EUVIMEDEUVIMED entdecken
Crossref

Discovering Hybrid World Representations with Co-Evolving Foundation Models

Jiajun Wu, Yunzhi Zhang, Hong-Xing Yu, Joy Hsu, Jiayuan Mao

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41020-41024

DOI: 10.1609/aaai.v40i48.42138 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiajun Wu und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This perspective article discusses an emerging research direction: to what extent can foundation models yield usable structure for modeling the physical world? We offer a Markovian formulation of structured world models and outline the notion of multi-level hybrid world representations that support compositional structure. We then review and suggest possible discovery paradigms, spanning distillation, interaction-driven continual learning, and ensemble learning.

Zitieren

APA

Wu, J., Zhang, Y., Yu, H., Hsu, J., & Mao, J. (2026). Discovering Hybrid World Representations with Co-Evolving Foundation Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41020-41024. https://doi.org/10.1609/aaai.v40i48.42138

Vancouver

Wu J, Zhang Y, Yu H, Hsu J, Mao J. Discovering Hybrid World Representations with Co-Evolving Foundation Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41020-41024. doi:10.1609/aaai.v40i48.42138

BibTeX
@article{Wu2026,
  author = {Wu, Jiajun and Zhang, Yunzhi and Yu, Hong-Xing and Hsu, Joy and Mao, Jiayuan},
  title = {Discovering Hybrid World Representations with Co-Evolving Foundation Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41020--41024},
  doi = {10.1609/aaai.v40i48.42138}
}
Kostenlos starten →