EEmbodied AI Hub
ModelFeaturedFully open

V-JEPA

Meta video JEPA world-model style representations — predictive features for physical video understanding.

Why: Influential open predictive video representation model

Official / sourcePaperBack to Model
世界模型表征MetaOpen source

Overview

V-JEPA is a curated model on Embodied AI Hub.

Meta video JEPA world-model style representations — predictive features for physical video understanding.

Why it matters: Influential open predictive video representation model

Always verify install pins, licenses, and hardware requirements on the official site before production use.

Who it is for

Builders mapping open embodied stacks; researchers comparing SOTA baselines.

Key highlights

  • Meta video JEPA world-model style representations — predictive features for physical video understanding.
  • Type: model; tags: 世界模型, 表征, Meta, 开源
  • Hub recommended

When to use

  • You need this category of open resource in your stack map
  • You are shortlisting baselines before deep evaluation

When not to use

  • License or hardware constraints block adoption
  • You only need a closed commercial stack with vendor SLA

Getting started

  1. 1Open the official URL and read the README / model card.
  2. 2Check license and citation requirements.
  3. 3Run the smallest official example before scaling.
  4. 4Cross-link related hub resources for a full pipeline.

Papers & reading

Caveats & pitfalls

  • Hub cards are curated summaries — verify upstream docs.
  • Stars and release names drift; treat metadata as approximate.

Content reviewed 2026-07-28