Vjepa 2 Selfsupervised Video Models Enable Understanding Prediction And Planning
2 mentions across 1 person
Visit ↗All mentions
“V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning”
Scaling Self-Supervised Video Pre-training for Zero-Shot Robotic Planning ↗“This paper explores a self-supervised approach that combines internet-scale video data with a small amount of interaction data (robot trajectories), to develop models capable of understanding, predicting, and planning in the physical world.”
V-JEPA 2: Self-Supervised Video Models for Embodied AI ↗