Liu, J. et al. 2026. SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 9 (Mar. 2026), 7168–7178. DOI:https://doi.org/10.1609/aaai.v40i9.37653.