Metraipolis › archive › dc_791410db07b4
Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware — arXiv:2609.37107
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37107
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:27:45.498Z
- SHA-256 of the archived text
3aa85f3b14309f37b585e21e07db6813aadeccabca9013b1103a962d7e419096- Stable URL of this page
https://metraipolis.com/documento/dc_791410db07b4
How to cite
Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware — arXiv:2609.37107 — arXiv (en), https://arxiv.org/abs/2609.37107 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_791410db07b4 (Metraipolis archive dc_791410db07b4, sha256 3aa85f3b14309f37b585e21e07db6813aadeccabca9013b1103a962d7e419096)
BibTeX
@misc{dc791410db07b4,
title = {Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware — arXiv:2609.37107},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37107},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_791410db07b4; sha256 3aa85f3b14309f37b585e21e07db6813aadeccabca9013b1103a962d7e419096},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37107. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present Waypoint 1.5, a real-time diffusion world model for interactive video generation on consumer-grade hardware. Unlike general video diffusion models, interactive world models (iWMs) must respond to dense user controls under strict latency and throughput constraints. Waypoint 1.5 is pre-trained on 100,000 hours of diverse, control-aligned video game data across hundreds of games, and generates playable video conditioned on full keyboard and mouse input. The model includes two resolution variants that run across a wide spectrum of consumer hardware. To characterize this unique setting, we distinguish rendered FPS, latent FPS, and control rate. We describe the data pipeline, architecture, training methodology, and runtime system behind Waypoint 1.5. We evaluate interactivity through latency and throughput. Finally, we discuss the safety and ethics considerations unique to iWMs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.HC). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.37107 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T16:58:50.356Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).