activity
20242026
most citedCode Repair with LLMs gives an Exploration-Exploitation Tradeoff

3 citations · 6 across the 9 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe

Tara Saba, Zhiyang Chen, Jikai Jason Li +3

High-performance GPU kernels are critical to modern machine learning systems, yet developing them remains a manual, expert-driven process. Recent work has explored using LLMs to au…