← Search

Yu Xuejun

2 accepted papers

2026

Mathesis: Towards Formal Theorem Proving from Natural Languages

ICLR 2026poster

Recent advances in large language models (LLMs) show strong promise for formal reasoning. However, most LLM-based theorem provers remain constrained by the need for expert-written formal statements as inputs, limiting their applicability to real-world problems expressed in natural language. We addre…

Cited by 0SourcecodeScholar
2026

ProofFlow: A Dependency Graph Approach to Faithful Proof Autoformalization

ICLR 2026poster

Proof autoformalization, the task of translating natural language theorems and proofs into machine-verifiable code, is a critical step for integrating large language models into rigorous mathematical workflows. Current approaches focus on producing executable code, but they frequently fail to preser…

Cited by 0SourcecodeScholar