Get started
Author

Gabriel Poesia

Observed names: Gabriel Poesia Reis e Silva, Poesia Reis e Silva, Gabriel, Poesia, Gabriel, Reis, Gabriel Poesia, e Silva, Gabriel Poesia Reis
ORCID: 0009-0003-7058-8428
Observed ORCID: 0009-0003-7058-8428
OpenAlex ID: A5043645877
Synchromesh: Reliable code generation from pre-trained language models
2022 · Poesia, Gabriel, Polozov, Oleksandr, et al. · arXiv (Cornell University) · 72
PDF
A benchmark of expert-level academic questions to assess AI capabilities
2026 · Long Phan, Alice Gatti, et al. · Nature · 61
PDF
Solving Math Word Problems by Combining Language Models With Symbolic Solvers
2023 · He-Yueya, Joy, Poesia, Gabriel, et al. · arXiv (Cornell University) · 16
PDF
Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions
2023 · Eric Zelikman, Qian Huang, et al. · neural information processing systems · 15
PDF
Open-domain clarification question generation without question examples
2021 · Julia White, Gabriel Poesia, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 15
PDF
Static placement of computation on heterogeneous devices
2017 · Gabriel Poesia, Breno Guimarães, et al. · Proceedings of the ACM on Programming Languages · 15
PDF
Hypothesis Search: Inductive Reasoning with Language Models
2023 · Wang, Ruocheng, Zelikman, Eric, et al. · arXiv (Cornell University) · 13
PDF
Peano: learning formal mathematical reasoning
2023 · Gabriel Poesia, Noah D. Goodman · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · 13
Contrastive Reinforcement Learning of Symbolic Reasoning Domains
2021 · Poesia, Gabriel, Dong, WenXin, et al. · arXiv (Cornell University) · 7
PDF
Dynamic dispatch of context-sensitive optimizations
2020 · Gabriel Poesia, Fernando Magno Quintão Pereira · Proceedings of the ACM on Programming Languages · 7
PDF
Formal Mathematical Reasoning: A New Frontier in AI
2024 · Yang, Kaiyu, Poesia, Gabriel, et al. · arXiv (Cornell University) · 5
PDF
dafny-annotator: AI-Assisted Verification of Dafny Programs
2024 · Poesia, Gabriel, Loughridge, Chloe, et al. · arXiv (Cornell University) · 4
PDF
Certified Deductive Reasoning with Language Models
2023 · Poesia, Gabriel, Gandhi, Kanishk, et al. · arXiv (Cornell University) · 2
PDF
Pragmatic Code Autocomplete
2021 · Gabriel Poesia, Noah Goodman · Proceedings of the AAAI Conference on Artificial Intelligence · 2
Formal Reasoning Meets LLMs: Toward AI for Mathematics and Verification
2026 · Kaiyu Yang, Gabriel Poesia, et al. · Communications of the ACM · 1
Automated Discovery of Tactic Libraries for Interactive Theorem Proving
2025 · Yutong Xin, Jimmy Xin, et al. · Proceedings of the ACM on Programming Languages · 1
PDF
Automated Discovery of Tactic Libraries for Interactive Theorem Proving
2025 · Xin, Yutong, Xin, Jimmy, et al. · arXiv (Cornell University) · 1
PDF
LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
2022 · Li, Zhening, Poesia, Gabriel, et al. · arXiv (Cornell University) · 1
PDF
A Lossless Data Reduction for Mining Constrained Patterns in n-ary Relations
2014 · Gabriel Poesia, Loïc Cerf · Lecture notes in computer science · 1
lean-piso-trip: Equivalence Search over Mathlib Theorems Modulo Rewrites and Binder Permutation (VMCAI 2027 Artifact)
2026 · Leßmann, Samuel, Henniger, Simon, et al. · Zenodo (CERN European Organization for Nuclear Research)
The Scaffolding Paradox: Evidence from AI-Assisted Dafny Proof Synthesis (Artefact)
2026 · Kravchuk-Kirilyuk, Anastasiya, Nguyen, Thanh Dat, et al. · Zenodo (CERN European Organization for Nuclear Research)
Formal Disco: Scalable Open-Ended Generation of Formally Verified Programs
2026 · Poesia, Gabriel, Henniger, Simon, et al. · arXiv (Cornell University)
PDF
Learning to Rank the Initial Branching Order of SAT Solvers
2026 · Eriksson, Arvid, Poesia, Gabriel, et al. · arXiv (Cornell University)
PDF
The Token Games: Evaluating Language Model Reasoning with Puzzle Duels
2026 · Henniger, Simon, Poesia, Gabriel · arXiv (Cornell University)
PDF
A benchmark of expert-level academic questions to assess AI capabilities
2026 · Center for AI Safety, Phan, Long, et al. · RWTH Publications (RWTH Aachen)
Works count: 43
Citation count: 222
H-index: 8
I10-index: 8
Year
Topic
Type