Scholar
Kyle Lo
Google Scholar ID: VJS12uMAAAAJ
Allen Institute for AI
Citations & Impact
Citations
19,210
H-index
43
i10-index
72
Publications
20
Co-authors
23
list available
Publications
Cited
0
Resume (English only)
Academic Achievements
- Published multiple papers, including three works presented at COLM 2025: 'Fluid Language Model Benchmarking', 'LLMs as Research Tools', and '2 OLMo 2 Furious'. Received Best Paper Honorable Mention at CVPR 2025 (Molmo and PixMo). Won Outstanding Paper Award at NAACL 2025 (DrawEduMath). Published a paper on Semantic Reader in Communications of the ACM. Released several models and datasets, such as Molmo and OLMoE, and won two Best Paper awards at ACL 2024.
Research Experience
- Currently a research scientist at the Allen Institute for AI, co-leading the OLMo project on open language modeling.
Background
- Research interests include large-scale pretraining of language models, with an emphasis on data curation and efficient experimentation. Also interested in methods for specializing language models to domains. Focuses on AI for science and education, particularly human-AI interaction problems like sensemaking over large collections or augmented reading interfaces. Enjoys building useful artifacts that support research, such as open corpora and OCR tools.
Miscellany
- Lives in Seattle, enjoys hanging out with his cat Belphegor, playing board games (Robinson Crusoe, Cthulu: Death May Die, Hanabi) and video games (Baldur's Gate 3, Valheim, Slay the Spire, Noita, Vampire Survivors). Loves D&D, just finished a four-year campaign in Eberron, now embarking on a West Marches campaign. Enthusiastic about boba, favorite places in Seattle are Xing Fu Tang, TP Tea, and Sunright Tea Studio.
