arXiv cs.AI
· Papers
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
arXiv:2607.06565v1 Announce Type: cross Abstract: Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit. Existing methods concatenate text and 3D tokens into a flat sequence and rely on self-attention,