A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.
3d scene understanding through local random ac- cess sequence modeling.arXiv preprint arXiv:2504.03875,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Autoregressive probabilistic world models trained on raw videos yield emergent object segmentation, 3D controllability, and physical relationship inference via multi-future motion correlation analysis.
citing papers explorer
-
Zero-shot World Models Are Developmentally Efficient Learners
A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.