metaai·lightalo unofficial · independent
Universe / World Models & Embodied AI / Meta Locate 3D
World Models & Embodied AI · 2025

Meta Locate 3D

'The flower vase near the TV console' — located in 3D

open source 576M params

Latest: Locate 3D (Apr 2025)

An end-to-end model (April 2025) that localizes objects in 3D scenes from natural-language queries like 'the flower vase near the TV console' — operating directly on point clouds from RGB-D sensor streams via a 3D-JEPA encoder and language-conditioned decoder that outputs 3D bounding boxes and masks, ready for real robots.

Why it matters

Locate 3D turns a sentence — 'the flower vase near the TV console' — into a 3D box and mask directly from RGB-D point clouds, using a self-supervised 3D-JEPA encoder, so robots can ground language in real scenes. Its 130,000-annotation dataset roughly doubled the world's supply of 3D referring expressions.

Facts

Try it yourself

Sources

More in World Models & Embodied AI

V-JEPA 2VL-JEPAV-JEPAPARTNROpenEQAMeta Motivo

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

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