Eric Jang
@ericjang11
Joined January 2014
4.1K Following 139.3K Followers
Cool set of experiments! Useful for folks getting into WAMs
WAMs are popular because of their promise of better generalization. Is that true? We started playing with Video-Action-Model (VAMs) and realized a gap: video model backbones can compositionally generalize but VAMs often do not.
We coin this the Video-Action-Generalization (VAG) gap and present a study on how to explain and improve it. More details:
🧵 below
Show more
