Metraipolis › archive › dc_b2e227564dde

IntactWorld: Joint World Modeling with Intact Features — arXiv:2610.11174

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11174
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:21.496Z
SHA-256 of the archived text
b82ed9ce9da2acf691aa2e6301f90033043d90b79e1674ea84aaba5e94fa6ba3
Stable URL of this page
https://metraipolis.com/documento/dc_b2e227564dde

How to cite

IntactWorld: Joint World Modeling with Intact Features — arXiv:2610.11174 — arXiv (en), https://arxiv.org/abs/2610.11174 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2e227564dde (Metraipolis archive dc_b2e227564dde, sha256 b82ed9ce9da2acf691aa2e6301f90033043d90b79e1674ea84aaba5e94fa6ba3)
BibTeX
@misc{dcb2e227564dde,
  title = {IntactWorld: Joint World Modeling with Intact Features — arXiv:2610.11174},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11174},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2e227564dde; sha256 b82ed9ce9da2acf691aa2e6301f90033043d90b79e1674ea84aaba5e94fa6ba3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11174. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While recent video generation models synthesize highly realistic visuals, they lack a genuine understanding of intrinsic real-world logic. Existing methods attempt to understand the world by internalizing diverse world knowledge, yet constrained by computational overhead or dimensionality alignment, their learning processes inevitably compress features, causing a severe loss of structural information. To address this, we propose \textbf{IntactWorld}, a \textbf{Joint World Modeling Architecture} utilizing uncompressed \textbf{Intact Features}. Since data naturally reside on a low-dimensional manifold within a high-dimensional space, predicting the flow velocity $v$ within this uncompressed high-dimensional space induces a severe manifold gap. To successfully eliminate this optimization bottleneck, our framework instead predicts the clean feature $x_0$ at intermediate layers. Furthermore, to mitigate the computational overhead of incorporating complete world knowledge, we introduce a \textit{Full-to-Compact Training Paradigm}. By replacing raw full features with highly refined CLS tokens, this paradigm enables efficient single-branch guidance, reducing spatial memory consumption by 11.4\% and cutting inference latency by 43.8\%. Extensive evaluations demonstrate the effectiveness of IntactWorld, outperforming established baselines by 2.46 points on the VBench 2.0 benchmark.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.11174 — 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 2026-10-09T05:55:07.190Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).