JEPA-Anything: Learning Predictive Models across Different Worlds
Ranking
Overall
86
Content
95
Popularity
66
Observed public metrics from 1 member.
Merged summary
TL;DR - JEPA-Anything is a domain-agnostic world-modeling framework that factorizes latent prediction targets into complementary components. It improves predictive performance across seven heterogeneous domains and links learned representations to interventions and experimentally supported scientific findings.
- Orthogonal predictive factorization extends JEPA by learning target factors through dedicated pathways and recombining them in a shared predictive architecture.
- The framework outperforms matched JEPA baselines on all 10 dynamics tasks and reduces single-intervention prediction error in Interventional Pong by 34.8%.
- It achieves the lowest reported one-step and 100-step molecular-dynamics errors among compared methods across four systems.
- Learned factors produced a biologically nominated intervention supported in multiple experimental models and recovered Keplerian scaling with a fitted exponent of -1.4991.
Sources (1)
JEPA-Anything: Learning Predictive Models across Different Worlds
Public signals
Hugging Face upvotes 70
TL;DR - JEPA-Anything is a domain-agnostic world-modeling framework that factorizes latent prediction targets into complementary components. It improves predictive performance across seven heterogeneous domains and links learned representations to interventions and experimentally supported scientific findings.
- Orthogonal predictive factorization extends JEPA by learning target factors through dedicated pathways and recombining them in a shared predictive architecture.
- The framework outperforms matched JEPA baselines on all 10 dynamics tasks and reduces single-intervention prediction error in Interventional Pong by 34.8%.
- It achieves the lowest reported one-step and 100-step molecular-dynamics errors among compared methods across four systems.
- Learned factors produced a biologically nominated intervention supported in multiple experimental models and recovered Keplerian scaling with a fitted exponent of -1.4991.