SOURCE-LINKED INTELLIGENCE

JEPA-Anything: Learning Predictive Models across Different Worlds

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global