Metraipolis › archive › dc_0920f453e69a

JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics — arXiv:2608.24044

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24044
License (as archived)
CC0-1.0
Archived
2026-10-18T06:35:51.162Z
SHA-256 of the archived text
61b6f806a30ba1b442b3b87808931403a64a14a0d094770479bebebb866a828a
Stable URL of this page
https://metraipolis.com/documento/dc_0920f453e69a

How to cite

JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics — arXiv:2608.24044 — arXiv (en), https://arxiv.org/abs/2608.24044 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0920f453e69a (Metraipolis archive dc_0920f453e69a, sha256 61b6f806a30ba1b442b3b87808931403a64a14a0d094770479bebebb866a828a)
BibTeX
@misc{dc0920f453e69a,
  title = {JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics — arXiv:2608.24044},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24044},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0920f453e69a; sha256 61b6f806a30ba1b442b3b87808931403a64a14a0d094770479bebebb866a828a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24044. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Latent world models plan by predicting how candidate actions advance learned latent dynamics. In self-predictive models, however, the encoder and predictor are optimized jointly and can co-adapt to latent transitions that are easy to predict but weakly constrained by the physical evolution of the scene. We introduce the cross-predictive JEPA (JEPA-x), which grounds latent dynamics in privileged physical trajectories. JEPA-x treats visual observations and physical states as corresponding views of the same action-conditioned trajectory, advances both through a shared predictor, and matches each prediction to the future representations of both modalities. This encourages the action-conditioned predictor to learn a common transition rule across the two views. Privileged physical state is used only during training, leaving a visual-only model at deployment. Empirical results show that JEPA-x reduces the rollout drift of a newly fitted predictor from $0.361$ to $0.104$ and increases mean control success from $53.6\%$ to $78.2\%$ on a multi-task suite spanning six evaluation subfamilies. We additionally show that direct physical-state regression improves decodability without improving forecastability or control, indicating that the benefit comes from shaping latent dynamics rather than merely encoding physical variables.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.24044 — 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 2026-10-18T06:28:52.211Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).