Metraipolis › archive › dc_09e3380a3de4

FORCE: Factorized Object Relations for Counterfactual Editing in Video World Models — arXiv:2611.00023

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00023
License (as archived)
CC0-1.0
Archived
2026-11-03T11:39:44.649Z
SHA-256 of the archived text
381c2d1f28aeae25e5ccf002fb88e921718545dacf4e605f6713a0c58368e523
Stable URL of this page
https://metraipolis.com/documento/dc_09e3380a3de4

How to cite

FORCE: Factorized Object Relations for Counterfactual Editing in Video World Models — arXiv:2611.00023 — arXiv (en), https://arxiv.org/abs/2611.00023 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09e3380a3de4 (Metraipolis archive dc_09e3380a3de4, sha256 381c2d1f28aeae25e5ccf002fb88e921718545dacf4e605f6713a0c58368e523)
BibTeX
@misc{dc09e3380a3de4,
  title = {FORCE: Factorized Object Relations for Counterfactual Editing in Video World Models — arXiv:2611.00023},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00023},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09e3380a3de4; sha256 381c2d1f28aeae25e5ccf002fb88e921718545dacf4e605f6713a0c58368e523},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00023. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World models predict how scenes evolve, but they are difficult to interrogate: given a model that forecasts a video, one cannot easily ask what would have happened had a particular interaction between two objects been different. We present Factorized Object Relations for Counterfactual Editing (FORCE), a world model that infers pairwise interactions from raw video without supervision and represents each as an explicit latent per object pair, so that a relation can be removed, changed, transferred or introduced directly. Objects are extracted by slot attention over frozen self-supervised features; a relation encoder infers each pair latent from a short observation window, and an interaction head turns it into a force. The latent is held fixed across the rollout, so an edit persists rather than being recomputed, and every edit acts on the model's own quantities with no mapping to simulator parameters. We evaluate in a simulated environment where the true outcome of an edit is available, scoring the change each edit induces against the change the simulator produces under the same operation. On held-out clips, FORCE's edits made from video agree with the simulator's response at 0.19 to 0.37 on our effect-based score; trained and scored on exact object positions instead, the same architecture reaches 0.57 to 0.85. The gap therefore lies not in the learned relational dynamics but in perception: what bounds an edit is how precisely objects can be located from video, and the precision editing needs lies just beyond what current object-centric perception delivers. Closing that gap is a concrete target for making counterfactual world models work from video.

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/2611.00023 — 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 2026-11-03T11:06:37.351Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).