Computerworld June 12, 2025
Taryn Plumb

It is Meta’s next step toward achieving “advanced machine intelligence,” and could be useful in manufacturing automation, surveillance analytics, in-building logistics, robotics, and other more advanced use cases.

Thanks largely to AI, robotics has come a long way in a short period of time, but robots continue to struggle in certain scenarios that they haven’t been trained for and need to adjust to.

This week, Meta (Nasdaq:META) said it has overcome some of these major hurdles with its new open-source Video Joint Embedding Predictive Architecture 2 (V-JEPA 2), the first world model trained primarily on video. V-JEPA 2 can predict next actions and respond to environments it hasn’t interacted with before.

“Meta’s recent unveiling of V-JEPA 2 marks a quiet...

Today's Sponsors

Venturous
ZeOmega

Today's Sponsor

Venturous

 
Topics: AI (Artificial Intelligence), Robotics/RPA, Technology
5 robotic surgery trends to watch in 2026
CES 2026 - Robots Are Movin’ Blue Collar Autonomy
What Really Happens When a Robot Draws Your Blood
The physical AI models market map: Behind the arms race to control robot intelligence
Nvidia's Jensen Huang says AI robotics is a 'once-in-a-generation' opportunity for Europe

Share Article