Metraipolis › archive › dc_acc3676a534d
World-as-Graph: Relational World Modeling Through Latent Space Graphs — arXiv:2609.38927
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38927
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:45:40.649Z
- SHA-256 of the archived text
99212bae46531ff0e96dfb46d46753664a7f2cc2fed1179790e75014fba74f25- Stable URL of this page
https://metraipolis.com/documento/dc_acc3676a534d
How to cite
World-as-Graph: Relational World Modeling Through Latent Space Graphs — arXiv:2609.38927 — arXiv (en), https://arxiv.org/abs/2609.38927 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_acc3676a534d (Metraipolis archive dc_acc3676a534d, sha256 99212bae46531ff0e96dfb46d46753664a7f2cc2fed1179790e75014fba74f25)
BibTeX
@misc{dcacc3676a534d,
title = {World-as-Graph: Relational World Modeling Through Latent Space Graphs — arXiv:2609.38927},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38927},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_acc3676a534d; sha256 99212bae46531ff0e96dfb46d46753664a7f2cc2fed1179790e75014fba74f25},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38927. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World models aim to learn representations of real-world environments and predict their future evolution. Recent object-centric world models have made expressive progress by representing visual scenes as sets of object-level latent states, but object-object relations are often captured only implicitly, which limits explicit relational and temporal structure modeling and object-centric dynamic memory modeling. To address such challenges, we propose World-As-Graph (WAG), a graph-based object-centric world model that introduces relational inductive bias into JEPA-style predictive representation learning. The proposed WAG contains two main modules: (1) Relation-aware structure induction, which constructs time-varying latent graphs from object-centric slots and designs relation-aware object masking policies to guide relational object representation learning in latent space; (2) Object-centric memory transition, which maintains and updates object-level dynamic states by combining relational information from neighboring objects with historical memory, enabling effective autoregressive future prediction. Extensive experiments on both visual reasoning and robotic manipulation tasks could demonstrate the superior performance of our proposed WAG. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.38927 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T13:18:10.292Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).