4 papers
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Ornith Team, Xiaoya Li, Guoyin Wang +3
Competitive programming remains one of the last few human strongholds in coding against AI. The best AI system to date still underperforms the best humans competitive programming:…
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
Songqiao Su, Xiaoya Li, Albert Wang +3
In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multi…
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
Xiaoya Li, Albert Wang, Guoyin Wang +2
Approximate nearest-neighbor search (ANNS) algorithms have become increasingly critical for recent AI applications, particularly in retrieval-augmented generation (RAG) and agent-b…
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Xiaoya Li, Albert Wang, Guoyin Wang +2
The exponential growth in demand for GPU computing resources has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for c…