← Search

Jianan Yao

2 accepted papers

2026

EXVERUS: Verus Proof Repair via Counterexample Reasoning

ICML 2026poster

Large Language Models (LLMs) have shown promising results in automating formal verification. However, existing approaches treat proof generation as a static, end-to-end prediction over source code, relying on limited verifier feedback and lacking access to concrete program behaviors. We present EXVE…

Cited by 0SourceScholar
2020

CLN2INV: Learning Loop Invariants with Continuous Logic Networks

ICLR 2020poster

Program verification offers a framework for ensuring program correctness and therefore systematically eliminating different classes of bugs. Inferring loop invariants is one of the main challenges behind automated verification of real-world programs which often contain many loops. In this paper, we…

Cited by 64SourceScholar