Skip to content

Author

Hao-Hang Qin

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses

Automated generation of LLM harnesses promises to improve inference through task specialization. Yet additional answer coverage can arise from repeated execution of the same program, making specialization difficult to identify. We introduce a controlled evaluation that separates answer coverage, repeatable task advanta...

Zi-Yang Xu, Haitian Zhong, Hao Zhou et al. · 0 citations

Code obfuscation against symbolic execution with mixed Boolean-arithmetic permutation

Code obfuscation is a fundamental technique for software protection and intellectual property defense, yet its effectiveness has been increasingly undermined by advances in symbolic execution and automated deobfuscation. Existing countermeasures based on path explosion, path divergence, or complex constraints suffer...

Mo-Xuan Wang, Hai-Yan Hu, Hao-Hang Qin et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.