Metraipolis › archive › dc_9a67dc71c8ec

SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors — arXiv:2608.04060

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04060
License (as archived): CC0-1.0
Archived: 2026-10-31T11:13:30.727Z
SHA-256 of the archived text: 735ca3320df8529317081acfe7e1cdc412315da6b1ae4bdd6f6fdba514852023
Stable URL of this page: https://metraipolis.com/documento/dc_9a67dc71c8ec

How to cite

SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors — arXiv:2608.04060 — arXiv (en), https://arxiv.org/abs/2608.04060 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9a67dc71c8ec (Metraipolis archive dc_9a67dc71c8ec, sha256 735ca3320df8529317081acfe7e1cdc412315da6b1ae4bdd6f6fdba514852023)

BibTeX

@misc{dc9a67dc71c8ec,
  title = {SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors — arXiv:2608.04060},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04060},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9a67dc71c8ec; sha256 735ca3320df8529317081acfe7e1cdc412315da6b1ae4bdd6f6fdba514852023},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04060. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural maps. We introduce SJEPA, a reconstruction-free JEPA framework that learns predictive representations whose induced dynamics admit compact symbolic descriptions. Its hybrid transition combines a symbolic law with a regularised neural correction for dynamics outside the selected grammar. The central principle is to learn the simplest adequate dynamics: representation constraints preserve informative, non-collapsed predictive coordinates, while operator compression favours low-complexity symbolic-neural transitions that remain predictively adequate. We formalise this principle through induced-dynamics complexity, analyse predictive-coordinate non-identifiability, and show that unconstrained operator compression creates a direct shortcut to representation collapse. The framework supports both alternating representation-equation learning and symbolic dynamics fitted to fixed representations. In controlled pendulum experiments, joint learning discovers substantially simpler symbolic dynamics with lower long-horizon rollout error and divergence than post-hoc fitting, while an unconstrained one-step diagnostic realises the predicted collapse shortcut. Under grammar misspecification, correction regularisation preserves the representable symbolic mechanism and directs the neural component towards residual dynamics. The results expose a controllable trade-off among predictive fidelity, representation quality, symbolic parsimony, and symbolic-neural allocation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04060 — 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 2026-10-31T11:02:13.473Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).