Paper Notes

标签: self-supervised-video

此标签下有2条笔记。

  • 2026年5月

    DiLA: Disentangled Latent Action World Models

  • 2025年6月

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


Created with Quartz v4.5.2 © 2026

  • Source