AIBullisharXiv – CS AI · Feb 277/105
🧠
K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
Researchers introduce K-Search, a new GPU kernel optimization framework that uses co-evolving world models with LLMs to significantly improve performance over existing methods. The system achieves up to 14.3x performance gains on complex kernels by decoupling high-level planning from low-level implementation, addressing limitations of current automated optimization approaches.