Alan-Barsag Gazzaev

AquaJEPA: Action-Conditioned Multimodal Predictive Representations for Underwater Robot Dynamics

AquaJEPA is introduced, an action-conditioned joint-embedding predictive model that fuses an RGB camera, forward-looking sonar, and proprioception with explicit sensor validity that achieves the best aggregate closed-loop performance and significantly outperforms three action-conditioned predictive baselines in paired...