Picture for Thomas L. Griffiths

Thomas L. Griffiths

Predicting Multi-Agent Specialization via Task Parallelizability

Add code
Mar 19, 2025
Viaarxiv icon

Using the Tools of Cognitive Science to Understand Large Language Models at Different Levels of Analysis

Add code
Mar 17, 2025
Viaarxiv icon

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks

Add code
Feb 27, 2025
Viaarxiv icon

On Benchmarking Human-Like Intelligence in Machines

Add code
Feb 27, 2025
Viaarxiv icon

Conformal Prediction as Bayesian Quadrature

Add code
Feb 18, 2025
Viaarxiv icon

What is a Number, That a Large Language Model May Know It?

Add code
Feb 03, 2025
Viaarxiv icon

RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation

Add code
Jan 15, 2025
Viaarxiv icon

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem

Add code
Oct 31, 2024
Figure 1 for Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Figure 2 for Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Figure 3 for Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Figure 4 for Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Viaarxiv icon

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse

Add code
Oct 27, 2024
Viaarxiv icon

Centaur: a foundation model of human cognition

Add code
Oct 26, 2024
Figure 1 for Centaur: a foundation model of human cognition
Figure 2 for Centaur: a foundation model of human cognition
Figure 3 for Centaur: a foundation model of human cognition
Figure 4 for Centaur: a foundation model of human cognition
Viaarxiv icon