Metraipolis › archive › dc_cdf72af4f72d

Enhancing Latent World Models with Associative Memory — arXiv:2610.19683

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19683
License (as archived)
CC0-1.0
Archived
2026-10-15T14:17:43.456Z
SHA-256 of the archived text
b36f4d9ce29cc73828d933299879f603cf7613dd97a4e47f7383312c7d559b08
Stable URL of this page
https://metraipolis.com/documento/dc_cdf72af4f72d

How to cite

Enhancing Latent World Models with Associative Memory — arXiv:2610.19683 — arXiv (en), https://arxiv.org/abs/2610.19683 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdf72af4f72d (Metraipolis archive dc_cdf72af4f72d, sha256 b36f4d9ce29cc73828d933299879f603cf7613dd97a4e47f7383312c7d559b08)
BibTeX
@misc{dccdf72af4f72d,
  title = {Enhancing Latent World Models with Associative Memory — arXiv:2610.19683},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19683},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdf72af4f72d; sha256 b36f4d9ce29cc73828d933299879f603cf7613dd97a4e47f7383312c7d559b08},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19683. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World models trained via latent dynamics offer a scalable path for embodied planning, yet existing methods suffer from representational collapse, computational overhead, and limited long-horizon capability. We introduce a memory-enhanced latent world model that augments JEPA-style prediction with a content-addressable memory bank. Our approach learns high-level representations directly from observations, operating at multiple temporal scales within a shared latent space, and conditions predictions via adaptive layer normalization. To prevent collapse and ensure effective memory usage, we design two complementary losses that encourage slot diversity and balanced temporal utilization. Experiments on PushT, Tworoom, Reacher, and OGBCube demonstrate that our method achieves state-of-the-art performance with a lightweight architecture, outperforming conventional latent world models on long-horizon planning tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.19683 — 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 2026-10-15T13:53:35.627Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).