Metraipolis › archive › dc_c1c8eff8d345

Motion-guided Contrastive Regularization For Latent World Models — arXiv:2611.06901

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06901
License (as archived)
CC0-1.0
Archived
2026-11-05T18:30:15.672Z
SHA-256 of the archived text
71ab30be72c2872521cab68916352f7687031d7f200edb0b5f5a49ac212ac210
Stable URL of this page
https://metraipolis.com/documento/dc_c1c8eff8d345

How to cite

Motion-guided Contrastive Regularization For Latent World Models — arXiv:2611.06901 — arXiv (en), https://arxiv.org/abs/2611.06901 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c1c8eff8d345 (Metraipolis archive dc_c1c8eff8d345, sha256 71ab30be72c2872521cab68916352f7687031d7f200edb0b5f5a49ac212ac210)
BibTeX
@misc{dcc1c8eff8d345,
  title = {Motion-guided Contrastive Regularization For Latent World Models — arXiv:2611.06901},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06901},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c1c8eff8d345; sha256 71ab30be72c2872521cab68916352f7687031d7f200edb0b5f5a49ac212ac210},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06901. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

JEPA-style world models learn action-conditioned latent dynamics without reconstructing observations, but distributional regularization alone does not ensure that their representations preserve information needed for control. We identify static collapse, a failure mode in which the encoder preserves episode-specific static content while suppressing manipulation-relevant state changes. Because static content is temporally predictable yet diverse across episodes, this failure can persist despite regularizers such as SIGReg. A controlled study on OGBench-Cube shows that introducing randomized backgrounds substantially degrades planning performance while leaving the underlying manipulation task unchanged. To address this problem, we propose motion-guided contrastive regularization. Our approach compares predicted latent transitions with transitions to candidate observations from the same episode, reducing the usefulness of static background identity for distinguishing action outcomes. Optical-flow similarities provide soft contrastive targets, allowing candidates with similar motion to receive similar supervision. Combined with latent prediction and SIGReg, our objective encourages representations to preserve within-episode state distinctions and similarities between related transitions. Our method improves planning success over LeWorldModel (LeWM) from 52% to 78% on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while maintaining comparable performance on four other visual-control benchmarks.

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/2611.06901 — 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 2026-11-05T18:19:49.067Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).