Publications

You can also find my work on Google Scholar.

Show

2026

Gradual Refinement in Coarse-to-Fine Concept Induction and Human-Like Iterative Programming

Alex Lew, Maddy Bowers, Gabriel Grand, Emanuel Kitzelmann, David Nagy, Tejaswini Ojha, Mukul Singh, Tobias Thomas, Dominik Ürüm, Hanqi Zhou

In Approaches and Applications of Inductive Programming (Dagstuhl Seminar 25491), Dagstuhl Reports, vol. 15, no. 11, pp. 150–152, 2026.

[Report] [PDF]

Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People

Gabriel Grand, Valerio Pepe, Joshua B. Tenenbaum, Jacob Andreas

International Conference on Learning Representations (ICLR), 2026. Oral presentation

[arXiv] [ICLR oral] [Project and demo] [Code]

2025

Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits

Dev Patel, Gabrielle Gervacio, Diekola Raimi, Kevin Zhu, Ryan Lagasse, Gabriel Grand, Ashwinee Panda, Maheep Chaudhary

ResponsibleFM at NeurIPS 2025 and Deployable AI at AAAI 2026, 2025. Oral talk at DAI at AAAI 2026

[arXiv]

Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning

Joongho Kim, Xirui Huang, Zarreen Reza, Gabriel Grand, Kevin Zhu, Ryan Lagasse

Efficient Reasoning Workshop at NeurIPS, 2025.

[arXiv]

Self-Steering Language Models

Gabriel Grand, Joshua B. Tenenbaum, Vikash K. Mansinghka, Alexander K. Lew, Jacob Andreas

Conference on Language Modeling (COLM), 2025. Featured on Hugging Face Daily Papers

[Paper] [Code] [MIT News]

Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo

João Loula, Benjamin LeBrun, Li Du, Ben Lipkin, Clemente Pasti, Gabriel Grand, Tianyu Liu, Yahya Emara, Marjorie Freedman, Jason Eisner, Ryan Cotterell, Vikash Mansinghka, Alexander K. Lew, Tim Vieira, Timothy J. O’Donnell

International Conference on Learning Representations (ICLR), 2025. Oral presentation

[OpenReview] [Code] [MIT News]

Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models

Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin, Unnathi Kumar, Setayesh Radkani, Thomas H. Clark, Carina Kauf, Jennifer Hu, R.T. Pramod, Gabriel Grand, Vivian Paulun, Maria Ryskina, Ekin Akyürek, Ethan Wilcox, Nafisa Rashid, Leshem Choshen, Roger Levy, Evelina Fedorenko, Joshua B. Tenenbaum, Jacob Andreas

Transactions of the Association for Computational Linguistics (TACL), 2025.

[TACL] [arXiv] [Project]

2024

A Llama Sunk My Battleship! Asking Rational Questions with LLMs via Bayesian Inference

Gabriel Grand, Valerio Pepe, Jacob Andreas, Joshua B. Tenenbaum

System-2 Reasoning at Scale Workshop at NeurIPS, 2024.

[Paper] [Code]

Stream of Search (SoS): Learning to Search in Language

Kanishk Gandhi, Denise Lee, Gabriel Grand, Muxin Liu, Winson Cheng, Archit Sharma, Noah D. Goodman

Conference on Language Modeling (COLM), 2024. Oral presentation

[arXiv] [Code]

Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling

Gabriel Grand, Valerio Pepe, Jacob Andreas, Joshua B. Tenenbaum

Annual Meeting of the Cognitive Science Society (CogSci), 2024.

[arXiv] [Code]

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

Gabriel Grand, Lionel Wong, Maddy Bowers, Theo X. Olausson, Muxin Liu, Joshua B. Tenenbaum, Jacob Andreas

International Conference on Learning Representations (ICLR), 2024.

[arXiv] [Code] [Talk] [MIT News]

2023

From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought

Lionel Wong, Gabriel Grand, Alexander K. Lew, Noah D. Goodman, Vikash K. Mansinghka, Jacob Andreas, Joshua B. Tenenbaum

arXiv:2306.12672, 2023.

[arXiv] [Code]

Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs

Alexander K. Lew, Tan Zhi-Xuan, Gabriel Grand, Vikash K. Mansinghka

arXiv:2306.03081, 2023.

[arXiv] [Code] [Documentation]

Discovering Abstractions from Language via Neurosymbolic Program Synthesis

Gabriel Grand

MIT Master's Thesis, advised by Jacob Andreas and Joshua B. Tenenbaum, 2023.

[MIT DSpace] [Code]

Evaluating Statistical Language Models as Pragmatic Reasoners

Benjamin Lipkin, Lionel Wong, Gabriel Grand, Joshua B. Tenenbaum

Annual Meeting of the Cognitive Science Society (CogSci), 2023.

[CogSci] [arXiv] [Code]

Grounded Physical Language Understanding with Probabilistic Programs and Simulated Worlds

Cedegao Zhang, Lionel Wong, Gabriel Grand, Joshua B. Tenenbaum

Annual Meeting of the Cognitive Science Society (CogSci), 2023.

[CogSci] [Code]

Top-Down Synthesis for Library Learning

Maddy Bowers, Theo X. Olausson, Lionel Wong, Gabriel Grand, Joshua B. Tenenbaum, Kevin Ellis, Armando Solar-Lezama

Proceedings of the ACM on Programming Languages (POPL), 2023.

[ACM Digital Library] [arXiv] [Code]

2022

Identifying concept libraries from language about object structure

Catherine Wong, William P. McCarthy, Gabriel Grand, Yoni Friedman, Joshua B. Tenenbaum, Jacob Andreas, Robert D. Hawkins, Judith E. Fan

Annual Meeting of the Cognitive Science Society (CogSci), 2022.

[arXiv] [Project] [Code]

‘Semantic projection’ recovers rich human knowledge of multiple object features from word embeddings

Gabriel Grand, Idan Blank, Francisco Pereira, Evelina Fedorenko

Nature Human Behaviour, 2022.

[Nature] [MIT McGovern Institute] [arXiv]

2021

ChemBERTa-2: Towards Chemical Foundation Models

Walid Ahmad, Elana Simon, Seyone Chithrananda, Gabriel Grand, Bharath Ramsundar

Machine Learning for Molecules Workshop at ELLIS, 2021.

[Paper] [Workshop]

2020

ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction

Seyone Chithrananda, Gabriel Grand, Bharath Ramsundar

Machine Learning for Molecules Workshop at NeurIPS, 2020.

[arXiv]

2019

Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects

Gabriel Grand, Yonatan Belinkov

Workshop on Shortcomings in Vision and Language at NAACL (SiVL), 2019. Best Paper Award

[ACL Anthology] [arXiv]

2018

On the Flip Side: Identifying Counterexamples in Visual Question Answering

Gabriel Grand, Aron Szanto, Yoon Kim, Alexander Rush

Deep Learning Day at KDD, 2018.

[arXiv] [KDD]

Learning Interpretable and Bias-Free Models for Visual Question Answering

Gabriel Grand

Harvard Undergraduate Thesis, advised by Alexander Rush, 2018. Hoopes Prize

[Thesis]