MDN-VJEPA: Multimodal Probabilistic Joint-Embedding World Models
MDN-VJEPA introduces a probabilistic framework called MDN-VJEPA to learn world models by predicting missing information. It uses a Mixture Density Network (MDN) instead of simple point predictions, allowing it to model multiple plausible future scenarios simultaneously. The model enforces a three-level hierarchy to ensure these multimodal predictions form coherent, temporally consistent trajectories.