Hi, I'm Ian! I do AI research at University of Washington with Noah Smith and Pang Wei Koh. I'm interested in the science of language modeling, especially advancing evaluation to better understand scaling behavior and robustness across textual domains.

Previously, I was a PYI at AI2. I got my MS in computer science from Northeastern University, and interned at AWS AI Labs and SIFT. I also hold a BA in cultural anthropology from Bard College.

Selected Publications

The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation
_{Ian Magnusson, Noah A. Smith, Pang Wei Koh
arXiv preprint, 2026 // [paper] [code] [models & data]}


DataDecide: How to Predict Best Pretraining Data with Small Experiments
_{Ian Magnusson, Nguyen Tai, Ben Bogin, David Heineman, Jena D. Hwang, Luca Soldaini, Akshita Bhagia, Jiacheng Liu, Dirk Groeneveld, Oyvind Tafjord, Noah A. Smith, Pang Wei Koh, Jesse Dodge
ICML 2025 // [paper] [data] [evals] [code] [models] [press]}


Paloma: A Benchmark for Evaluating Language Model Fit
_{Ian Magnusson, Akshita Bhagia, Valentin Hofmann, Luca Soldaini, Ananya Harsh Jha, Oyvind Tafjord, Dustin Schwenk, Evan Pete Walsh, Yanai Elazar, Kyle Lo, Dirk Groeneveld, Iz Beltagy, Hannaneh Hajishirzi, Noah A. Smith, Kyle Richardson, Jesse Dodge
NeurIPS 2024 // [paper] [data] [code] [models]}


OLMo: Accelerating the Science of Language Models
_{Dirk Groeneveld, Iz Beltagy, Pete Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Harsh Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Raghavi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, et al.
ACL 2024 // [paper] [model] [code] [blog] [press]}