Zhichao Zhai, Menglei Zhao, Guikun Chen, Zihao Yan, Kanzhi Wu, Wenguan Wang, Jun Xiao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.30127 · open-access PDF
As habilidades dos modelos de linguagem para interpretar tarefas e gerar programas oferecem uma base promissora para o raciocínio espacial 3D. No entanto, seguir as instruções espaciais em cenas 3D requer que os programas construam referências geométricas que a linguagem deixa implícita. Neste trabalho, apresentamos o VoxProg, que formula a colocação de objetos 3D através da programação voxel: um modelo de linguagem traduz as interpretações de tarefas em programas executáveis sobre visões voxel locais de superfícies de cena.
Machine translation (Meta M2M100); the English original follows.
Language models' abilities to interpret tasks and generate programs offer a promising basis for 3D spatial reasoning. Yet following spatial instructions in 3D scenes requires programs to construct geometric references that language leaves implicit. In this work, we introduce VoxProg, which formulates 3D object placement through voxel programming: a language model translates task interpretations into executable programs over local voxel views of scene surfaces. Because these views index surface geometry on regular grids with explicit coordinates and neighborhood relations, an evidence program c
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30127, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange