NLP

Transformers are Graph Neural Networks

Chaitanya K. Joshi
Neural Nets

Shortcuts: How Neural Networks Love to Cheat

Jörn-Henrik Jacobsen, Robert Geirhos, Claudio Michaelis
Overviews

How to Stop Worrying About Compositionality

Aurelie Herbelot
Overviews

Challenges of Comparing Human and Machine Perception

Judy Borowski and Christina Funke
Ethics

Lessons from the PULSE Model and Discussion

Andrey Kurenkov
Speech-To-Text

A Speech-To-Text Practitioner’s Criticisms of Industry and Academia

Alexander Veysov
Speech-To-Text

Towards an ImageNet Moment for Speech-to-Text

Alexander Veysov
Best Practices

Quantifying Independently Reproducible Machine Learning

Edward Raff
Perspectives

GPT-2 and the Nature of Intelligence

Gary Marcus
Policy

The Economics of AI Today

Juan Mateos-Garcia
Conference

Is NeurIPS Getting Too Big?

Andrey Kurenkov