arXiv cs.CV
· Papers
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
arXiv:2605.29655v3 Announce Type: replace Abstract: Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based representations discard deterministic spatial ordering, leading to ambiguous sequence pre