Sub-JEPA stabilizes JEPA-based world models by enforcing isotropic Gaussian priors in random subspaces, achieving better bias-variance balance and outperforming LeWM on continuous control tasks.
Diffusion policy: Vi- suomotor policy learning via action diffusion.The International Journal of Robotics Research, 44(10- 11):1684–1704
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
Sub-JEPA stabilizes JEPA-based world models by enforcing isotropic Gaussian priors in random subspaces, achieving better bias-variance balance and outperforming LeWM on continuous control tasks.