Hello! My name is Ishaan Watts, and I am a first-year graduate student in the Machine Learning Department at Carnegie Mellon University. I am interested in the science of foundation models and understanding their failure modes. Currently, I am working with Prof. Aditi Raghunathan on studying how pretraining choices influence downstream performance [ICML'26][Spotlight Talk @ ICBINB Workshop, ICLR'26].

In a past role, I was a Pre-Doctoral Researcher at Google DeepMind under the guidance of Dr. Partha Talukdar. I was part of the Modular Large-Scale Continual Learning group, where I worked on model composition. I also worked as a Research Intern at Microsoft Research under Dr. Sunayana Sitaram, where we studied linguistic diversity in India and worked toward fair and inclusive evaluation of language models [NAACL'24, ACL'24, EMNLP'24, AAAI'25]. I completed my bachelor's degree at IIT Delhi.

Outside of research, I'm a fitness enthusiast and enjoy going to the gym and training for triathlons. I recently completed my first marathon!

Keywords: Large Language Models, Pretraining, Continual Learning, Evaluations

For more details about my background, refer to my Resume. If you'd like to chat about research or triathlon training, feel free to reach out via email!

Last Updated: 05/07/2026

C=Conference, P=Preprint, ^*=Equal Contribution