Preprint
Jul 2026
StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design
StepX-Edge is presented, a 0.9B-parameter on-device UI vision-language model that resolves this tension through three-layer co-design of architecture, training, and deployment, and achieves the strongest overall UI understanding among<=1B models.
Yin Wang, Haotian Hu, J. Han et al.
· 1 citation