V-JEPA-MedOS: Temporal Masked Video Prediction as a Pretraining Objective for Surgical World Models
V-JEPA (Bardes et al. 2024) is integrated as the visual backbone of MedOS, a dual-process surgical world model. V-JEPA processes T-frame video clips with aggressive spatiotemporal masking: the context encoder sees only 25% of all N = T × H_p × W_p patches, while the predictor reconstructs 40% target patches via MSE in latent space. An EMA target encoder (momentum=0.996) provides stable regression targets. This replaces the 4-objective MC-JEPA loss (photometric + smoothness + backward + VICReg) with a single MSE objective and shifts temporal scale from 2-frame pairs (33ms) to T-frame clips (seconds). All 57 tests pass (37 original + 20 new V-JEPA tests). A mini model (32px, 4-frame, embed_dim=64) achieves VJEPA loss=1.2909 and confirmed output shapes robot_waypoints=(2,3,6). V-JEPA captures procedure-level temporal dependencies that 2-frame MC-JEPA misses.