SOURCE-LINKED INTELLIGENCE

AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Existing approaches face a representation trade-off: perspective models operate on local views and must preserve off-screen content over long rollouts, whereas broader spatial coverage is typically obtained by synthesizing full-sphere videos or constructing explicit 3D representations. Motivated by the complementary roles of global context and selective local acuity in visual perception, we present AlayaVista, a camera-controllable streaming video wo

Read original source ↗ Open in workspace

recordType

paper

region

Global