1 code implementation • 3 Feb 2022 • Stanislas Polu, Jesse Michael Han, Kunhao Zheng, Mantas Baksys, Igor Babuschkin, Ilya Sutskever
We explore the use of expert iteration in the context of language modeling applied to formal mathematics.
Ranked #4 on Automated Theorem Proving on miniF2F-test (using extra training data)
1 code implementation • 24 Jan 2022 • Arvind Neelakantan, Tao Xu, Raul Puri, Alec Radford, Jesse Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, Johannes Heidecke, Pranav Shyam, Boris Power, Tyna Eloundou Nekoul, Girish Sastry, Gretchen Krueger, David Schnurr, Felipe Petroski Such, Kenny Hsu, Madeleine Thompson, Tabarak Khan, Toki Sherbakov, Joanne Jang, Peter Welinder, Lilian Weng
Similarly to text embeddings, we train code embedding models on (text, code) pairs, obtaining a 20. 8% relative improvement over prior best work on code search.
Ranked #1 on Passage Ranking on MS MARCO
no code implementations • 11 Oct 2021 • Jesse Michael Han, Igor Babuschkin, Harrison Edwards, Arvind Neelakantan, Tao Xu, Stanislas Polu, Alex Ray, Pranav Shyam, Aditya Ramesh, Alec Radford, Ilya Sutskever
We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models.
3 code implementations • ICLR 2022 • Kunhao Zheng, Jesse Michael Han, Stanislas Polu
We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving.
Ranked #1 on Automated Theorem Proving on miniF2F-valid (using extra training data)
4 code implementations • ICLR 2022 • Jesse Michael Han, Jason Rute, Yuhuai Wu, Edward W. Ayers, Stanislas Polu
Labeled data for imitation learning of theorem proving in large libraries of formalized mathematics is scarce as such libraries require years of concentrated effort by human specialists to be built.
Ranked #8 on Automated Theorem Proving on miniF2F-test
no code implementations • 21 Dec 2020 • Daniel Selsam, Jesse Michael Han, Leonardo de Moura, Patrice Godefroid
We introduce a new programming paradigm called oracle-guided decision programming in which a program specifies a Markov Decision Process (MDP) and the language provides a universal policy.
1 code implementation • 6 Jul 2020 • Jesse Michael Han
Modern SAT solvers routinely operate at scales that make it impractical to query a neural network for every branching decision.
1 code implementation • 23 Apr 2019 • Jesse Michael Han, Floris van Doorn
We describe a formalization of forcing using Boolean-valued models in the Lean 3 theorem prover, including the fundamental theorem of forcing and a deep embedding of first-order logic with a Boolean-valued soundness theorem.
Logic in Computer Science Logic 03-04, 03E35, 03E40