MISSION REPORT · Research · 2026-07
Conditional Senseiver — Cloud-Gap Filling
Query-conditioned attention that reconstructs complete spatial fields from sparse, cloud-masked satellite observations (nighttime lights).
- PyTorch
- Attention
DOSSIER
Mission report in progress
This mission report is still being written. The archive one-liner above is the summary on file.
Sparse-sensor field
Illustrative demo — not the research model.
A synthetic field of fixed-seed Gaussians is sampled by sensors you place; a worker then draws a radial-basis Gaussian-process posterior and its uncertainty.
