Yue Shui

Baidu, Inc

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Code Generation & Program Synthesis (1)

Frequent co-authors

Chenyu Ma (1)Hangfei Xu (1)

Papers (1)

Jul 20, 2026

Harness Engineering for LLM-Driven GPU Kernel Generation

Expert-guided LLMs can achieve up to 29.68x speedups in GPU kernel performance, highlighting the critical role of human knowledge in AI-driven optimization.

Yue Shui, Chenyu Ma, Hangfei Xu

Code Generation & Program Synthesis

Search

Yue Shui

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)