Newest papers

Exploring Temporal Context-Aware Physical Grounding in Latent World Models

Yilei Man, Yang Chen, Jingcai Guo · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28483 · open-access PDF

German

Unter den bestehenden Familien bieten die Joint Embedding Predictive Architectures (JEPAs) einen natürlichen Rahmen, indem sie Übergänge direkt im latenten Raum statt auf Pixelebene modellieren. Jedoch bleiben in den JEPA-basierten Weltmodellen zwei Probleme bestehen: (i) die physische Grundlage fehlt an expliziter Aggregation des zeitlichen Kontexts und (ii) die Aktionsplanung stets übermäßig auf generische Probenverteilungen angewiesen ist. Zu diesem Zweck schlagen wir $\mathcal{G}$-JEPA vor, das den zeitlichen Kontext in die physische Grundlage für latente

Machine translation (Meta M2M100); the English original follows.

Abstract

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange