Beyond Domain-Specific World Models: JEPA-Anything Uses 1 Recipe for 7 Fields

What happened

Tested across 7 domains, it beat matched JEPA baselines on all 10 dynamics tasks and cut Interventional Pong intervention error by 34.8%. Researchers from PhAI Labs, CUHK, Fudan, Stanford, Oxford and Princeton have released JEPA-Anything , a domain-agnostic framework for building world models.

It extends joint-embedding predictive architectures (JEPAs) with a method called Orthogonal Predictive Factorization (OPF) . The research team tested it across 7 domains: vision, biology, clinical trajectories, control, molecular dynamics, physical fields and weather.

JEPA-Anything splits a JEPA's single latent target into 4 orthogonal factors, each with its own predictor. Instead of designing a new predictive model for each field, it applies one shared learning recipe to very different systems.

Key facts

• Researchers from PhAI Labs, CUHK, Fudan, Stanford, Oxford and Princeton have — released: JEPA-Anything , a domain-agnostic framework for building world models
• The research team — tested: it across 7 domains: vision, biology, clinical trajectories, control, molecular dynamics, physical fields and weather