Gabriel Poesia

Gabriel Poesia

Hi! I'm a final year Computer Science PhD student at the Stanford AI Lab, advised by Noah Goodman in the Computation and Cognition Lab.

My research is centered around learning formal reasoning, for humans and machines. This involves defining a suitable ``game of mathematics'' (on a formal system), learning to find proofs (using language models and deep reinforcement learning), discovering mathematical abstractions, and ultimately using these tools to build joyful and scalable experiences for mathematics education. My recent research builds heavily on ideas from intrinsically motivated learning, and also explores program verification.

[Longer research summary (5 min read)]

A headshot.

Publications

NeurIPS 2024 Oral Learning Formal Mathematics From Intrinsic Motivation
Gabriel Poesia, David Broman, Nick Haber and Noah D. Goodman
[arXiv] [Code]
ICML 2024 When do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
Zhening Li, Gabriel Poesia and Armando Solar-Lezama
TMLR 2024 Certified Deductive Reasoning with Language Models
Gabriel Poesia, Kanishk Gandhi*, Eric Zelikman* and Noah D. Goodman
[arXiv]
ICLR 2024 Hypothesis Search: Inductive Reasoning with Language Models
Ruocheng* Wang, Eric Zelikman*, Gabriel Poesia, Yewen Pu, Nick Haber and Noah D. Goodman
[arXiv]
Phil. Trans. of the Royal Society A 2023 Peano: Learning Formal Mathematical Reasoning
Gabriel Poesia and Noah D. Goodman
[arXiv]
NeurIPS 2023 Spotlight Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions
Eric Zelikman, Qian Huang, Gabriel Poesia, Noah D. Goodman and Nick Haber
[arXiv]
NeurIPS Math-AI 2022 Lemma: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
Zhening Li*, Gabriel Poesia*, Omar Costilla-Reyes, Noah Goodman and Armando Solar-Lezama
[Link] [arXiv] [PDF]
CogSci 2022 Left to the Reader: Abstracting Solutions in Mathematical Reasoning
Gabriel Poesia and Noah Goodman
[PDF]
ICLR 2022 Synchromesh: Reliable Code Generation from Pre-trained Language Models
Gabriel Poesia*, Alex Polozov*, Vu Le, Ashish Tiwari, Gustavo Soares, Chris Meek and Sumit Gulwani
[PDF]
NeurIPS 2021 Contrastive Reinforcement Learning of Symbolic Reasoning Domains
Gabriel Poesia, WenXin Dong and Noah Goodman
[arXiv]
EMNLP 2021 Open-domain clarification question generation without question examples
Julia White, Gabriel Poesia, Robert Hawkins, Dorsa Sadigh and Noah Goodman
[Link] [PDF]
AAAI 2021 Pragmatic Code Autocomplete
Gabriel Poesia and Noah D. Goodman
[Link] [PDF] [Code]
OOPSLA 2020 Dynamic Dispatch of Context-Sensitive Optimizations
Gabriel Poesia and Fernando Magno Quintão Pereira
[Link] [PDF] [Code]
OOPSLA 2017 Static Placement of Computation on Heterogeneous Devices
Gabriel Poesia, Breno Guimarães, Fabrício Ferracioli and Fernando Magno Quintão Pereira
[Link] [PDF]
ECML/PKDD 2014 A Lossless Data Reduction for Mining Constrained Patterns in n-ary Relations
Gabriel Poesia and Loïc Cerf
[Link] [PDF]

Other interests

Programming contests. I used to be an ACM-ICPC competitor (world finalist in 2015), and generally involved in programming contests in various ways. In particular, I authored 3 problems for the ACM-ICPC Latin American regionals, 2 in 2017, one in 2020, and another one upcoming in 2023. I've also coached several teams, taught at training camps in Latin America, and co-authored the problems that selected high schoolers to represent Brazil in the International Olympiad of Informatics in 2018.

Data musicalization. I've been having a lot of fun in creating music from data, as a powerful way to subjectively experience information. One recent finished project on this line was a musicalization of the COVID deaths in Brazil, along with the equally disturbing reactions from our president at the time, which you can watch on YouTube.

Invited Talks

Contact

"poetry in Portuguese"@stanford.edu