GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning

Excerpt

arXiv:2610.02091v1 Announce Type: cross Abstract: Despite progress in vision-language models, 3D spatial reasoning from 2D images remains challenging. Text-based methods describe intermediate geometry with discrete tokens, limiting fidelity for continuous spatial relations. Continuous latents offer richer representations, but a single latent type does not explicitly separate the cues needed across spatial tasks. Decomposed spatial latents address this by representing position, direction, and glo