Anat Kleiman

I am a 4th year PhD candidate in Computer Science at Harvard University in Machine Learning Foundations. I am advised by Sham Kakade and Jonathan Frankle. My research focuses on the science of deep learning, with a particular emphasis on large language models (LLMs). I am especially interested in identifying and addressing empirical challenges in LLM applications, including issues like catastrophic forgetting and inefficient reasoning. In addition, my work explores the use of LLMs in tasks involving reasoning, unlearning, and continual learning. I am also supported by the Kempner Graduate Student Fellowship

In the summer of 2024, I interned as a Machine Learning Research Intern at Apple where I worked on unlearning. Before that, in the summer of 2022, I worked as a Machine Learning intern at Netflix focusing on video automation. Finally, during the summers of 2019-2020, I worked as a software engineering intern at Uber ATG on self-driving vehicles. I also completed my MSE degree in Computer Science at Princeton University where I worked with Ryan Adams.