WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving
WA-JEPA is presented, a V-JEPA-native world-action model designed for autonomous driving planning that employs hybrid future-masked pre-training and recast future prediction as conditional flow matching over latent futures, which substantially improves the model's ability to generate plausible future latents for downst...
Xin-Lin Wang, Yu Xiang, Yuheng Zhou et al.
· 6 citations
· ⚡1