Ophthalmic decision-making depends on subtle lesion-scale cues interpreted across multimodal imaging and over time, yet most medical foundation models remain static and degrade under modality and acquisition shifts. Here we introduce EyeWorld, a generative world model that conceptualizes the eye as a partially observed dynamical system grounded in clinical imaging. EyeWorld learns an observation-stable latent ocular state shared across modalities, unifying fine-grained parsing, structure-preserving cross-modality translation and quality-robust enhancement within a single framework. Longitudinal supervision further enables time-conditioned state transitions, supporting forecasting of clinically meaningful progression while preserving stable anatomy. By moving from static representation learning to explicit dynamical modeling, EyeWorld provides a unified approach to robust multimodal interpretation and prognosis-oriented simulation in medicine.
@article{arxiv.2603.14039,
title = {EyeWorld: A Generative World Model of Ocular State and Dynamics},
author = {Ziyu Gao and Xinyuan Wu and Xiaolan Chen and Zhuoran Liu and Ruoyu Chen and Bowen Liu and Bingjie Yan and Zhenhan Wang and Kai Jin and Jiancheng Yang and Yih Chung Tham and Mingguang He and Danli Shi},
journal= {arXiv preprint arXiv:2603.14039},
year = {2026}
}