Kangjie Bao — accepted AI-conference papers

2026

Let's Explore Step by Step: Generating Provable Formal Statements with Deductive Exploration

Qi Liu, Kangjie Bao, Yue Yang, Xinhao Zheng, Renqiu Xia, Qinxiang Cao +1

ICLR 2026poster

Mathematical problem synthesis shows promise in resolving data exhaustion, contamination, and leakage for AI training and evaluation. Despite enormous efforts, an **expressiveness-validity-complexity trilemma** remains an open question. Existing methods either lack whole-process verifiability, are c…

Cited by 0 Source ↗Scholar ↗

2025

ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data

Xiaoyang Liu, Kangjie Bao, Jiashuo Zhang, Yunqi Liu, Yu Chen, Yuntian Liu +2

NeurIPS 2025poster

Autoformalization, the automatic translation of mathematical content from natural language into machine-verifiable formal languages, has seen significant progress driven by advances in large language models (LLMs). Nonetheless, a primary barrier to further improvements is the limited availability of…

Cited by 0 Source ↗code ↗Scholar ↗