Beyond Pixel Histories: World Models with Persistent 3D State
Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D representation of the environment, meaning 3D consistency must be implicitly learned from data, and spatial memory is restricted to limited temporal context windows. This results in an unrealistic user experience and presents significant obstacles to downstream tasks such as training agents. To address this, we present PERSIST, a new paradigm of world model which simulates the evolution of a latent 3D scene: environment, camera, and renderer. This allows us to synthesise new frames with persistent spatial memory an...
| Authors | Samuel Garcin, Thomas Walker, Steven McDonagh et al. |
|---|---|
| Primary category | cs.CV |
| Published | 3 March 2026 |
| Last updated at source | 3 June 2026 |
Connected in the knowledge graph
- PERSIST-team/persist-eval-sampleDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.