Training a system to predict what will happen next in a video is a natural approach for learning world understanding because if a system can predict future video frames it presumably has learned the underlying structure of the world; however, this approach for video fails where it works for text: with text there are a finite number of possible next tokens so prediction can succeed, but with video there are infinite possible pixel configurations making exact frame prediction intractable.
causalpending
Speaker
Yann LeCunEvidence Quote
“we cannot do this for images for video frames we do not have good ways of representing distributions...bumps into mathematical intractabilities”
Created: 8/11/2026, 1:17:36 AM
Your notes
Loading notes...