Gabriel Poesia

Gabriel Poesia

Hello! I'm a 4th year Computer Science PhD student at Stanford University, affiliated with the NLP Group and advised by Noah Goodman in the Computation and Cognition Lab.

I'm deeply interested in models that can learn to reliably perform and verify high-level mathematical reasoning, motivated and grounded by applications in computer-assisted education. This ends up touching on problems in AI as well as in cognitive science.

A headshot.

Publications

Phil. Trans. of the Royal Society A 2023 Peano: Learning Formal Mathematical Reasoning
Gabriel Poesia and Noah D. Goodman
[arXiv]
arXiv 2022 Parsel: A Unified Natural Language Framework for Algorithmic Reasoning
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 official ACM-ICPC Latin American regionals, 2 in 2017 and one in 2020. 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 have people subjectively experience information. I have an ongoing side-project using COVID-related data that will be released this September 2021. Stay tuned!

Invited Talks

Contact

"poetry in Portuguese"@stanford.edu