No AI summary available for this article.
Why It Matters
World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling across radically different systems? We introduce JEPA-Anything, a domain-agnostic framework based on orthogonal predictive factorization (OPF). Extending joint-embedding predictive architectures, OPF decomposes latent targets into complementary factors, learns them through dedicated pathways, and recombines them within a shared predictive design. We evaluate JEPA-Anything across seve...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.20800v1 · Indexed about 1 hour ago