Back to today’s briefing

Story perspectives

Meta Unveils V-JEPA 2: AI Model Transforms Robot Perception

6/12/2025

50 8

Summary

Story summary

Meta has launched its groundbreaking V-JEPA 2 AI model, revolutionizing how robots perceive the physical world. With training on over 1 million hours of video, this model harnesses common sense reasoning to predict actions. Impressively, V-JEPA 2 operates 30 times faster than Nvidia's model, pushing the boundaries of AI in real-world applications.

1 of 1

Story summary

Meta has launched its groundbreaking V-JEPA 2 AI model, revolutionizing how robots perceive the physical world. With training on over 1 million hours of video, this model harnesses common sense reasoning to predict actions. Impressively, V-JEPA 2 operates 30 times faster than Nvidia's model, pushing the boundaries of AI in real-world applications.