Gabriel Poesia

40 papers A* 8Journal 28Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Formal Reasoning Meets LLMs: Toward AI for Mathematics and Verification. Commun. ACM Kaiyu Yang, Gabriel Poesia, Jingxuan He, Wenda Li, Kristin E. Lauter, Swarat Chaudhuri, Dawn Song
2026	J	`jnl`	Learning to Rank the Initial Branching Order of SAT Solvers. CoRR Arvid Eriksson, Gabriel Poesia, Roman Bresson, Karl Henrik Johansson, David Broman
2026	J	`jnl`	The Token Games: Evaluating Language Model Reasoning with Puzzle Duels. CoRR Simon Henniger, Gabriel Poesia
2025	J	`jnl`	A Matter of Interest: Understanding Interestingness of Math Problems in Humans and Language Models. CoRR Shubhra Mishra, Yuka Machino, Gabriel Poesia, Albert Q. Jiang, Joy Hsu, Adrian Weller, Challenger Mishra, David Broman, Joshua B. Tenenbaum, Mateja Jamnik, Cedegao E. Zhang, Katherine M. Collins
2025	J	`jnl`	Automated Discovery of Tactic Libraries for Interactive Theorem Proving. CoRR Yutong Xin, Jimmy Xin, Gabriel Poesia, Noah D. Goodman, Qiaochu Chen, Isil Dillig
2025	J	`jnl`	Automated Discovery of Tactic Libraries for Interactive Theorem Proving. Proc. ACM Program. Lang. Yutong Xin, Jimmy Xin, Gabriel Poesia, Noah D. Goodman, Qiaochu Chen, Isil Dillig
2025	J	`jnl`	Code-enabled language models can outperform reasoning models on diverse tasks. CoRR Cedegao E. Zhang, Cédric Colas, Gabriel Poesia, Joshua B. Tenenbaum, Jacob Andreas
2025	—	`conf`	Position: Formal Mathematical Reasoning - A New Frontier in AI. ICML (Position Papers) Kaiyu Yang, Gabriel Poesia, Jingxuan He, Wenda Li, Kristin E. Lauter, Swarat Chaudhuri, Dawn Song
2025	J	`jnl`	Programmatic Representation Learning with Language Models. CoRR Gabriel Poesia, Georgia Gabriela Sampaio
2025	J	`jnl`	ProofCompass: Enhancing Specialized Provers with LLM Guidance. CoRR Nicolas Wischermann, Claudio Mayrink Verdun, Gabriel Poesia, Francesco Noseda
2025	A*	`conf`	h4rm3l: A Language for Composable Jailbreak Attack Synthesis. ICLR Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia, Davide Ghilardi, Anna Goldie, Federico Bianchi, Dan Jurafsky, Christopher D. Manning
2024	J	`jnl`	Certified Deductive Reasoning with Language Models. Trans. Mach. Learn. Res. Gabriel Poesia, Kanishk Gandhi, Eric Zelikman, Noah D. Goodman
2024	J	`jnl`	Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning. CoRR Simon Frieder, Jonas Bayer, Katherine M. Collins, Julius Berner, Jacob Loader, András Juhász, Fabian Ruehle, Sean Welleck, Gabriel Poesia, Ryan-Rhys Griffiths, Adrian Weller, Anirudh Goyal, Thomas Lukasiewicz, Timothy Gowers
2024	J	`jnl`	Formal Mathematical Reasoning: A New Frontier in AI. CoRR Kaiyu Yang, Gabriel Poesia, Jingxuan He, Wenda Li, Kristin E. Lauter, Swarat Chaudhuri, Dawn Song
2024	A*	`conf`	Hypothesis Search: Inductive Reasoning with Language Models. ICLR Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, Noah D. Goodman
2024	A*	`conf`	Learning Formal Mathematics From Intrinsic Motivation. NeurIPS Gabriel Poesia, David Broman, Nick Haber, Noah D. Goodman
2024	J	`jnl`	Learning Formal Mathematics From Intrinsic Motivation. CoRR Gabriel Poesia, David Broman, Nick Haber, Noah D. Goodman
2024	J	`jnl`	MathCAMPS: Fine-grained Synthesis of Mathematical Problems From Human Curricula. CoRR Shubhra Mishra, Gabriel Poesia, Belinda Mo, Noah D. Goodman
2024	A*	`conf`	When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions. ICML Zhening Li, Gabriel Poesia, Armando Solar-Lezama
2024	J	`jnl`	When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions. CoRR Zhening Li, Gabriel Poesia, Armando Solar-Lezama
2024	J	`jnl`	dafny-annotator: AI-Assisted Verification of Dafny Programs. CoRR Gabriel Poesia, Chloe Loughridge, Nada Amin
2024	J	`jnl`	h4rm3l: A Dynamic Benchmark of Composable Jailbreak Attacks for LLM Safety Assessment. CoRR Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia, Davide Ghilardi, Anna Goldie, Federico Bianchi, Dan Jurafsky, Christopher D. Manning
2023	—	`conf`	Can Visual Scratchpads With Diagrammatic Abstractions Augment LLM Reasoning? ICBINB Joy Hsu, Gabriel Poesia, Jiajun Wu, Noah D. Goodman
2023	J	`jnl`	Certified Reasoning with Language Models. CoRR Gabriel Poesia, Kanishk Gandhi, Eric Zelikman, Noah D. Goodman
2023	J	`jnl`	Hypothesis Search: Inductive Reasoning with Language Models. CoRR Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, Noah D. Goodman
2023	A*	`conf`	Parsel🦆: Algorithmic Reasoning with Language Models by Composing Decompositions. NeurIPS Eric Zelikman, Qian Huang, Gabriel Poesia, Noah D. Goodman, Nick Haber
2023	J	`jnl`	Solving Math Word Problems by Combining Language Models With Symbolic Solvers. CoRR Joy He-Yueya, Gabriel Poesia, Rose E. Wang, Noah D. Goodman
2022	J	`jnl`	LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions. CoRR Zhening Li, Gabriel Poesia, Omar Costilla-Reyes, Noah D. Goodman, Armando Solar-Lezama
2022	J	`jnl`	Parsel: A Unified Natural Language Framework for Algorithmic Reasoning. CoRR Eric Zelikman, Qian Huang, Gabriel Poesia, Noah D. Goodman, Nick Haber
2022	J	`jnl`	Peano: Learning Formal Mathematical Reasoning. CoRR Gabriel Poesia, Noah D. Goodman
2022	A*	`conf`	Synchromesh: Reliable Code Generation from Pre-trained Language Models. ICLR Gabriel Poesia, Alex Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, Sumit Gulwani
2022	J	`jnl`	Synchromesh: Reliable code generation from pre-trained language models. CoRR Gabriel Poesia, Oleksandr Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, Sumit Gulwani
2021	A*	`conf`	Contrastive Reinforcement Learning of Symbolic Reasoning Domains. NeurIPS Gabriel Poesia, Wenxin Dong, Noah D. Goodman
2021	J	`jnl`	Contrastive Reinforcement Learning of Symbolic Reasoning Domains. CoRR Gabriel Poesia, Wenxin Dong, Noah D. Goodman
2021	—	`conf`	Open-domain clarification question generation without question examples. EMNLP (1) Julia White, Gabriel Poesia, Robert X. D. Hawkins, Dorsa Sadigh, Noah D. Goodman
2021	J	`jnl`	Open-domain clarification question generation without question examples. CoRR Julia White, Gabriel Poesia, Robert X. D. Hawkins, Dorsa Sadigh, Noah D. Goodman
2021	A*	`conf`	Pragmatic Code Autocomplete. AAAI Gabriel Poesia, Noah D. Goodman
2020	J	`jnl`	Dynamic dispatch of context-sensitive optimizations. Proc. ACM Program. Lang. Gabriel Poesia, Fernando Magno Quintão Pereira
2017	J	`jnl`	Static placement of computation on heterogeneous devices. Proc. ACM Program. Lang. Gabriel Poesia, Breno Campos Ferreira Guimarães, Fabricio Ferracioli, Fernando Magno Quintão Pereira
2014	—	`conf`	A Lossless Data Reduction for Mining Constrained Patterns in n-ary Relations. ECML/PKDD (2) Gabriel Poesia, Loïc Cerf

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.