V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning | Deep Learning JP

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

2025年09月30日 riyo.ono dls-2025, papers

【DL輪読会】 V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning by @DeepLearning2023

%d人のブロガーが「いいね」をつけました。