Weiqi Zhang, Wenyuan Zhang, Yu-Shen Liu, Junsheng Zhou · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28631 · open-access PDF
Os modelos mundiais atuais para a simulação explícita do mundo geralmente seguem dois caminhos distintos: (1) modelos de geração de vídeo (por exemplo, Sora), que simulam aparências realistas, mas não preservam a consistência 3D; e (2) modelos de geração 3D (por exemplo, Marble), que geram cenas geometricamente consistentes, mas geralmente produzem observações estáticas, menos realistas. apresentamos AEON, uma estrutura unificada que conecta modelos mundiais baseados em vídeo e 3D e combina os benefícios de ambos.
Machine translation (Meta M2M100); the English original follows.
Current world models for explicit world simulation typically follow two distinct pathways: (1) video generative models (e.g., Sora), which simulate realistic appearances but fail to preserve 3D consistency; and (2) 3D generative models (e.g., Marble), which generate geometrically consistent scenes but often yield static, less realistic observations. We present AEON, a unified framework that bridges video-based and 3D-based world models and combines the benefits of both. The key insight of AEON lies in a generative model that operates within the text- or image-conditioned video latent space whi
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=2610.28631, 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