Metraipolis › archive › dc_8d848154eba3

ReWorld: An Interactive World Model with Long-Horizon Memory — arXiv:2608.23565

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23565
License (as archived)
CC0-1.0
Archived
2026-10-18T07:42:01.847Z
SHA-256 of the archived text
be4044b7adcf5b9523e8819dbb23aafe730feb21f46ef595f6600c75ccf058d6
Stable URL of this page
https://metraipolis.com/documento/dc_8d848154eba3

How to cite

ReWorld: An Interactive World Model with Long-Horizon Memory — arXiv:2608.23565 — arXiv (en), https://arxiv.org/abs/2608.23565 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d848154eba3 (Metraipolis archive dc_8d848154eba3, sha256 be4044b7adcf5b9523e8819dbb23aafe730feb21f46ef595f6600c75ccf058d6)
BibTeX
@misc{dc8d848154eba3,
  title = {ReWorld: An Interactive World Model with Long-Horizon Memory — arXiv:2608.23565},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23565},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d848154eba3; sha256 be4044b7adcf5b9523e8819dbb23aafe730feb21f46ef595f6600c75ccf058d6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23565. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounded one. ReWorld separates the two during training and bounds them at inference. Mixed per-head attention windows confine most heads to the recent past while a small set of global heads attends over the entire history, and random head routing keeps either capability from binding to particular heads; random chunk dropping makes sparse histories in-distribution. At inference the whole past lives under a fixed budget: a bounded KV cache backed by a pose-indexed landmark bank, from which the model retrieves the landmarks nearest the current pose. A metric-scale-aligned data engine places eight sources -- Unreal-rendered fly-throughs, game roaming, and real-world footage -- on one physical action scale, so the same key press moves the camera the same distance in every source, and palindrome trajectories supply the revisit evidence that memory training needs. Distribution-matching distillation confined to a LoRA adapter then compresses sampling to four steps: one backbone serves both a high-fidelity multi-step mode and a real-time interactive one, streaming 704x1280 video across photorealistic, game-style, and stylized worlds. Under a three-axis protocol covering action following, long-horizon recall, and video quality, against six recent interactive world models it attains the best control fidelity ($11.95^\circ$ rotation error and the best camera-motion consistency) and the best generation quality; and on minute-long out-and-back rollouts ($64$\,s, $384$ latents), its fixed 12-chunk cache still regenerates the starting view -- at rollout lengths where a sliding window has long evicted the evidence and full-KV attention runs out of memory.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.23565 — 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 2026-10-18T07:37:52.787Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).