Octrees as an Explicit 3D Language
Existing 3D large language models (LLMs) compromise on two fronts: they compress shapes into latent codebook indices or coordinate text, which removes spatial structure from what the model observes, and they acquire the 3D modality by fine-tuning the backbone, which overwrites its general language…
By Ran Dan, Si-Tong Wei, Pengfei Xiong, Wei Zhang, Yadong Mu, Peng-Shuai WangarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Oct 5, 2026.
Comments
Sign in to join the discussion.