KE
Kevin Ellis
cs.AIcs.LGcs.CLcs.CVcs.PLcs.SEcs.ROcs.GRLanguageAlgorithms
On Valency
published · living versionsW_xkbsgmjm·v1 · currentpublished
How Humans Learn Unfamiliar Worlds: A Think-Aloud Dataset on ARC-AGI-3
with Shuzhi Liu, Archana Warrier, Dat Nguyen, Chengqi Zheng +1
1 version
W_ht977um8·v1published
Preprints & journals
48 papers in the corpus · 2017–2026PRECOCIAL: Pretraining with Code Curriculums via Iterative Search for Accelerated Learning2610.24970v1 · Edward Gu, Ali Payani, Kevin Ellis2026 · 0 citationsarXivon Valency
EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning2609.35047v1 · Yichao Liang, Amber Li, Dat Nguyen et al.2026 · 0 citationsarXiv
Induction and Inquiry via Probabilistic Reasoning over Language and Code2609.01815v1 · Wasu Top Piriyakulkij, Sam Acquaviva, Cassidy Langenfeld et al.2026 · 0 citationsarXiv
Twin: Playing an Unknown Game with a Test-Time Digital Twin2608.14490v1 · Alexy Skoutnev, Kirill Acharya, Gaston Longhitano et al.2026 · 0 citationsarXiv
Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction2607.08233v1 · Sophia Koehler, Antonia Wust, Inga Ibs et al.2026 · 0 citationsarXiv
MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics2606.01538v2 · Ziga Kovacic, Kevin Ellis2026 · 0 citationsarXiv
Predicting Performance of Symbolic and Prompt Programs with Examples2605.21515v1 · Chengqi Zheng, Keya Hu, Shuzhi Liu et al.2026 · 0 citationsarXiv
Bongards at the Boundary of Perception and Reasoning: Programs or Language?2602.03038v1 · Cassidy Langenfeld, Claas Beger, Gloria Geng et al.2026 · 0 citationsarXiv
OmniCode: A Benchmark for Evaluating Software Engineering Agents2602.02262v3 · Atharv Sonwane, Eng-Shen Tu, Wei-Chung Lu et al.2026 · 0 citationsarXiv
Joint Learning of Hierarchical Neural Options and Abstract World Model2602.02799v2 · Wasu Top Piriyakulkij, Wolfgang Lehrach, Kevin Ellis et al.2026 · 0 citationsarXiv
Benchmarking World-Model Learning with Environment-Level Queries2510.19788v4 · Archana Warrier, Dat Nguyen, Michelangelo Naim et al.2025 · 0 citationsForty-third International Conference on Machine Learning, 2026
ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning2509.26255v3 · Yichao Liang, Dat Nguyen, Cambridge Yang et al.2025 · 1 citationarXiv
A Neuroscience-Inspired Dual-Process Model of Compositional Generalization2507.18868v3 · Alex Noviello, Claas Beger, Jacob Groner et al.2025 · 0 citationsarXiv
Refactoring Codebases through Library Design2506.11058v3 · Ziga Kovacic, Justin T. Chiu, Celine Lee et al.2025 · 1 citationarXiv
Programmatic Video Prediction Using Large Language Models2505.14948v1 · Hao Tang, Kevin Ellis, Suhas Lohit et al.2025 · 0 citationsarXiv
PoE-World: Compositional World Modeling with Products of Programmatic Experts2505.10819v4 · Wasu Top Piriyakulkij, Yichao Liang, Hao Tang et al.2025 · 0 citationsarXiv
LLM-Guided Probabilistic Program Induction for POMDP Model Estimation2505.02216v2 · Aidan Curtis, Hao Tang, Thiago Veloso et al.2025 · 0 citationsarXiv
Cognitive maps are generative programs2504.20628v1 · Marta Kryven, Cole Wyeth, Aidan Curtis et al.2025 · 0 citationsarXiv
Challenges and Paths Towards AI for Software Engineering2503.22625v1 · Alex Gu, Naman Jain, Wen-Ding Li et al.2025 · 10 citationsarXiv
Combining Induction and Transduction for Abstract Reasoning2411.02272v4 · Wen-Ding Li, Keya Hu, Carter Larsen et al.2024 · 2 citationsarXiv
VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning2410.23156v2 · Yichao Liang, Nishanth Kumar, Hao Tang et al.2024 · 3 citationsarXiv
Symbolic metaprogram search improves learning efficiency and explains rule learning in humans.39127796 · Rule, Joshua S, Piantadosi, Steven T, Cropper, Andrew et al.2024 · 8 citationsNature communications. 2024;15(1):6847
Is Programming by Example solved by LLMs?2406.08316v3 · Wen-Ding Li, Kevin Ellis2024 · 4 citationsarXiv
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff2405.17503v3 · Hao Tang, Keya Hu, Jin Peng Zhou et al.2024 · 11 citationsarXiv
WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment2402.12275v3 · Hao Tang, Darren Key, Kevin Ellis2024 · 9 citationsarXiv
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning2402.06025v7 · Wasu Top Piriyakulkij, Cassidy Langenfeld, Tuan Anh Le et al.2024 · 0 citationsarXiv
Active Preference Inference using Language Models and Probabilistic Reasoning2312.12009v2 · Wasu Top Piriyakulkij, Volodymyr Kuleshov, Kevin Ellis2023 · 3 citationsarXiv
Rapid Motor Adaptation for Robotic Manipulator Arms2312.04670v2 · Yichao Liang, Kevin Ellis, Joao Henriques2023 · 9 citationsarXiv
Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language2306.02797v3 · Kevin Ellis2023 · 4 citationsarXiv
DreamCoder: growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning.37271169 · Ellis, Kevin, Wong, Lionel, Nye, Maxwell et al.2023 · 124 citationsPhilosophical transactions. Series A, Mathematical, physical, and engineering sciences. 2023;381(2251):20220050
LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas2306.02049v2 · Kensen Shi, Hanjun Dai, Wen-Ding Li et al.2023 · 0 citationsarXiv
Discovering Quantum Circuit Components with Program Synthesis2305.01707v1 · Leopoldo Sarra, Kevin Ellis, Florian Marquardt2023 · 6 citationsarXiv
Top-Down Synthesis for Library Learning2211.16605v2 · Matthew Bowers, Theo X. Olausson, Lionel Wong et al.2022 · 33 citationsProc. ACM Program. Lang. 7, POPL, Article 41 (January 2023), pp 1182-1213
A language of thought for the mental representation of geometric shapes.36403385 · Sablé-Meyer, Mathias, Ellis, Kevin, Tenenbaum, Josh et al.2022 · 88 citationsCognitive psychology. 2022;139:101527
Toward Trustworthy Neural Program Synthesis2210.00848v2 · Darren Key, Wen-Ding Li, Kevin Ellis2022 · 6 citationsarXiv
Synthesizing theories of human language with Bayesian program induction.36042196 · Ellis, Kevin, Albright, Adam, Solar-Lezama, Armando et al.2022 · 17 citationsNature communications. 2022;13(1):5024
From Perception to Programs: Regularize, Overparameterize, and Amortize2206.05922v2 · Hao Tang, Kevin Ellis2022 · 1 citationarXiv
Efficient Pragmatic Program Synthesis with Informative Specifications2204.02495v1 · Saujas Vaduguru, Kevin Ellis, Yewen Pu2022 · 0 citationsarXiv
CrossBeam: Learning to Search in Bottom-Up Program Synthesis2203.10452v1 · Kensen Shi, Hanjun Dai, Kevin Ellis et al.2022 · 6 citationsarXiv
Scaling Neural Program Synthesis with Distribution-based Search2110.12485v1 · Nathanael Fijalkow, Guillaume Lagarde, Th'eo Matricon et al.2021 · 9 citationsarXiv
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface2107.06393v2 · Tuan Anh Le, Katherine M. Collins, Luke Hewitt et al.2021 · 0 citationsICLR 2022
Leveraging Language to Learn Program Abstractions and Search Heuristics2106.11053v3 · Catherine Wong, Kevin Ellis, Joshua B. Tenenbaum et al.2021 · 9 citationsarXiv
Learning abstract structure for drawing by efficient motor program induction2008.03519v1 · Lucas Y. Tian, Kevin Ellis, Marta Kryven et al.2020 · 17 citationsarXiv
Program Synthesis with Pragmatic Communication2007.05060v3 · Yewen Pu, Kevin Ellis, Marta Kryven et al.2020 · 10 citationsarXiv
Five Ways in Which Computational Modeling Can Help Advance Cognitive Science: Lessons From Artificial Grammar Learning.31663267 · Zuidema, Willem, French, Robert M, Alhama, Raquel G et al.2021 · 11 citationsTopics in cognitive science. 2020;12(3):925-941
Write, Execute, Assess: Program Synthesis with a REPL1906.04604v1 · Kevin Ellis, Maxwell Nye, Yewen Pu et al.2019 · 65 citationsarXiv
Learning to Infer and Execute 3D Shape Programs1901.02875v3 · Yonglong Tian, Andrew Luo, Xingyuan Sun et al.2019 · 68 citationsarXiv
Learning to Infer Graphics Programs from Hand-Drawn Images1707.09627v5 · Kevin Ellis, Daniel Ritchie, Armando Solar-Lezama et al.2017 · 136 citationsarXiv
Career total: 75 works. 48 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.