Skip to content

JEPA-Anything: Learning Predictive Models across Different Worlds

Sep 2026 · 2 citations · 38 references
Computer Science

TL;DR

JEPA-Anything, a domain-agnostic framework based on orthogonal predictive factorization (OPF), achieves the lowest one-step and 100-step molecular errors among compared methods in all four systems and supports a common factorized predictive principle across heterogeneous worlds.

Abstract

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 seven domains: vision, biology, clinical trajectories, control, molecular dynamics, physical fields, and weather. Experiments span representation learning, intervention prediction, out-of-distribution generalization, and long-horizon dynamics, including 10 matched dynamics tasks, forecasting of over 1,000 clinical events, and 100-step molecular rollouts across four systems. Against matched JEPA baselines, JEPA-Anything improves reported metrics on all 10 dynamics tasks and reduces single-intervention prediction error on Interventional Pong by 34.8%. It achieves the lowest one-step and 100-step molecular errors among compared methods in all four systems. Beyond prediction, a factor-nominated biological intervention receives experimental support in cell co-cultures, patient-derived organoids, tumor fragments, and mice; latent orbital modes recover the Keplerian scaling exponent with a fitted slope of -1.4991. These results support a common factorized predictive principle across heterogeneous worlds, connecting world modeling with intervention and experimentally grounded scientific discovery. Code: https://github.com/Gen-Verse/JEPA-Anything

View source

Similar papers

#machine learning Preprint Aug 2026

Orthogonal JEPA: Factorized Predictive States for Latent World Models

Method, a latent world-modeling framework based on orthogonal predictive factorization, is introduced, a latent world-modeling framework based on orthogonal predictive factorization that can be used by a readout, decoder, planner, or autoregressive rollout of an underlying system.

Tao-Yong Cui, Pheng-Ann Heng, Wan-Li Ouyang · 0 citations
#artificial intelligence Preprint Oct 2026

Pythia: Toward Foundation World Models for Multimodal Time Series

Time-series foundation models offer a unified approach to forecasting across heterogeneous domains. Textual context and auxiliary observations provide complementary information about temporal dynamics, yet reusable multimodal predictive representations remain underexplored. We introduce Pythia, a foundation world model...

Xilin Dai, Hong-Zhou Chen, Yi-Fan Hu et al. · 2 citations
Preprint Oct 2026

Juno: Taming Predictive Latents for Vision-Language-Action Models

Joint-embedding predictive architectures (JEPAs) predict masked or future observations in representation space, offering a natural source of predictive latents for vision-language-action (VLA) models. Yet making these latents useful across pretraining, policy learning, and deployment requires addressing three failures:...

Yu-Chen Zhu, Chen-Yi Xu, Yu-Lin Zhang et al. · 0 citations
#machine learning Preprint Aug 2026

JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics

This work introduces the cross-predictive JEPA (JEPA-x), which grounds latent dynamics in privileged physical trajectories, and shows that direct physical-state regression improves decodability without improving forecastability or control, indicating that the benefit comes from shaping latent dynamics rather than merel...

Kehan Wen, Ziming Li, Si-Yuan Luo et al. · 2 citations
#artificial intelligence Preprint Sep 2026

RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations

RD-JEPA, a joint-embedding predictive architecture for self-supervised pretraining on reaction-diffusion trajectories, indicates that prediction of future-state representations can support data-efficient adaptation across related reaction-diffusion systems.

Chen-Hao Si, Ming Yan · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.