SOURCE-LINKED INTELLIGENCE

Can 4D Foundation Models Remember?

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Perceiving and remembering the visual world is fundamental to navigating and interacting with our environment. Current 4D foundation models, such as camera-controllable video models or 4D reconstruction models, can perceive and reconstruct dynamic environments, but how well they remember what they have perceived remains an open question. Existing benchmarks largely rely on pixel-level metrics and lack ground truth for objects once they leave the field of view, making them unable to evaluate visual memory in an object-centric manner against references. To fill this gap, we introduce PersistBenc

Read original source ↗ Open in workspace

recordType

paper

region

Global