8 papers
Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments
Shuoming Zhang, Ruiyuan Xu, Haofeng Li +7
Large language models now write a growing share of the world's code, increasingly inside agents and serving systems that compile, execute, or dispatch generated code without line-b…
Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages
Shuoming Zhang, Qiuchu Yu, Yangyu Zhang +6
LLM-based agents are increasingly used to generate GPU kernels, but they often know what optimizations to try without knowing when those optimizations are sound. We introduce KLine…
When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
Shuoming Zhang, Jiacheng Zhao, Hanyuan Dong +9
Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers. Large Language Models (LLMs) increasingly serve as tooling pla…
SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
Yifan Zhou, Zhentao Zhang, Ziming Cheng +8
As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, re…
The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers
Shuoming Zhang, Jiacheng Zhao, Qiuchu Yu +4
This survey has provided a systematic overview of the emerging field of LLM-enabled compilation by addressing several key research questions. We first answered how LLMs are being i…
QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
Changxin Ke, Rui Zhang, Shuo Wang +11
The rise of GPU-based high-performance computing (HPC) has driven the widespread adoption of parallel programming models such as CUDA. Yet, the inherent complexity of parallel prog…