Gabriel Poesia
Hello! I'm a 3rd 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 currently building models that can 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.
Publications
| CogSci 2022 |
Left to the Reader: Abstracting Solutions in Mathematical Reasoning [PDF] |
| ICLR 2022 |
Synchromesh: Reliable Code Generation from Pre-trained Language Models [PDF] |
| NeurIPS 2021 |
Contrastive Reinforcement Learning of Symbolic Reasoning Domains [arXiv] |
| EMNLP 2021 |
Open-domain clarification question generation without question examples [Link] [PDF] |
| AAAI 2021 |
Pragmatic Code Autocomplete [Link] [PDF] [Code] |
| OOPSLA 2020 |
Dynamic Dispatch of Context-Sensitive Optimizations [Link] [PDF] [Code] |
| OOPSLA 2017 |
Static Placement of Computation on Heterogeneous Devices [Link] [PDF] |
| ECML/PKDD 2014 |
A Lossless Data Reduction for Mining Constrained Patterns in n-ary Relations [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
- Synchromesh: Reliable Code Generation from Pre-trained Models @ Microsoft Research, Oct 2021.
- Pragmatic Code Autocomplete: Resolving User Input Ambiguity in Context @ Microsoft Research Cambridge, Aug 2021.
- Contrastive Reinforcement Learning of Symbolic Reasoning Domains @ Google Research, Jul 2021.
- Pragmatic Code Autocomplete @ Microsoft Data+AI, Nov 2020.