Reading, Writing, Sharing, and Interacting with the World through Video

A survey examines video foundation models and video world models through a world modeling lens, organizing the literature around four operations: reading infers world properties from observed video, writing synthesizes video from specified or learned world conditions, sharing integrates understanding and generation through common modeling mechanisms, and interacting predicts and updates world states under actions and evolving observations. The approach treats observed video as a partial, lossy, and temporally ordered projection of a latent temporal world, distinguishing temporal coherence in sequences from consistency in the underlying world state.