Research

2025

• Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
  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
  

• Frontier LLMs Still Struggle with Simple Reasoning Tasks
  Alan Malek*, Jiawei Ge*, Nevena Lazic, Chi Jin, András György, Csaba Szepesvári (*=equal contribution)
  

• Principled Out-of-Distribution Generalization via Simplicity
  Jiawei Ge, Amanda Wang, Shange Tang, Chi Jin
  

• Covariates-Adjusted Mixed-Membership Estimation: A Novel Network Model with Optimal Guarantees
  Jianqing Fan, Jiawei Ge, Jikai Hou (alphabetical order)
  

• MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations
  Kaixuan Huang, Jiacheng Guo, Zihao Li, Xiang Ji, Jiawei Ge, Wenzhe Li, Yingqing Guo, Tianle Cai, Hui Yuan, Runzhe Wang, Yue Wu, Ming Yin, Shange Tang, Yangsibo Huang, Chi Jin, Xinyun Chen, Chiyuan Zhang, Mengdi Wang
  Forty-Second International Conference on Machine Learning (ICML 2025)
  

2024

• Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games
  Jiawei Ge*, Yuanhao Wang*, Wenzhe Li, Chi Jin (*=equal contribution)
  Forty-Second International Conference on Machine Learning (ICML 2025)
  

• Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
  Jiawei Ge*, Debarghya Mukherjee*, Jianqing Fan (*=equal contribution)
  The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
  

2023

• Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
  Jiawei Ge*, Shange Tang*, Jianqing Fan, Cong Ma, Chi Jin (*=equal contribution)
  International Conference on Learning Representations (ICLR), 2024
  

• UTOPIA: Universally Trainable Optimal Prediction Intervals Aggregation
  Jianqing Fan, Jiawei Ge, Debarghya Mukherjee (alphabetical order)
  

• On the Provable Advantage of Unsupervised Pretraining
  Jiawei Ge*, Shange Tang*, Jianqing Fan, Chi Jin (*=equal contribution)
  International Conference on Learning Representations (ICLR), 2024 (Spotlight)