Thomas L. Griffiths

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 82

Top Topics

Mental Representations

Cognitive Architectures

Top Venues

PLoS Comput. Biol.

Publications

Bonan Zhao, Natalia Vélez, Thomas L. Griffiths
Comparing Human Behavior to an Optimal Policy for Innovation. AAAI Spring Symposia (2024)
Carlos G. Correa, Thomas L. Griffiths, Nathaniel D. Daw
Program-Based Strategy Induction for Reinforcement Learning. CoRR (2024)
Yufei Tian, Abhilasha Ravichander, Lianhui Qin, Ronan Le Bras, Raja Marjieh, Nanyun Peng, Yejin Choi, Thomas L. Griffiths, Faeze Brahman
MacGyver: Are Large Language Models Creative Problem Solvers? NAACL-HLT (2024)
Xudong Guo, Kaixuan Huang, Jiale Liu, Wenhui Fan, Natalia Vélez, Qingyun Wu, Huazheng Wang, Thomas L. Griffiths, Mengdi Wang
Embodied LLM Agents Learn to Cooperate in Organized Teams. CoRR (2024)
Xuechunzi Bai, Angelina Wang, Ilia Sucholutsky, Thomas L. Griffiths
Measuring Implicit Bias in Explicitly Unbiased Large Language Models. CoRR (2024)
Liyi Zhang, Logan Nelson, Thomas L. Griffiths
Analyzing the Benefits of Prototypes for Semi-Supervised Category Learning. CoRR (2024)
Raja Marjieh, Pol van Rijn, Ilia Sucholutsky, Harin Lee, Thomas L. Griffiths, Nori Jacoby
A Rational Analysis of the Speech-to-Song Illusion. CoRR (2024)
Declan Campbell, Sreejan Kumar, Tyler Giallanza, Thomas L. Griffiths, Jonathan D. Cohen
Human-Like Geometric Abstraction in Large Pre-trained Neural Networks. CoRR (2024)
Stephan C. Meylan, Thomas L. Griffiths
Word Forms Reflect Trade-Offs Between Speaker Effort and Robust Listener Recognition. Cogn. Sci. 48 (7) (2024)
Ryan Liu, Jiayi Geng, Joshua C. Peterson, Ilia Sucholutsky, Thomas L. Griffiths
Large Language Models Assume People are More Rational than We Really are. CoRR (2024)
Sunayana Rane, Polyphony J. Bruna, Ilia Sucholutsky, Christopher T. Kello, Thomas L. Griffiths
Concept Alignment. CoRR (2024)
Andi Peng, Ilia Sucholutsky, Belinda Z. Li, Theodore R. Sumers, Thomas L. Griffiths, Jacob Andreas, Julie Shah
Learning with Language-Guided State Abstractions. ICLR (2024)
Ilia Sucholutsky, Katherine M. Collins, Maya Malaviya, Nori Jacoby, Weiyang Liu, Theodore R. Sumers, Michalis Korakakis, Umang Bhatt, Mark K. Ho, Joshua B. Tenenbaum, Bradley C. Love, Zachary A. Pardos, Adrian Weller, Thomas L. Griffiths
Representational Alignment Supports Effective Machine Teaching. CoRR (2024)
Jian-Qiao Zhu, Thomas L. Griffiths
Incoherent Probability Judgments in Large Language Models. CoRR (2024)
Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan, Thomas L. Griffiths
Cognitive Architectures for Language Agents. Trans. Mach. Learn. Res. 2024 (2024)
Sreejan Kumar, Raja Marjieh, Byron Zhang, Declan Campbell, Michael Y. Hu, Umang Bhatt, Brenden Lake, Thomas L. Griffiths
Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction. CoRR (2024)
Liyi Zhang, Michael Y. Li, Thomas L. Griffiths
What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions. CoRR (2024)
Gianluca M. Bencomo, Jake Snell, Thomas L. Griffiths
Implicit Maximum a Posteriori Filtering via Adaptive Optimization. ICLR (2024)
Ryan Liu, Theodore R. Sumers, Ishita Dasgupta, Thomas L. Griffiths
How do Large Language Models Navigate Conflicts between Honesty and Helpfulness? CoRR (2024)
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice. CoRR (2024)
Allison Chen, Ilia Sucholutsky, Olga Russakovsky, Thomas L. Griffiths
Analyzing the Roles of Language and Vision in Learning from Limited Data. CoRR (2024)
Raja Marjieh, Sreejan Kumar, Declan Campbell, Liyi Zhang, Gianluca M. Bencomo, Jake Snell, Thomas L. Griffiths
Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases. CoRR (2024)
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
Recovering Mental Representations from Large Language Models with Markov Chain Monte Carlo. CoRR (2024)
Ioana Marinescu, R. Thomas McCoy, Thomas L. Griffiths
Distilling Symbolic Priors for Concept Learning into Neural Networks. CoRR (2024)
Akshara Prabhakar, Thomas L. Griffiths, R. Thomas McCoy
Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning. CoRR (2024)
Andi Peng, Ilia Sucholutsky, Belinda Z. Li, Theodore R. Sumers, Thomas L. Griffiths, Jacob Andreas, Julie A. Shah
Learning with Language-Guided State Abstractions. CoRR (2024)
Andi Peng, Andreea Bobu, Belinda Z. Li, Theodore R. Sumers, Ilia Sucholutsky, Nishanth Kumar, Thomas L. Griffiths, Julie A. Shah
Preference-Conditioned Language-Guided Abstraction. CoRR (2024)
Andi Peng, Andreea Bobu, Belinda Z. Li, Theodore R. Sumers, Ilia Sucholutsky, Nishanth Kumar, Thomas L. Griffiths, Julie A. Shah
Preference-Conditioned Language-Guided Abstraction. HRI (2024)
Maya Malaviya, Ilia Sucholutsky, Thomas L. Griffiths
Pushing the Limits of Learning from Limited Data. AAAI Spring Symposia (2024)
Jian-Qiao Zhu, Thomas L. Griffiths
Eliciting the Priors of Large Language Models using Iterated In-Context Learning. CoRR (2024)
Thomas L. Griffiths, Jian-Qiao Zhu, Erin Grant, R. Thomas McCoy
Bayes in the age of intelligent machines. CoRR (2023)
Aditi Jha, Joshua C. Peterson, Thomas L. Griffiths
Extracting Low-Dimensional Psychological Representations from Convolutional Neural Networks. Cogn. Sci. 47 (1) (2023)
Ilia Sucholutsky, Thomas L. Griffiths
Alignment with human representations supports robust few-shot learning. CoRR (2023)
Raja Marjieh, Nori Jacoby, Joshua C. Peterson, Thomas L. Griffiths
The Universal Law of Generalization Holds for Naturalistic Stimuli. CoRR (2023)
Natalia Vélez, Brian R. Christian, Mathew D. Hardy, Bill D. Thompson, Thomas L. Griffiths
How do Humans Overcome Individual Computational Limitations by Working Together? Cogn. Sci. 47 (1) (2023)
Raja Marjieh, Ilia Sucholutsky, Thomas A. Langlois, Nori Jacoby, Thomas L. Griffiths
Analyzing Diffusion as Serial Reproduction. ICML (2023)
Daniel Reichman, Falk Lieder, David D. Bourgin, Nimrod Talmon, Thomas L. Griffiths
The Computational Challenges of Means Selection Problems: Network Structure of Goal Systems Predicts Human Performance. Cogn. Sci. 47 (8) (2023)
Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan, Thomas L. Griffiths
Cognitive Architectures for Language Agents. CoRR (2023)
R. Thomas McCoy, Shunyu Yao, Dan Friedman, Matthew Hardy, Thomas L. Griffiths
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve. CoRR (2023)
Michael Y. Li, Fred Callaway, William D. Thompson, Ryan P. Adams, Thomas L. Griffiths
Learning to Learn Functions. Cogn. Sci. 47 (4) (2023)
Zi Wang, Alexander Ku, Jason Baldridge, Thomas L. Griffiths, Been Kim
Gaussian Process Probes (GPP) for Uncertainty-Aware Probing. CoRR (2023)
Ruiqi He, Carlos G. Correa, Thomas L. Griffiths, Mark K. Ho
Structurally guided task decomposition in spatial navigation tasks. CoRR (2023)
Andrea Wynn, Ilia Sucholutsky, Thomas L. Griffiths
Learning Human-like Representations to Enable Learning Human Values. CoRR (2023)
Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, Karthik Narasimhan
Tree of Thoughts: Deliberate Problem Solving with Large Language Models. CoRR (2023)
Kerem Oktar, Ilia Sucholutsky, Tania Lombrozo, Thomas L. Griffiths
Dimensions of Disagreement: Unpacking Divergence and Misalignment in Cognitive Science and Artificial Intelligence. CoRR (2023)
Qihong Lu, Tan T. Nguyen, Qiong Zhang, Uri Hasson, Thomas L. Griffiths, Jeffrey M. Zacks, Samuel J. Gershman, Kenneth A. Norman
Toward a More Biologically Plausible Neural Network Model of Latent Cause Inference. CoRR (2023)
Sreejan Kumar, Ishita Dasgupta, Nathaniel D. Daw, Jonathan D. Cohen, Thomas L. Griffiths
Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning. PLoS Comput. Biol. 19 (8) (2023)
Ilia Sucholutsky, Ruairidh M. Battleday, Katherine M. Collins, Raja Marjieh, Joshua C. Peterson, Pulkit Singh, Umang Bhatt, Nori Jacoby, Adrian Weller, Thomas L. Griffiths
On the informativeness of supervision signals. UAI (2023)
Michael Chang, Alyssa L. Dayan, Franziska Meier, Thomas L. Griffiths, Sergey Levine, Amy Zhang
Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement. CoRR (2023)
Carlos G. Correa, Mark K. Ho, Frederick Callaway, Nathaniel D. Daw, Thomas L. Griffiths
Humans decompose tasks by trading off utility and computational cost. PLoS Comput. Biol. 19 (6) (2023)
Minkyu Shin, Jin Kim, Bas van Opheusden, Thomas L. Griffiths
Superhuman Artificial Intelligence Can Improve Human Decision Making by Increasing Novelty. CoRR (2023)
Michael Chang, Alyssa L. Dayan, Franziska Meier, Thomas L. Griffiths, Sergey Levine, Amy Zhang
Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement. ICLR (2023)
Ryan Liu, Howard Yen, Raja Marjieh, Thomas L. Griffiths, Ranjay Krishna
Improving Interpersonal Communication by Simulating Audiences with Language Models. CoRR (2023)
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller, Andi Peng, Andreea Bobu, Been Kim, Bradley C. Love, Erin Grant, Jascha Achterberg, Joshua B. Tenenbaum, Katherine M. Collins, Katherine L. Hermann, Kerem Oktar, Klaus Greff, Martin N. Hebart, Nori Jacoby, Qiuyi Zhang, Raja Marjieh, Robert Geirhos, Sherol Chen, Simon Kornblith, Sunayana Rane, Talia Konkle, Thomas P. O'Connell, Thomas Unterthiner, Andrew K. Lampinen, Klaus-Robert Müller, Mariya Toneva, Thomas L. Griffiths
Getting aligned on representational alignment. CoRR (2023)
Raja Marjieh, Ilia Sucholutsky, Pol van Rijn, Nori Jacoby, Thomas L. Griffiths
What Language Reveals about Perception: Distilling Psychophysical Knowledge from Large Language Models. CoRR (2023)
Liyi Zhang, R. Thomas McCoy, Theodore R. Sumers, Jian-Qiao Zhu, Thomas L. Griffiths
Deep de Finetti: Recovering Topic Distributions from Large Language Models. CoRR (2023)
Jake C. Snell, Gianluca M. Bencomo, Thomas L. Griffiths
A Metalearned Neural Circuit for Nonparametric Bayesian Inference. CoRR (2023)
Michael Y. Li, Erin Grant, Thomas L. Griffiths
Gaussian Process Surrogate Models for Neural Networks. UAI (2023)
R. Thomas McCoy, Thomas L. Griffiths
Modeling rapid language learning by distilling Bayesian priors into artificial neural networks. CoRR (2023)
Levin Brinkmann, Fabian Baumann, Jean-François Bonnefon, Maxime Derex, Thomas F. Müller, Anne-Marie Nussberger, Agnieszka Czaplicka, Alberto Acerbi, Thomas L. Griffiths, Joseph Henrich, Joel Z. Leibo, Richard McElreath, Pierre-Yves Oudeyer, Jonathan Stray, Iyad Rahwan
Machine Culture. CoRR (2023)
Raja Marjieh, Pol van Rijn, Ilia Sucholutsky, Theodore R. Sumers, Harin Lee, Thomas L. Griffiths, Nori Jacoby
Words are all you need? Language as an approximation for human similarity judgments. ICLR (2023)
Carlos G. Correa, Sophia Sanborn, Mark K. Ho, Frederick Callaway, Nathaniel D. Daw, Thomas L. Griffiths
Exploring the hierarchical structure of human plans via program generation. CoRR (2023)
Gianluca M. Bencomo, Jake C. Snell, Thomas L. Griffiths
Implicit Maximum a Posteriori Filtering via Adaptive Optimization. CoRR (2023)
Sunayana Rane, Mark K. Ho, Ilia Sucholutsky, Thomas L. Griffiths
Concept Alignment as a Prerequisite for Value Alignment. CoRR (2023)
Yufei Tian, Abhilasha Ravichander, Lianhui Qin, Ronan Le Bras, Raja Marjieh, Nanyun Peng, Yejin Choi, Thomas L. Griffiths, Faeze Brahman
MacGyver: Are Large Language Models Creative Problem Solvers? CoRR (2023)
Raja Marjieh, Ilia Sucholutsky, Thomas A. Langlois, Nori Jacoby, Thomas L. Griffiths
Analyzing Diffusion as Serial Reproduction. CoRR (2022)
Ilia Sucholutsky, Raja Marjieh, Nori Jacoby, Thomas L. Griffiths
On the Informativeness of Supervision Signals. CoRR (2022)
Mark K. Ho, Thomas L. Griffiths
Cognitive Science as a Source of Forward and Inverse Models of Human Decisions for Robotics and Control. Annu. Rev. Control. Robotics Auton. Syst. 5 (2022)
Rachit Dubey, Thomas L. Griffiths, Peter Dayan
The pursuit of happiness: A reinforcement learning perspective on habituation and comparisons. PLoS Comput. Biol. 18 (8) (2022)
Mathew D. Hardy, Bill D. Thompson, P. M. Krafft, Thomas L. Griffiths
Bias amplification in experimental social networks is reduced by resampling. CoRR (2022)
Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths, Dylan Hadfield-Menell
Linguistic communication as (inverse) reward design. CoRR (2022)
Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths, Dylan Hadfield-Menell
How to talk so your robot will learn: Instructions, descriptions, and pragmatics. CoRR (2022)
Michael Y. Li, Erin Grant, Thomas L. Griffiths
Gaussian process surrogate models for neural networks. CoRR (2022)
Raja Marjieh, Pol van Rijn, Ilia Sucholutsky, Theodore R. Sumers, Harin Lee, Thomas L. Griffiths, Nori Jacoby
Words are all you need? Capturing human sensory similarity with textual descriptors. CoRR (2022)
Sreejan Kumar, Ishita Dasgupta, Raja Marjieh, Nathaniel D. Daw, Jonathan D. Cohen, Thomas L. Griffiths
Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning. CoRR (2022)
Sreejan Kumar, Carlos G. Correa, Ishita Dasgupta, Raja Marjieh, Michael Y. Hu, Robert D. Hawkins, Nathaniel D. Daw, Jonathan D. Cohen, Karthik Narasimhan, Thomas L. Griffiths
Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines. CoRR (2022)
Sunayana Rane, Mira L. Nencheva, Zeyu Wang, Casey Lew-Williams, Olga Russakovsky, Thomas L. Griffiths
Predicting Word Learning in Children from the Performance of Computer Vision Systems. CoRR (2022)
Takateru Yamakoshi, Thomas L. Griffiths, Robert D. Hawkins
Probing BERT's priors with serial reproduction chains. ACL (Findings) (2022)
Michael Chang, Thomas L. Griffiths, Sergey Levine
Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation. CoRR (2022)
Mathew D. Hardy, Peaks M. Krafft, Bill Thompson, Thomas L. Griffiths
Overcoming Individual Limitations Through Distributed Computation: Rational Information Accumulation in Multigenerational Populations. Top. Cogn. Sci. 14 (3) (2022)
Carlos G. Correa, Mark K. Ho, Frederick Callaway, Nathaniel D. Daw, Thomas L. Griffiths
Humans decompose tasks by trading off utility and computational cost. CoRR (2022)
Thomas A. Langlois, H. Charles Zhao, Erin Grant, Ishita Dasgupta, Thomas L. Griffiths, Nori Jacoby
Passive attention in artificial neural networks predicts human visual selectivity. NeurIPS (2021)