Zhiyuan Wang

Zhiyuan Wang

CityUHK

Hi, I’m Zhiyuan Wang. I am a first-year PhD student in the Department of Data Science at City University of Hong Kong (CityUHK), and I am very fortunate to be advised by Prof. Kaidi Xu. Previously, I received my master’s degree in Computer Science and Technology at the University of Electronic Science and Technology of China (UESTC), where I was advised by Prof. Xiaoshuang Shi in the Trust Intelligent Medical (TIM) Lab.

My research interests include Uncertainty Quantification and Conformal Prediction.

I am very excited about potential collaboration opportunities! If you share similar research interests and find my work interesting, I warmly welcome you to contact me via email!

🤖 Research

  • Hallucination detection via uncertainty decomposition and quantification;
  • Task-specific risk control via split conformal prediction, confidence interval calibration, and linear expectation constraint.

🔥 News

  • 2026.08: Two papers were accepted by EMNLP 2026.
  • 2026.06: One paper was accepted by MICCAI 2026.
  • 2026.05: Passed the Outstanding Master’s Thesis selection defense and received unanimous “Excellent” ratings.
  • 2026.05: Admitted to the PhD program in Data Science at CityUHK.
  • 2026.05: Two papers were accepted by ICML 2026.
  • 2025.11: One paper was accepted by AAAI 2026.
  • 2025.10: Awarded the National Scholarship for Graduate Students.
  • 2025.09: Invited to serve as ICLR 2026 AC.
  • 2025.05: One paper was accepted by ACL 2025.
  • 2025.02: One paper was accepted by ICLR 2025.
  • 2025.01: One paper was accepted by Engineering Applications of Artificial Intelligence.

📚 Selected Publications

(*corresponding author; $^\dagger$equal contribution)

  1. Zijun Jia, Yuanchang Ye, Sen Jia, Yiyao Qian, Haoning Wang, Baojie Chen, Diyin Tang, Jinsong Yu*, Zhiyuan Wang*. BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation. Conference on Empirical Methods in Natural Language Processing (EMNLP), Findings, 2026.

  2. Anqi Hu, Zijun Jia, Zhiyuan Wang*, Bo Fu*. MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition. Conference on Empirical Methods in Natural Language Processing (EMNLP), Main, 2026.

  3. Binyu Tan$^\dagger$, Zhiyuan Wang$^\dagger$, Jinhao Duan, Kaidi Xu, Heng Tao Shen, Xiaoshuang Shi, Fumin Shen. Conformal 3D Lesion Segmentation with Balanced Risk Control. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2026.

  4. Zhiyuan Wang, Aniri, Tianlong Chen, Yue Zhang, Heng Tao Shen, Xiaoshuang Shi, Kaidi Xu. LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems. International Conference on Machine Learning (ICML), Regular, 2026.

  5. Zhiyuan Wang, Jinhao Duan, Qingni Wang, Xiaofeng Zhu, Tianlong Chen, Xiaoshuang Shi, Kaidi Xu. COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees. Annual AAAI Conference on Artificial Intelligence (AAAI), Poster, 2026.

  6. Zhiyuan Wang$^\dagger$, Qingni Wang$^\dagger$, Yue Zhang, Tianlong Chen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi Xu. SConU: Selective Conformal Uncertainty in Large Language Models. Annual Meeting of the Association for Computational Linguistics (ACL), Main, 2025.

  7. Zhiyuan Wang, Jinhao Duan, Chenxi Yuan, Qingyu Chen, Tianlong Chen, Yue Zhang, Ren Wang, Xiaoshuang Shi, Kaidi Xu. Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications. Engineering Applications of Artificial Intelligence (EAAI), 2025.

  8. Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Xiaoshuang Shi, Kaidi Xu, Hengtao Shen, Xiaofeng Zhu. ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees. Conference on Empirical Methods in Natural Language Processing (EMNLP), Findings, 2024.

🏆 Honors and Awards

  • National Scholarship (2021, 2022, 2025)
  • UESTC “Academic Youth” Graduate Student Honor Award (2025)
  • UESTC Outstanding Graduate Students (2024, 2025×2)
  • UESTC Scholarship for Outstanding Students (2023-2025)
  • CQUPT Honours Degrees (2023)
  • Provincial Merit Student (2022)
  • CQUPT First-class Scholarship (2020-2022)
  • CQUPT Merit Student (2020-2022)

👨‍🎓 Education

  • Sep 2026 - Present, City University of Hong Kong (CityUHK), Doctor of Data Science.
  • Sep 2023 - Jun 2026, University of Electronic Science and Technology of China (UESTC), Master of Computer Science and Technology.
  • Sep 2019 - Jun 2023, Chongqing University of Posts and Telecommunications (CQUPT), Bachelor of Internet of Things Engineering (Hons, Rank 1/154).

💬 Academic Services

Program Committee Member of Conferences: ICLR, NeurIPS, ACL, EMNLP, EACL, AACL, AAAI, ACM MM, IJCAI, ICASSP, CIKM

Journal Reviewer: IEEE Transactions on Image Processing (TIP), Transactions on Machine Learning Research (TMLR), Neural Networks (NN), ACM Computing Surveys (CSUR), Array, Information Processing and Management (IPM), Chemometrics and Intelligent Laboratory Systems (CILS)