Associate Professor, Institute of Computing Technology, Chinese Academy of Sciences
3 papers at NeurIPS 2025
We introduce NeuComBack, a novel benchmark for Neural Compilation, and propose an automatic prompt learning method that significantly improves both correctness and optimization of LLM-generated assembly.
This paper introduces MigGPT, a novel framework that leverages large language models and a code fingerprint structure to automate the migration and maintenance of out-of-tree Linux kernel patches.