Kyle Lo
Former Ai2 research scientist who co-led the OLMo project; last-listed author of the Dolma paper
Kyle Lo was a research scientist at Ai2, where Lo co-led the OLMo project on open language modeling; Lo's site marks a farewell to Ai2 in March 2026. Lo's research centers on large-scale language-model pretraining, with an emphasis on data curation, data mixing, benchmark validity, and efficient experimentation. Lo is the last-listed author of the Dolma paper, a co-author of the original OLMo paper, and is credited in OLMo 2 with base-model development and in OLMoE with pretraining dataset creation and data experiments.13456
Work
OLMoOpen weights
Co-led the OLMo project at Ai2, per Lo's site; co-author of the OLMo paper (2024), credited in OLMo 2 with base-model development, and in OLMoE with helping create the pretraining dataset and analyzing data experiments.1456
DolmaOpen data
Last-listed author of the Dolma paper, which describes a three-trillion-token English corpus released for research on language-model pretraining.3
Other documented roles
Roles the sources document but that are not confirmed as current.
- Research scientist; co-lead of the OLMo project, Ai2 (Allen Institute for AI)12
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.