How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms
The results suggest that intuitive-physics knowledge emerges reliably in pretrained video representations, but its accessibility depends strongly on pretraining paradigm, representational depth, and readout mechanism.
Samuele Punzo, N. Caselli, Ippokratis Pantelidis et al.
· 3 citations