Yilei Man, Yang Chen, Jingcai Guo · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28483 · open-access PDF
A aprendizagem da dinâmica latente é fundamental para a construção de modelos mundiais condicionados pela ação para o planejamento. Entre as famílias existentes, as Arquiteturas Preditivas Embutidas Conjuntas (JEPAs) oferecem um quadro natural, modelando transições diretamente no espaço latente, em vez de no nível de pixels. No entanto, dois problemas permanecem nos modelos mundiais baseados na JEPA: (i) a aterramento físico carece de agregação explícita do contexto temporal e (ii) o planejamento de ações sempre depende excessivamente de distribuições de amostragem genéricas.
Machine translation (Meta M2M100); the English original follows.
Learning latent dynamics is fundamental to building action-conditioned world models for planning. Among existing families, Joint Embedding Predictive Architectures (JEPAs) offer a natural framework by modeling transitions directly in latent space rather than at the pixel level. However, two issues remain in JEPA-based world models: (i) physical grounding lacks explicit aggregation of temporal context and (ii) action planning always overly relies on generic sampling distributions. To this end, we propose $\mathcal{G}$-JEPA, which incorporates temporal context into physical grounding for latent
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=2610.28483, 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