Picture for Gary Marcus

Gary Marcus

Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyc

Add code
Jul 31, 2023
Viaarxiv icon

A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Human Language?

Add code
Jul 26, 2023
Viaarxiv icon

Testing AI performance on less frequent aspects of language reveals insensitivity to underlying meaning

Add code
Feb 27, 2023
Viaarxiv icon

DALL-E 2 Fails to Reliably Capture Common Syntactic Processes

Add code
Oct 25, 2022
Viaarxiv icon

A very preliminary analysis of DALL-E 2

Add code
May 02, 2022
Viaarxiv icon

The Defeat of the Winograd Schema Challenge

Add code
Jan 16, 2022
Figure 1 for The Defeat of the Winograd Schema Challenge
Figure 2 for The Defeat of the Winograd Schema Challenge
Figure 3 for The Defeat of the Winograd Schema Challenge
Figure 4 for The Defeat of the Winograd Schema Challenge
Viaarxiv icon

A Review of Winograd Schema Challenge Datasets and Approaches

Add code
Apr 23, 2020
Viaarxiv icon

The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence

Add code
Feb 19, 2020
Figure 1 for The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Figure 2 for The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Figure 3 for The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Figure 4 for The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Viaarxiv icon

Innateness, AlphaZero, and Artificial Intelligence

Add code
Jan 17, 2018
Viaarxiv icon

Deep Learning: A Critical Appraisal

Add code
Jan 02, 2018
Viaarxiv icon