COP-GEN models multimodal Copernicus Earth observation data as conditional distributions via a latent diffusion transformer, producing diverse physically consistent outputs and covering 90% of the real observation manifold on a new stochastic benchmark.
Mmearth: Exploring multi-modal pretext tasks for geospatial representation learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A proxy consistency loss trains location encoders on proxy geographic data to outperform direct input fusion or frozen embeddings for air quality and poverty mapping with sparse labels.
citing papers explorer
-
COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data
COP-GEN models multimodal Copernicus Earth observation data as conditional distributions via a latent diffusion transformer, producing diverse physically consistent outputs and covering 90% of the real observation manifold on a new stochastic benchmark.
-
A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoders
A proxy consistency loss trains location encoders on proxy geographic data to outperform direct input fusion or frozen embeddings for air quality and poverty mapping with sparse labels.