Tag
ALPS is a pretrained ViT-B/16 visual state encoder for world models that unifies physical-state prediction, language alignment, and pixel reconstruction in a single patch-token representation, achieving state-probe performance matching the 3.5x larger V-JEPA 2-L and 85.5% mean policy success on LIBERO when paired with its native text tower.
This NYU/Xi'an Jiaotong paper shows that early representational drift forms a low-dimensional 'scaffold' subspace that networks preferentially reuse when learning later tasks, indicating that early experience leaves a persistent geometric imprint on neural network adaptation.