About
At Stanford, I’m advised by Dan Jurafsky and Christopher Potts. My research is focused on interpretability.
I want to understand how neural networks (particularly language models) work. To that end, I’m excited about causal approaches and insights from linguistics—however, I’m not committed to any particular line of work and am always excited to try new things!
I completed my B.S. in Computer Science and Linguistics at Georgetown University, where I worked with Nathan Schneider. I interned at ETH Zürich with Ryan Cotterell working on information theory, as well as at Apple and Redwood Research. (See my CV for more.)
Hit me up on Twitter or at aryamana [at] stanford [dot] edu.
Greatest hits
News
2025-05-01AxBench will be a spotlight paper at ICML 2025 🇨🇦 (this will be the second time me and Zen are presenting a spotlight paper together in Vancouver…)2024-11-04Bayesian scaling laws for in-context learning w/ Noah Goodman2024-09-26ReFT will be a spotlight paper at NeurIPS 2024 🇨🇦2024-08-16CausalGym won an outstanding paper award at ACL 2024 🇹🇭2024-06-21Presented pyvene and IruMozhi at NAACL 2024 🇲🇽2024-04-05New interp-inspired ultra-efficient finetuning method out: ReFT (repo, tweet).2024-03-13We released the paper for pyvene, a new library for intervening on the internal states of neural networks!2024-02-19My first lead-author project as a Ph.D. student is out: CausalGym: Benchmarking causal interpretability methods on linguistic tasks.2023-09-14Moved to the San Francisco Bay Area 🌉 to start my Ph.D. 🫡2023-07-31Back from the Leiden University Summer School in Languages and Linguistics in the Netherlands!2023-02-08Accepted to the Ph.D. program at Stanford CS!