David Wadden
Research scientist at Google DeepMind on Gemini post-training; former Ai2 researcher on OLMo and Tülu
- Research scientist, working on post-training for Gemini, Google DeepMind1
David Wadden is a research scientist at Google DeepMind, working on post-training for Gemini. Before that, Wadden was a research scientist on the AllenNLP and Semantic Scholar teams at Ai2. Wadden co-authored the Tülu 2 paper on adapting open language models, is credited with base-model development in the OLMo 2 paper, which lists Wadden with an Ai2 affiliation, and ran DCLM evaluations for OLMoE. Wadden's earlier research includes SciFact and MultiVerS, work on verifying scientific claims.1234
Work
OLMo 2 and OLMoE (OLMo family)Open weights
Credited in the OLMo 2 paper with base-model development, including training and data curation, and in the OLMoE paper with running DCLM evaluations and Weights & Biases reports.34
Tülu 2Published research
Co-author of "Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2" (2023).2
SciFact and MultiVerS (external site: dwadden.github.io)Published research
First author of the SciFact-Open and MultiVerS papers on scientific claim verification, as listed on Wadden's homepage.1
Other documented roles
Roles the sources document but that are not confirmed as current.
- Research scientist on the AllenNLP and Semantic Scholar teams, Ai2 (Allen Institute for AI)13
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.