Kanishk Gandhi

I am interested in building machines that understand people. I explore topics in reasoning, discovery and interaction.

CS PhD Student, Stanford
Advisor: Noah Goodman
Additional Advisors: Dorsa Sadigh, Tobi Gerstenberg
Previous Affiliations: Brenden Lake, NYU; Moira Dillon, NYU; Microsoft Research (with Dimitris Papailiopoulos); PathAI; IIT Kanpur

Publications

2025

Scaling up the think-aloud method — CogSci 2025 (Oral)
Daniel Wurgaft*, Ben Prystawski*, Kanishk Gandhi, Cedegao E. Zhang, Joshua B. Tenenbaum, Noah D. Goodman arXiv
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs — CoLM 2025 (Oral)
Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, Nathan Lile, Noah D. Goodman arXiv Media: CNBC
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models — Preprint 2025
Alon Albalak, Duy Phung, Nathan Lile, Rafael Rafailov, Kanishk Gandhi, Louis Castricato, Anikait Singh, Chase Blagden, Violet Xiang, Dakota Mahan, Nick Haber arXiv
D3: A Large Dataset for Training Code Language Models to Act Diff-by-Diff — CoLM 2025
Ulyana Piterbarg, Kanishk Gandhi, Lerrel Pinto, Noah Goodman, Rob Fergus OpenReview
Non-literal Understanding of Number Words by Language Models — CogSci 2025
Polina Tsvilodub*, Kanishk Gandhi*, Haoran Zhao*, Jan-Philipp Fränken, Michael Franke, Noah D. Goodman arXiv
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought — Preprint 2025
Violet Xiang, Charlie Snell, Kanishk Gandhi, Alon Albalak, Anikait Singh, Chase Blagden, Duy Phung, Rafael Rafailov, Nathan Lile, Dakota Mahan, Louis Castricato, Jan-Philipp Fränken, Nick Haber, Chelsea Finn arXiv
BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery — NeurIPS 2025 — Scaling Environments for Agents Workshop
Kanishk Gandhi*, Michael Y. Li*, Lyle Goodyear, Louise Li, Aditi Bhaskar, Mohammed Zaman, Noah D. Goodman arXiv

2024

Stream of Search (SoS): Learning to Search in Language — CoLM 2024 (Oral)
Kanishk Gandhi, Denise Lee, Gabriel Grand, Muxin Liu, Winson Cheng, Archit Sharma, Noah D. Goodman arXiv
Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models — CogSci 2024 (Oral) , NeurIPS Workshop 2023
Jan-Philipp Fränken, Kanishk Gandhi, Tori Qiu, Ayesha Khawaja, Noah D. Goodman, Tobias Gerstenberg arXiv NeurIPS Workshop
Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data from Large Language Models — Preprint 2024
Alex Havrilla, Andrew Dai, Laura O'Mahony, Koen Oostermeijer, Vera Zisler, Alon Albalak, Fabrizio Milo, Sharath Chandra Raparthy, Kanishk Gandhi, Baber Abbasi, Duy Phung, Maia Iyer, Dakota Mahan, Chase Blagden, Srishti Gureja, Mohammed Hamdy, Wen-Ding Li, Giovanni Paolini, Pawan Sasanka Ammanamanchi, Elliot Meyerson arXiv
Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models — Preprint 2024
Joy He-Yueya, Wanjing Anya Ma, Kanishk Gandhi, Benjamin W. Domingue, Emma Brunskill, Noah D. Goodman arXiv
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels — NeurIPS 2024
Jan-Philipp Fränken, Eric Zelikman, Rafael Rafailov, Kanishk Gandhi, Tobias Gerstenberg, Noah D. Goodman arXiv
Human-like Affective Cognition in Foundation Models — Preprint 2024
Kanishk Gandhi, Zoe Lynch, Jan-Philipp Fränken, Kayla Patterson, Sharon Wambu, Tobias Gerstenberg, Desmond C. Ong, Noah D. Goodman arXiv

2023

Social Contract AI: Aligning AI Assistants with Implicit Group Norms — NeurIPS Socially Responsible Language Modeling Research Workshop 2023 (Oral)
Jan-Philipp Fränken, Sam Kwok*, Peixuan Ye*, Kanishk Gandhi, Dilip Arumugam, Jared Moore, Alex Tamkin, Tobias Gerstenberg, Noah D. Goodman arXiv
Understanding social reasoning in language models with language models — NeurIPS 2023 (Spotlight)
Kanishk Gandhi*, Jan-Philipp Fränken*, Tobias Gerstenberg, Noah Goodman arXiv Code
Certified Deductive Reasoning with Language Models — TMLR 2023 ICLR 2025 (Presentation)
Gabriel Poesia, Kanishk Gandhi*, Eric Zelikman*, Noah D. Goodman arXiv Code
Strategic Reasoning with Language Models — NeurIPS Foundation Models and Decision Making Workshop 2023
Kanishk Gandhi, Dorsa Sadigh, Noah Goodman arXiv
Intuitions about physical scenes and objects in Virtual Reality (VR) — CogSci
Peter Zhu, Kanishk Gandhi, Yixing Wang, Steven Le, Jiajun Wu, Hyowon Gweon
Commonsense Psychology in Human Infants and Machines — Cognition 2023
Gala Stojnic, Kanishk Gandhi, Shannon Yasuda, Brenden M. Lake, Moira R. Dillon Media: NSF Science Now WNYC/Gothamist The Daily Beast The Jerusalem Post NYU News Washington Square News ScienceDaily

2022

Eliciting Compatible Demonstrations for Multi-Human Imitation Learning — CoRL 2022
Kanishk Gandhi, Siddharth Karamcheti, Madeline Liao, Dorsa Sadigh

2021

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others — NeurIPS 2021
Kanishk Gandhi, Gala Stojnic, Brenden M. Lake, Moira R. Dillon
Evaluating infants’ reasoning about agents using the Baby Intuitions Benchmark (BIB) — CogSci 2021
Gala Stojnic, Kanishk Gandhi, Brenden Lake, Moira Dillon

2020

Mutual exclusivity as a challenge for deep neural networks — NeurIPS 2020
Kanishk Gandhi, Brenden M. Lake Media: New Scientist