Jiawei Ge

I am a fifth-year Ph.D. student in the Department of Operations Research and Financial Engineering at Princeton University under the supervision of Professor Jianqing Fan and Professor Chi Jin. Before coming to Princeton, I received my bachelor's degree from School of Mathematics at Fudan University in 2021. My research focuses on developing statistical foundations and efficient algorithms that turn vast, heterogeneous data into trustworthy AI systems. E-mail: jg5300 [@] princeton [DOT] edu Google Scholar, CV Research interests LLMs understanding; Unsupervised pretraining; Out-of-distribution generalization (OOD); Benchmarking LLMs; Networks; Uncertainty quantification.

News

• I'm honored to receive the School of Engineering and Applied Science Award for Excellence. (Sep, 2024)

Featured projects

• Developing reliable and interpretable agents
  

  • Ge, J., Tang, S., Fan, J. and Jin, C., 2023. On the Provable Advantage of Unsupervised Pretraining. ICLR 2024.

  • Ge, J., Tang, S., Fan, J., Ma, C. and Jin, C., 2023. Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift. ICLR 2024.

  • Ge, J., Wang, A., Tang, S. and Jin, C., 2025. Principled Out-of-Distribution Generalization via Simplicity. arXiv preprint arXiv:2505.22622.

  • Ge, J., Wang, Y., Li, W. and Jin, C., 2024. Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games. ICML 2025.

  • Huang, K., Guo, J., Li, Z., Ji, X., Ge, J., Li, W., Guo, Y., Cai, T., Yuan, H., Wang, R. and Wu, Y., 2025. MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations. ICML 2025.

  • Malek, A., Ge, J., Jin, C., György, A. and Szepesvári, C., 2025. Frontier LLMs Still Struggle with Simple Reasoning Tasks. arXiv preprint arXiv:2507.07313.

  • Lin, Y., Tang, S., Lyu, B., Yang, Z., Chung, J.H., Zhao, H., Jiang, L., Geng, Y., Ge, J., Sun, J. and Wu, J., 2025. Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction. arXiv preprint arXiv:2508.03613.

• Network modeling
  

  • Fan, J., Ge, J. and Hou, J., 2025. Covariates-Adjusted Mixed-Membership Estimation: A Novel Network Model with Optimal Guarantees. arXiv preprint arXiv:2502.06671.

• Uncertainty quantification
  

  • Fan, J., Ge, J. and Mukherjee, D., 2023. UTOPIA: Universally Trainable Optimal Prediction Intervals Aggregation. arXiv preprint arXiv:2306.16549.

  • Ge, J., Mukherjee, D. and Fan, J., 2024. Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shiftt. NeurIPS 2024.