HKUST, ARC Lab (Tencent IEG), University of Hong Kong & UT Austin · Geometry-Native World Model

GAE

Embeds geometry directly into the generative latent space, so one shared latent decodes to RGB, depth, camera pose and 3D geometry together instead of treating geometry as an external constraint bolted onto an appearance-only latent. Freezes a geometry foundation model and trains only a compact codec compressing 3,072 channels down to 128, then uses flow matching to generate latents conditioned on text or reference images. Against RAEv2, Stable Diffusion's VAE and the Wan v2.1 video VAE it reports FVD improvements of 12.7% on RealEstate10K and 23.1% on DL3DV, and halves camera trajectory error, ranking first on geometric consistency on 40 of 64 benchmark scenes. Code and an interactive text-to-image demo producing downloadable point clouds are released.