Pradeep Dasigi

I am a Lead Research Scientist on the Olmo team at the Allen Institute for AI. I have been actively involved in developing open language models, e.g. OLMo and Tulu with a focus on post-training. My current research interests lie in training (vision) language models for open-ended long-horizon agentic tasks including coding, search, and web browsing. My prior work spanned evaluation and training data curation for language models, improving the robustness and generalization of learning algorithms, and building question answering systems.

I used to be a frequent host on the NLP Highlights podcast along with other members of the AllenNLP team.