Metraipolis › archive › dc_aa83fd248782

MASS: Multiplayer World Models with Authoritative Shared State — arXiv:2608.06257

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06257
License (as archived)
CC0-1.0
Archived
2026-10-31T10:37:45.530Z
SHA-256 of the archived text
91a3638a139fb3d86f07a70a5075e016e348eec10eaf63a476ee4382ded1c395
Stable URL of this page
https://metraipolis.com/documento/dc_aa83fd248782

How to cite

MASS: Multiplayer World Models with Authoritative Shared State — arXiv:2608.06257 — arXiv (en), https://arxiv.org/abs/2608.06257 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa83fd248782 (Metraipolis archive dc_aa83fd248782, sha256 91a3638a139fb3d86f07a70a5075e016e348eec10eaf63a476ee4382ded1c395)
BibTeX
@misc{dcaa83fd248782,
  title = {MASS: Multiplayer World Models with Authoritative Shared State — arXiv:2608.06257},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06257},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa83fd248782; sha256 91a3638a139fb3d86f07a70a5075e016e348eec10eaf63a476ee4382ded1c395},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06257. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current video world models struggle in multiplayer environments because they entangle world state with view-dependent visual latents, leading to redundant compute, view inconsistencies, and poor scalability. We propose MASS (Multiplayer world models with Authoritative Shared State) to resolve this limitation. Inspired by multiplayer game architectures, MASS disentangles world dynamics and view rendering. A learned Logic Engine advances a global, authoritative typed state from joint actions without any hand-written transition function, acting as the sole recurrent memory and synchronization reference. From this shared state, a learned Rendering Engine generates independent and consistent views for any requested camera on demand. This explicit disentangling allows MASS to achieve superior state accuracy and lower cross-view inconsistency compared to state-of-the-art multi-view baselines on a matched multiplayer Snake benchmark. It advances predicted worlds with 1,024 concurrent players for 10,000 recurrent steps. Our results show that explicit, authoritative state modeling provides a practical foundation for scalable and consistent multi-agent world simulation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.06257 — 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 2026-10-31T10:23:31.065Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).