Introduces a 'geospatial model foundry' that learns unified representations from the weights of existing models rather than raw data.
March 25, 2026
Original Paper
GeoSANE: Learning Geospatial Representations from Models, Not Data
arXiv · 2603.23408
The Takeaway
This shifts foundation model development from data pre-training to weight generation. By treating model weights as the primary source of knowledge, GeoSANE can generate task-specific networks on-demand that outperform models trained from scratch or distilled via standard methods.
From the abstract
Recent advances in remote sensing have led to an increase in the number of available foundation models; each trained on different modalities, datasets, and objectives, yet capturing only part of the vast geospatial knowledge landscape. While these models show strong results within their respective domains, their capabilities remain complementary rather than unified. Therefore, instead of choosing one model over another, we aim to combine their strengths into a single shared representation. We in