CUHK-Shenzhen, NUS, HKUST, NVIDIA and MSRA · Long-Horizon World Model

SolarWM

An open video world-model framework trained on five-second clips that runs minute- to hour-scale real-time inference while keeping interaction responsive and the world coherent. Four backbones at different scales - SolarWM-Wan-5B, Wan-14B, LTX-2.5 and Minimax-H3 - across causal student and bidirectional models. Ships an open dataset of 1.43M clips at 25TB with the full processing pipeline including camera annotation and filtering, plus code and checkpoints; dataset access needs a request form.