metaai·lightalo unofficial · independent
Universe / World Models & Embodied AI / V-JEPA 2
World Models & Embodied AI · 2025

V-JEPA 2

It learned physics from video — then drove a robot arm it had never met

open source ViT-L 300M / ViT-H 600M / ViT-g 1B (V-JEPA 2.1 spans 80M-2B) params

Latest: V-JEPA 2.1 (Mar 16, 2026) — new recipe for high-quality, temporally consistent dense features; family now spans 80M to 2B parameters

Meta's flagship world model, released June 11, 2025: trained on over 1 million hours of video plus only ~62 hours of robot data, its action-conditioned variant (V-JEPA 2-AC) enabled zero-shot planning on real Franka robot arms in unseen labs. Meta simultaneously released three physical-reasoning benchmarks (IntPhys 2, MVPBench, CausalVQA).

Why it matters

V-JEPA 2 is the strongest evidence yet for JEPA-style world models: trained on over a million hours of video plus under 62 hours of robot data, its action-conditioned variant planned zero-shot on Franka arms in labs it never saw — 100% on reaching, 80% on pick-and-place — and set new action-anticipation records.

Facts

Try it yourself

Lineage

Descends fromV-JEPA
Led toVL-JEPA

See the whole family tree →

Sources

More in World Models & Embodied AI

Meta Locate 3DPARTNROpenEQAMeta MotivoI-JEPAEgo-Exo4D

Read the World Models & Embodied AI story on the sky →

✦ Open on the map Explore World Models & Embodied AI Quiz me