🍁 This fall I'll begin my PhD at Stanford, supported by the NSF CS Graduate Fellowship!
I study foundation models with a focus on methods: how we make decisions about data [1], draw conclusions from experiments [2], and how model behavior changes at scale [3]. I've developed new, cheap and efficient tools for measuring model behavior [4, 5], and built receipes for fully-open language models [6, 7]. Recently, I've been thinking about how methods from pretraining can help us build vision-language, speech-language and reasoning models (interested? please reach out!).
I work on these problems at Ai2 as part of the Open Language Model (OLMo) project, advised by Kyle Lo and Jesse Dodge. Before that, I was an undergrad at Georgia Tech 🐝, fortunate to be advised by Prof. Wei Xu and work with Yao Dou and Mounica Maddela. I've also spent a few summers at AWS and a healthcare startup Patientco. I enjoy reading, hiking, and making homebrew nitrogen cold brew.
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces [code, leaderboard]
2 OLMo 2 Furious [blog, code, models, data]
* = equal contribution
pip install lens-metric - A simple library to evalute text simplification using our LENS and LENS-SALSA LLMs on HuggingFace using only 5 lines of Python [demo].A few interesting corners of the internet I find worth checking out!
...
... to `clone`
... to flip through
Games, Puzzles, and Computation by Erik Demaine
The Corrections by Jonathan Franzen
Naked Statistics by Charles Wheelan
Society Must be Defended by Michel Foucault
Oblivion by David Foster Wallace
I also enjoy trying new coffee shops. Here's some recommendations across Atlanta, that I visited during my undergrad, and a growing list across Seattle.