JEPA-Anything proposes one world-modeling framework across vision, biology, weather and more
gekobraa · x · 2026-09-21
A new paper introduces JEPA-Anything, a domain-agnostic world-modeling framework built on Orthogonal Predictive Factorization (OPF): a single JEPA latent state is decomposed into complementary factors that predict different parts of a system, then recombined in a shared predictive design.
- Evaluated across seven domains: vision, biology, clinical trajectories, control, molecular dynamics, physical fields, and weather.
- Improves reported metrics on all 10 matched dynamics tasks vs matched JEPA baselines; cuts single-intervention prediction error on Interventional Pong by 34.8%.
- Lowest one-step and 100-step molecular rollout errors among compared methods in all four systems.
- Latent orbital modes recover Kepler's scaling exponent (fitted slope -1.4991).
- A factor-nominated biological intervention gained experimental support in cell co-cultures, patient-derived organoids, tumor fragments and mice.
More from Research
- minpts-check: one-run predictor tells if your HDBSCAN clusters survive min_samples changes — leland_mcinnes · 2026-11-12
- Architecture study sparks monitoring concerns over a multi-hop planning spike — ChowdhuryNeil · 2026-11-12
- SGLang Megakernel Pushes Muse Spark to 1,109 tok/s, 2.1x Over Baseline — hsu_byron · 2026-11-12
- ArcGrav: a cross-model Agent Control Language to cut token overhead — ArchitecturalGravity · 2026-11-12
- Open-source dual-arm robot solves tangram puzzles with 90 demos, ~60% success — DanGrover · 2026-11-12
- FutureHouse's deslopper trains Kosmos to write indistinguishably from human experts — proteinrosh · 2026-11-12