Researchers release JEPA-Anything
JEPA-Anything released — a domain-agnostic predictive framework that decomposes the latent target into complementary factors and learns each through a dedicated pathway (OPF). Applied to 7 domains — vision, biology, clinical trajectories, control, molecular dynamics, physical fields and weather — it improved on baselines in all 10 dynamics tasks, cut intervention-prediction error on Interventional Pong by 34.8%, achieved the lowest error at both 1 step and 100 steps on 4 molecular systems, predicted more than 1,000 kinds of clinical events, and recovered the Kepler scaling exponent with a slope of -1.4991.
Why it matters
A case of a JEPA-family predictive architecture moving beyond video to molecules, clinical data and weather within the same framework. It reflects a trend toward defining world models not as "video generation" but as "domain-agnostic state prediction".
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2609.20800Added in Week 39, 2026 · See that week