Preprint
Sep 2026
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training across heterogeneous data sources and video backbones is challenging: datasets differ in temporal scale, camera geometry, visual quality, motion, and captioning styles...
Jun-Chao Huang, Gui-An Fang, Sheng-Ju Qian et al.
· 1 citation