Experiments demonstrate that DINO world models can plan object manipulation by optimizing action sequences: pushing T-shaped objects into target positions and manipulating scattered blue chips, showing learned models capture interaction dynamics without explicit physical simulation
factualpending
Speaker
Yann LeCunEvidence Quote
“what you see at the bottom is the internal mental prediction of what the system of the sequence of actions the system was planning”
Created: 8/11/2026, 7:07:43 AM
Your notes
Loading notes...