Metraipolis › archive › dc_7932bcfb2491
Orthogonal JEPA: Factorized Predictive States for Latent World Models — arXiv:2608.20065
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20065
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T11:48:25.065Z
- SHA-256 of the archived text
22ec1db6e08ef6e8bbd24ecc15c196813982b8368e2dcda907307fa0b8acdcdf- Stable URL of this page
https://metraipolis.com/documento/dc_7932bcfb2491
How to cite
Orthogonal JEPA: Factorized Predictive States for Latent World Models — arXiv:2608.20065 — arXiv (en), https://arxiv.org/abs/2608.20065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7932bcfb2491 (Metraipolis archive dc_7932bcfb2491, sha256 22ec1db6e08ef6e8bbd24ecc15c196813982b8368e2dcda907307fa0b8acdcdf)
BibTeX
@misc{dc7932bcfb2491,
title = {Orthogonal JEPA: Factorized Predictive States for Latent World Models — arXiv:2608.20065},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20065},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7932bcfb2491; sha256 22ec1db6e08ef6e8bbd24ecc15c196813982b8368e2dcda907307fa0b8acdcdf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a direct way to learn such states by predicting targets in representation space instead of reconstructing every detail of the observation. Standard JEPAs, however, organize all predictable content through one target embedding and one prediction pathway. In complex systems, this monolithic state can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure. We introduce \method, a latent world-modeling framework based on orthogonal predictive factorization. Learned basis matrices analyze each target state into multiple components, and a dedicated prediction branch estimates each component from a shared context representation. Predictive regression preserves the factor magnitudes required for state synthesis, an orthogonality objective discourages repeated directions, factor-activity regularization maintains variation in projected targets, and online variance regularization discourages coordinate-wise encoder collapse. Predicted components are synthesized into a complete latent state that can be used by a readout, decoder, planner, or autoregressive rollout. The same predictive-state mechanism applies when the target is temporally future, spatially hidden, or another partial observation of the same system. Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.20065 — 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 2026-10-18T11:47:43.336Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).