Abhinav Bhatelé

Predicting Cross-Architecture Performance of Parallel Programs

2024

A variety of hardware architectures, both CPUs and GPUs, are used today to build supercomputers and parallel clusters. Often times, users can choose which hardware platform they want to run on. Modern scientific workflows have …

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

2024 · arXiv (Cornell University)

Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-token training objective that we call the goldfish loss. During …