Paper Notes

标签: V-JEPA

此标签下有4条笔记。

  • 2026年5月

    Latent Video Prediction Learns Better World Models

  • 2026年5月

    Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models

  • 2025年10月

    Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density

  • 2024年2月

    Revisiting Feature Prediction for Learning Visual Representations from Video


Created with Quartz v4.5.2 © 2026

  • Source