zhou Dai, Zhi-Hua Zhou.
The 38th AAAI Conference on Artificial Intelligence (AAAI 2024).LOG: Active Model Adaptation for Label-Efficient OOD Generalization. [PDF]
Jie-Jing Shao, Lan-Zhe Guo, Xiao-Wen Yang, Yu-Feng Li.
The 36th Conference on Neural Information Processing Systems (NeurIPS 2022).
Journal Papers
- Open-Set Learning under Covariate Shift. [PDF]
Jie-Jing Shao*, Xiao-Wen Yang*, Lan-Zhe Guo.
Machine Learning (ML’22).
Other Papers
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models. [PDF] [Webpage]
Xiao-Wen Yang, Xuan-Yi Zhu, Wen-Da Wei, Ding-Chu Zhang, Jie-Jing Shao, Zhi Zhou, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2025.LawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLM. [PDF]
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.
Preprint, 2025.ChinaTravel: A Real-World Benchmark for Language Agent in Chinese Travel Planning. [PDF] [Webpage]
Jie-Jing Shao*, Xiao-Wen Yang*, Bo-Wen Zhang*, Bai-Zhi Chen,
Wen-Da Wei, Guohao Cai, Zhenhua Dong, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2024.Investigating the Limitation of CLIP Models: The Worst-Performing Categories. [PDF]
Jie-Jing Shao*, Jiang-Xin Shi*, Xiao-Wen Yang*, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2023.Lightweight Retrieval Tuning for Black-Box Language Models. [PDF]
Xiao-Wen Yang, Hong-Jie You, Peng-Xiao Song, Hao-Ran Hao, Jie-Jing Shao, Yu-Feng Li.
NeurIPS’23 ENSLP Workshop.
Software
- LawGPT: A Large Language Model in the Legal Domain. [GitHub]
Honor
- National Scholarship, Nanjing University, Oct 2024
- Outstanding Student, Nanjing University, Nov 2024
- President’s Scholarship, Nanjing University, Oct 2023
- Outstanding Graduate, Nanjing University, Jun 2023
Academic Service
Reviewer for:
- AAAI 2024, 2025
- ICLR 2024, 2025
- ICML 2024, 2025
- NeurIPS 2023, 2024
- ACL Rolling Review 2024
Meta Reviewer for IJCAI 2025