Metraipolis › archive › dc_73cf8982aa55

WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon — arXiv:2609.35560

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35560
License (as archived)
CC0-1.0
Archived
2026-10-07T23:54:51.546Z
SHA-256 of the archived text
7636550e3fe279f7a68829c2a42d81963df585314a59878dd1874556771db4e5
Stable URL of this page
https://metraipolis.com/documento/dc_73cf8982aa55

How to cite

WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon — arXiv:2609.35560 — arXiv (en), https://arxiv.org/abs/2609.35560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73cf8982aa55 (Metraipolis archive dc_73cf8982aa55, sha256 7636550e3fe279f7a68829c2a42d81963df585314a59878dd1874556771db4e5)
BibTeX
@misc{dc73cf8982aa55,
  title = {WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon — arXiv:2609.35560},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35560},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73cf8982aa55; sha256 7636550e3fe279f7a68829c2a42d81963df585314a59878dd1874556771db4e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Interactive world models require responding in real time to versatile controls and maintaining long-horizon consistency. However, modeling heterogeneous controls remains difficult, while explosive contexts and unstable distillation impede achieving both long-horizon consistency and real-time responsiveness. In this paper, we present WorldPlay2, an interactive world model that couples a factorized hybrid control interface with a co-design of compressed memory and stable distillation. 1) Our factorized hybrid control interface integrates frame-aligned action control with structured semantic control that explicitly disentangles scene appearance, character identity, and dynamic semantic events, thereby facilitating effective control learning. 2) To achieve efficient long-horizon modeling, we compress historical contexts into compact memory tokens shared by the autoregressive student and the bidirectional teacher. This design enables clip-wise, memory-conditioned score evaluation instead of jointly processing an entire long rollout, substantially reducing distillation overhead. 3) We further propose Stable Forcing, which initializes the autoregressive student via a few-step strategy and leverages full-rollout replay to preserve the quality of long-horizon rollouts, ensuring robust and stable distillation. Extensive experiments demonstrate the strong generalizability of our model and its superior performance compared to existing methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.35560 — 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 2026-10-07T23:29:27.591Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).