{"ID":23507447,"CreatedAt":"2026-09-18T02:21:44.056544415Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.20800","arxiv_id":"2609.20800","title":"JEPA-Anything: Learning Predictive Models across Different 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","short_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 ortho...","url_abs":"https://arxiv.org/abs/2609.20800","url_pdf":"https://arxiv.org/pdf/2609.20800v1","authors":"[\"Taoyong Cui\",\"Zhongyao Wang\",\"Xinyue Xu\",\"Weiyang Liu\",\"Zhaochen Yu\",\"Yuying Zhang\",\"Qiang Gao\",\"Mengyue Yang\",\"Wanli Ouyang\",\"Pheng Ann Heng\",\"Yingcheng Wu\",\"Zhenfei Yin\",\"Ling Yang\"]","published":"2026-09-17T17:55:57Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":639821,"CreatedAt":"2026-09-18T02:21:44.056544415Z","UpdatedAt":"2026-09-18T02:21:44.056544415Z","DeletedAt":null,"paper_id":23507447,"paper_url":"https://arxiv.org/abs/2609.20800","paper_title":"JEPA-Anything: Learning Predictive Models across Different Worlds","repo_url":"https://github.com/Gen-Verse/JEPA-Anything","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}