Aryaman Arora

PublicationsPostsProjects

Search

Search IconIcon to open search

# About

Hi! I’m Aryaman, an incoming Ph.D. student in Computer Science in the Stanford NLP group. Currently, I am a final-year undergrad majoring in Computer Science and Linguistics at Georgetown University, where I am advised by Nathan Schneider. I also frequently collaborate with Ryan Cotterell at ETH Zürich.

My research interests are multilingual NLP, computational linguistics, and mechanistic interpretability. I also enjoy historical linguistics. Some fundamental questions I care about are:

  1. How do transformer language models work? Why are they so successful and alternatives (like RNNs) are not?
  2. How do multilingual language models distribute and share processing across languages?
  3. Can we formalise some ideas about human language from linguistics using information-theoretic methods?
  4. What is the linguistic history of the Indian subcontinent?

You’ll find more on my résumé and list of publications. I also have some small NLP-focused blog posts here.

# News

# Selected papers