Papers
Deep Learning
- Llemma: An Open Language Model For Mathematics
Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, Marco Dos Santos, Stephen McAleer, Albert Q. Jiang, Jia Deng, Stella Biderman, and Sean Welleck
Preprint, 2023. ICLR, 2024.
Paper: arXiv
-
OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
Keiran Paster, Marco Dos Santos, Zhangir Azerbayev, and Jimmy Ba
Preprint, 2023. ICLR, 2024
Paper: arXiv
- ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics.
Zhangir Azerbayev, Bartosz Piotrowski, Hailey Schoelkopf, Edward W. Ayers, Dragomir Radev, and Jeremy Avigad
Preprint, 2023.
Paper: arXiv
- ProofNet: A benchmark for autoformalizing and formally proving undergraduate-level mathematics problems
Zhangir Azerbayev, Bartosz Piotrowski, and Jeremy Avigad
MATH-AI Workshop at NeurIPS'22 (see above for long paper), 2022.
Paper: pdf
- Explicit Knowledge Transfer for Weakly-Supervised Code Generation
Zhangir Azerbayev, Ansong Ni, Hailey Schoelkopf, and Dragomir Radev
Preprint, 2022. Published at the Deep Learning for Code Workshop at ICLR 2023.
Paper: arXiv
Computational Cognitive Science
- Learning a Metacognition for Object Detection
with Marlene Berke, Mario Belledonne, and Julian Jara-Ettinger (I am third author)
Preprint, 2021.
Paper: arXiv