Jui-Hui Chung 鍾瑞輝

The Program in Applied and Computational Mathematics, Princeton University
Fine Hall, Princeton NJ 08540
email: jc1220 AT math.princeton.edu

I'm a PhD student in the Program in Applied and Computational Mathematics at Princeton University, advised by Jacob Shapiro. I'm interested in mathematical physics of topological insulators. Recently, I'm working on automated theorem proving with LLMs, advised by Chi Jin. I received my undergrad and master degrees in physics from National Taiwan University, where I was advised by Ying-Jer Kao, and worked on computational physics.

Automated theorem proving with LLMs

• Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement (2026)
  Jui-Hui Chung*, Ziyang Cai*, Zihao Li, Qishuo Yin, Rohit Agarwal, Simon Park, Rodrigo Porto, Narutatsu Ri, Ziran Yang
  Shange Tang, Xingyu Dang, Hongzhou Lin, Mengdi Wang, Danqi Chen, Chi Jin, Liam H Fowl*, Sanjeev Arora
  Preprint. [Project Page] [arXiv]
• Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover (2026)
  Jui-Hui Chung, Hongzhou Lin, Lai Jiang, Shange Tang, Chi Jin
  Preprint. [arXiv]
• Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction (2025)
  Yong Lin*, Shange Tang*, Bohan Lyu*, Ziran Yang*, Jui-Hui Chung*, Haoyu Zhao*, Lai Jiang*, Yihan Geng*
  Jiawei Ge, Jingruo Sun, Jiayun Wu, Jiri Gesi, Ximing Lu, David Acuna, Kaiyu Yang, Hongzhou Lin*, Yejin Choi, Danqi Chen, Sanjeev Arora, Chi Jin*
  International Conference on Learning Representations (ICLR 2026). [Conference]

Machine learning

• GrepSeek: Training Search Agents for Direct Corpus Interaction (2026)
  Alireza Salemi, Chang Zeng, Atharva Nijasure, Jui-Hui Chung, Razieh Rahimi, Fernando Diaz, Hamed Zamani
  Preprint. [arXiv]
• High-Order Flow Matching: Unified Framework and Sharp Statistical Rates (2025)
  Maojiang Su, Jerry Yao-Chieh Hu, Yi-Chen Lee, Ning Zhu, Jui-Hui Chung, Shang Wu, Zhao Song, Minshuo Chen, Han Liu
  Advances in Neural Information Processing Systems (NeurIPS 2025). [Conference]

Mathematical physics

• Topological Classification of Insulators: III. Non-interacting Spectrally-Gapped Systems in All Dimensions (2026)
  with Jacob Shapiro
  Preprint. [arXiv]
• Essentially Commuting with a Unitary (2025)
  with Jacob Shapiro
  J. Funct. Anal. (2026). [Journal] [arXiv]
• Topological Classification of Insulators: II. Quasi-Two-Dimensional Locality (2024)
  with Jacob Shapiro
  Preprint. [arXiv]
• Topological Classification of Insulators: I. Non-interacting Spectrally-Gapped One-Dimensional Systems (2023)
  with Jacob Shapiro
  Adv. Math. 480, 110486 (2025). [Journal] [arXiv]

Older work (in physics)

• Neural Monte Carlo renormalization group (2021)
  Jui-Hui Chung, Ying-Jer Kao
  Phys. Rev. Research 3, 023230 (2021). [Journal] [arXiv]
• Optimal Real-Space Renormalization-Group Transformations with Artificial Neural Networks (2019)
  Jui-Hui Chung, Ying-Jer Kao
  Workshop on Machine Learning and the Physical Sciences (NeurIPS 2019). [Workshop]
• Electronic Properties of Möbius Cyclacenes Studied by Thermally-Assisted-Occupation Density Functional Theory (2019)
  Jui-Hui Chung, Jeng-Da Chai
  Sci Rep 9, 2907 (2019). [Journal]
• Self-consistent determination of the fictitious temperature in thermally-assisted-occupation density functional theory (2017)
  Chih-Ying Lin, Kerwin Hui, Jui-Hui Chung, Jeng-Da Chai
  RSC Adv 7, 50496 (2017). [Journal]

Last updated: June 4, 2026.