profile_picture
Xiangqi (Shawn) Wang
I am seeking potential research collaborations and the position of industry research intern. If you are interested, please contact me.,
xwang76@nd.edu

I’m a first-year PhD student in MINE Lab of Computer Science and Engineering (CSE) at the University of Notre Dame began from Fall 2024, supervised by Prof. Xiangliang Zhang. Previously, I was fortunate to be advised by Prof.Qi Liu in USTC and remotely supervised by Prof. Huazheng Wang and Jian Kang. I also did research on causal inference mentored by Prof. Zhuoran Yang.

I am deeply interested in large language models (LLMs)—especially reinforcement learning (RL) for LLMs, reasoning capabilities, and foundational problems such as knowledge graphs and bandit algorithms. My research designs learning frameworks that strengthen LLM reasoning and decision-making, informed by graph representation and online learning, while advancing trustworthy AI principles (robustness, reliability, transparency). I also care about the social impact of AI, aiming to translate technical progress into safe, equitable, and beneficial real-world applications.

Interests

  • Large Language Models
  • Reinforcement Learning
  • LLM Reasoning
  • Causal Inference
  • Bandit Algorithms

Academia

University of Notre Dame
2024 - present
Ph.D. Student CSE
University of Science and Technology of China
2020 - 2024
B.Sc. CSE
graduated with first class honor from School of the Gifted Young

News

news section subtitle
  • Check our research of causal enhanced RL on LLM! , Sep 2025.
  • One First-Author Paper is accepted by NeurIPS 2025 as Spotlight! , Sep 2025.
  • One Paper is accepted by EMNLP 2025! , Sep 2025.
  • One Paper is accepted by COLM 2025! , Auf. 2025.
  • One First-Author Paper is accepted by TMLR! , June. 2025.
  • One Paper is accepted by ACL! , May. 2025.
  • One First-Author Paper is accepted by WSDM! , Feb. 2025.

Recent Publications

Custom Subtitle: see my google scholar for the latest list
Causally-Enhanced Reinforcement Policy Optimization, 2025, Under Review
Xiangqi Wang , Y. Huang , Y. Zhou , X. Luo , K. Guo , X. Zhang
AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking on Large Language Models, 2025, NeurIPS Spolight
Xiangqi Wang , Y. Huang , Y. Wang , X. Luo , K. Guo , Y. Zhou , X. Zhang
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective, 2025, arXiv preprint arXiv:2502.14296
Y. Huang , C. Gao , S. Wu , H. Wang , Xiangqi Wang , Y. Zhou , Y. Wang , J. Ye , J. Shi
Fair Online Influence Maximization, 2025, Transactions on Machine Learning Research (TMLR)
Xiangqi Wang , S. Zhang , J. E. A. Escamilla , Q. Wu , X. Zhang , J. Kang , H. Wang
WildlifeLookup: A Chatbot Facilitating Wildlife Management with Accessible Data and Insights, 2025, Proceedings of the 18th ACM International Conference on Web Search and Data Mining (WSDM)
Xiangqi Wang , T. Yang , J. Rohr , B. Scheffers , N. Chawla , X. Zhang
AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?, 2024, arXiv preprint arXiv:2410.21259
H. Bao , Y. Huang , Y. Wang , J. Ye , Xiangqi Wang , X. Chen , Y. Zhao , T. Zhou
CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP, 2024, ACL
T. Yang , L. Dai , Xiangqi Wang , M. Cheng , Y. Tian , X. Zhang
Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?, 2024, COLM
Y. Huang , Z. Yuan , Y. Zhou , K. Guo , Xiangqi Wang , H. Zhuang , W. Sun , L. Sun
NS4AR: A New, Focused on Sampling Areas Sampling Method in Graphical Recommendation Systems, 2023, arXiv preprint arXiv:2307.07321
Xiangqi Wang , D. Aishan , Q. Liu

Projects

Custom Subtitle: see my github for the complete list
Knowledge Network of Wildlife Query Website
Modified verl framework with Jacobian Causal Scores