← Model index
Physical AI / embodied world models

Meta V-JEPA 2

V-JEPA 2 is Meta’s video-based world model for understanding, predicting, and planning in physical environments. It is oriented toward robot reasoning and physical intuition rather than generating walkable 3D worlds for creators.

ResearchPaper / researchUpdated 2026-06-09

Overview

StatusResearch
AccessPaper / research
Released2025
Inputsvideo, image goals, robot observations
Outputslatent predictions, planning signals, robot action support
Best forphysical reasoning, robot planning, video understanding, embodied AI research

Why it matters

V-JEPA 2 helps define the embodied-AI side of the world model category: predicting outcomes, planning actions, and understanding physical dynamics.

Roamscape use

Tracked as a scientific world model reference for physical AI and embodied reasoning.

Strengths

  • physical-world prediction
  • planning orientation
  • robotics relevance
  • strong research framing

Limitations

  • not a 3D world generator
  • not a consumer creator tool
  • outputs are not exportable worlds

Sources

Related models