Leaderboard
World ModelsOpen weights
V-JEPA 2
Self-supervised video joint-embedding predictive architecture; learns world dynamics for prediction and robot planning.
Crosshair Index
—
#5 of 5 · World Models
- Provider
- Meta AI
- Released
- 2025-06-11
- Parameters
- 1.2B
Scorecard
No published results yet. This model is tracked and will populate as standardized results become available.