Kyle Lo
research
I’m a research scientist at the Allen Institute for AI on the OLMo and Semantic Scholar projects. I specialize in topics in natural language processing, machine learning and human-AI interaction:
me
I live in Seattle. When not working, I hang with my cat Belphegor and play board games (Robinson Crusoe, Cthulu: Death May Die, Hanabi) and video games (Baldur's Gate 3, Valheim, Slay the Spire, Noita, Vampire Survivors). I love D&D and am currently on year three of a campaign in Eberron. I'm a boba enthusiast and my favorites in Seattle are Xing Fu Tang, TP Tea and Sunright Tea Studio.
news
| Oct 1, 2024 | Excited that our Semantic Reader paper is published in Communications of the ACM! 🥳 This paper synthesized work from multiple years worth of research by over 40 researchers and engineers across dozens of institutions, all focusing on how to make AI useful for improving scholarly reading. Check out the paper here! |
|---|---|
| Sep 25, 2024 | Molmo our first multimodal OLMo model is out! Molmo is our family of open, late-fusion image+text language models, all available on huggingface, trained using a really high-quality dataset of images + dense captions / task demonstrations that we’ll be releasing openly! Read the paper here, play with the model here, and download the weights here. |
| Sep 3, 2024 | OLMoE is out! Our first mixture of experts model in the OLMo family 🎉 OLMoE has only 1B active params but matches perf of larger dense models 🫨 and comes released with: ✅ weights ✅ data ✅ code ✅ ckpts ✅ logs ✅ detailed paper! Download the weights here and read the paper here! |