Haofeng Li
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper measures the prevalence of recurring vulnerability patterns (variants) across multiple AI infrastructure repositories and proposes INFRASCOPE, a framework to automatically detect these variants.
This paper introduces decode-time grammars to ensure grammatical and semantic correctness of code generated by large language models, particularly for low-resource programming surfaces.
Papers
Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments
Shuoming Zhang, Ruiyuan Xu, Haofeng Li, Qiuchu Yu +6 more
This paper introduces decode-time grammars to ensure grammatical and semantic correctness of code generated by large language models, particularly for low-resource programming surfaces.