Picture for Tomer Ullman

Tomer Ullman

Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models

Add code
Nov 26, 2024
Viaarxiv icon

One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity

Add code
Nov 07, 2024
Viaarxiv icon

MMToM-QA: Multimodal Theory of Mind Question Answering

Add code
Jan 16, 2024
Viaarxiv icon

Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks

Add code
Feb 26, 2023
Viaarxiv icon

Type theory in human-like learning and inference

Add code
Oct 04, 2022
Viaarxiv icon

Testing Relational Understanding in Text-Guided Image Generation

Add code
Jul 29, 2022
Figure 1 for Testing Relational Understanding in Text-Guided Image Generation
Figure 2 for Testing Relational Understanding in Text-Guided Image Generation
Figure 3 for Testing Relational Understanding in Text-Guided Image Generation
Figure 4 for Testing Relational Understanding in Text-Guided Image Generation
Viaarxiv icon

A Compositional Object-Based Approach to Learning Physical Dynamics

Add code
Mar 04, 2017
Figure 1 for A Compositional Object-Based Approach to Learning Physical Dynamics
Figure 2 for A Compositional Object-Based Approach to Learning Physical Dynamics
Figure 3 for A Compositional Object-Based Approach to Learning Physical Dynamics
Figure 4 for A Compositional Object-Based Approach to Learning Physical Dynamics
Viaarxiv icon