Autoregressive probabilistic world models trained on raw videos yield emergent object segmentation, 3D controllability, and physical relationship inference via multi-future motion correlation analysis.
Understanding segment anything model: Sam is biased towards texture rather than shape
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Physical Object Understanding with a Physically Controllable World Model
Autoregressive probabilistic world models trained on raw videos yield emergent object segmentation, 3D controllability, and physical relationship inference via multi-future motion correlation analysis.