JEPA-Anything：跨不同世界学习预测模型
JEPA-Anything: Learning Predictive Models across Different Worlds
AI总结：
提出领域无关的JEPA-Anything框架，基于正交预测分解，在七个领域验证了通用预测原则，提升动力学预测并获实验支持。
AI中文摘要：
世界建模使智能体能够预测后果、指导干预并从交互中学习。然而，预测模型仍然局限于特定领域：是否存在一种通用的学习原则，能够支持跨根本不同系统的世界建模？我们提出了JEPA-Anything，一种基于正交预测分解（OPF）的领域无关框架。扩展联合嵌入预测架构，OPF将潜在目标分解为互补因子，通过专用路径学习它们，并在共享预测设计中重新组合。我们在七个领域评估了JEPA-Anything：视觉、生物学、临床轨迹、控制、分子动力学、物理场和天气。实验涵盖表示学习、干预预测、分布外泛化和长时程动力学，包括10个匹配的动力学任务、对超过1000个临床事件的预测，以及跨四个系统的100步分子展开。与匹配的JEPA基线相比，JEPA-Anything在所有10个动力学任务上改进了报告指标，并将Interventional Pong上的单次干预预测误差降低了34.8%。在所有四个系统中，它实现了所比较方法中最低的一步和100步分子误差。在预测之外，一个因子指定的生物干预在细胞共培养、患者来源类器官、肿瘤碎片和小鼠中获得了实验支持；潜在轨道模式恢复了开普勒标度指数，拟合斜率为-1.4991。这些结果支持跨异质世界的共同因子化预测原则，将世界建模与干预和实验基础的科学发现联系起来。代码：此https URL
英文摘要：
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
