Preprint
Oct 2026
Time-JEPA: Grounding Video World Models with Physical Time Series
Video world models learn how visual environments evolve by predicting missing or future content. However, physical-state information can provide useful context for predicting how environments evolve. Prior work incorporates this information through different mechanisms: domain-specific physical laws can complicate mult...
Shen-Yi Li, Zi-Yang Zhang, Wen Wu et al.
· 0 citations