arXiv Artificial Intelligence

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

1 hour ago 06.08.2026 07:00 👁 1 views
SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors

Quick summary

arXiv:2608.04060v1 Announce Type: cross Abstract: 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 const

Key takeaways

  • arXiv:2608.04060v1 Announce Type: cross Abstract: 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.

Why it matters

The significance is not only the legal text but how it changes product design. Decisions around “SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors” may reshape data collection, model training, output accountability and market access.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗