3 papers
cs.LG2026
Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism
Chenwei Cui, Rockwell Jackson, Benjamin Joseph Herrera +2
Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional computation, with Expert…
cs.CV2026
GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI
Naomi Simumba, Nils Lehmann, Paolo Fraccaro +9
Geospatial Foundation Models (GeoFMs) are transforming Earth Observation (EO), but evaluation lacks standardized protocols. GEO-Bench-2 addresses this with a comprehensive framewor…
cs.CV2025
Cropland Mapping using Geospatial Embeddings
Ivan Zvonkov, Gabriel Tseng, Inbal Becker-Reshef +1
Accurate and up-to-date land cover maps are essential for understanding land use change, a key driver of climate change. Geospatial embeddings offer a more efficient and accessible…