Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Kevin: Multi-Turn RL for Generating CUDA Kernels
Carlo Baronio, Pietro Marsella, Ben Pan +2
Writing GPU kernels is a challenging task and critical for AI systems' efficiency. It is also highly iterative: domain experts write code and improve performance through execution…
cs.LG2025
Data Unlearning in Diffusion Models
Silas Alberti, Kenan Hasanaliyev, Manav Shah +1
Recent work has shown that diffusion models memorize and reproduce training data examples. At the same time, large copyright lawsuits and legislation such as GDPR have highlighted…